Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
18265 papers
Generative neural models have recently achieved state-of-the-art results for constituency parsing. However, without a feasible search procedure, their use has so far been limited to reranking the output of external parsers in which decoding is more tractable. We describe an alternative to the conventional action-level beam search used for discriminative neural models that enables us to decode directly in these generative models. We then show that by improving our basic candidate selection strategy and using a coarse pruning function, we can improve accuracy while exploring significantly less of the search space. Applied to the model of Choe and Charniak (2016), our inference procedure obtains 92.56 F1 on section 23 of the Penn Treebank, surpassing prior state-of-the-art results for single-model systems.
OBJECTIVE: New MRI sequences based on rapid radial acquisition have reduced gradient noise. The purpose of this study was to compare Silent T1-weighted and unenhanced MR angiography (MRA) against conventional sequences in a clinical population. MATERIALS AND METHODS: The study cohort consisted of 40 patients with suspected brain metastases (median age, 60 years; range, 23-91 years) who underwent T1-weighted contrast-enhanced MRI and 51 patients with suspected vascular lesions or cerebral ischemia (median age, 60 years; range, 16-94 years) who underwent unenhanced intracranial MRA. Three neuroradiologists reviewed the images blindly and rated several measures of image quality on a 5-point Likert scale. Reviewers recorded the number of enhancing lesions and whether Silent images were better than, worse than, or equivalent to conventional images. RESULTS: For T1-weighted MR images, ratings were slightly lower for Silent versus conventional images, except for diagnostic confidence. Although more lesions were detected on conventional images, this difference was not statistically significant; agreement was seen in 88% of cases. In 48% of cases, T1-weighted scans were deemed equivalent, but when a preference existed, it was usually for conventional images (38% vs 14%). Conventional MRA images were rated higher on all image quality metrics and were strongly preferred (reviewers preferred conventional images in 69% of cases, rated the images as equivalent in 27% of cases, and preferred Silent images in 4% of cases). In some cases, artifacts on Silent images caused reduced vessel caliber, vessel irregularities, and even absent vessels. CONCLUSION: Although conventional T1-weighted images were preferred overall, most Silent T1-weighted images were rated as equivalent to or better than conventional images and represent a potential alternative for imaging of noise-averse patients. Silent MRA scored significantly worse and could not be recommended at this time, suggesting that it requires additional refinement before routine clinical use.
BACKGROUND: Formulaic expressions, including idioms and other fixed expressions, comprise a significant proportion of discourse. Although much has been written about this topic, controversy remains about their psychological status. An important claim about formulaic expressions, that they are known to native speakers, has seldom been directly demonstrated. This study tested the hypothesis that formulaic expressions are known and stored as whole unit mental representations by performing three perceptual experiments. METHOD: Listeners transcribed two kinds of spectrally-degraded spoken sentences, half formulaic, and half novel, newly created expressions, matched for grammar and length. Two familiarity ratings, usage and exposure, were obtained from listeners for each expression. Text frequency data for the stimuli and their constituent words were obtained using a spoken corpus. RESULTS: Participants transcribed formulaic more successfully than literal utterances. Usage and familiarity ratings correlated with accuracy, but formulaic utterances with low ratings were also transcribed correctly. Phrase types differed significantly in text frequency, but word frequency counts did not differentiate the two kinds of expressions. DISCUSSION: These studies provide new converging evidence that formulaic expressions are encoded and processed as whole units, supporting a dual-process model of language processing, which assumes that grammatical and formulaic expressions are differentially processed.
Sentiment analysis on Chinese text has intensively studied. The basic task for related research is to construct an affective lexicon and thereby predict emotional scores of different levels. However, finite lexicon resources make it difficult to effectively and automatically distinguish between various types of sentiment information in Chinese texts. This IJCNLP2017-Task2 competition seeks to automatically calculate Valence and Arousal ratings within the hierarchies of vocabulary and phrases in Chinese. We introduce a regression methodology to automatically recognize continuous emotional values, and incorporate a word embedding technique. In our system, the MAE predictive values of Valence and Arousal were 0.811 and 0.996, respectively, for the sentiment dimension prediction of words in Chinese. In phrase prediction, the corresponding results were 0.822 and 0.489, ranking sixth among all teams.
In this paper, we propose efficient and less resource-intensive strategies for parsing of code-mixed data. These strategies are not constrained by in-domain annotations, rather they leverage pre-existing monolingual annotated resources for training. We show that these methods can produce significantly better results as compared to an informed baseline. Besides, we also present a data set of 450 Hindi and English code-mixed tweets of Hindi multilingual speakers for evaluation. The data set is manually annotated with Universal Dependencies.
Abstract The CELEX lexical database ( Baayen, Piepenbrock & van Rijn 1995 ) was developed in the 1990s, providing a database of the syntactic, morphological, phonological and orthographic forms of between 50,000 and 125,000 words of Dutch, English and German. This database was used as the basis for the development of the PolyLex lexicons, which included syntactic, morphological and phonological information for around 3,000 words of Dutch, English and German. Orthographic information was subsequently added in the PolyOrth project. The PolyOrth project was based on the assumption that the underlying, lexical phonological forms could be used to derive the surface orthographic forms by means of a combination of phoneme-grapheme mappings and sets of autonomous spelling rules for each language. One of the complications encountered during the project was the fact that the phonological forms in CELEX were not always genuinely underlying forms which made deriving the orthographic forms tricky. This paper discusses the nature and status of underlying phonological forms, their relation to orthography and the issues of finding this information in databases.
We propose a simple extension to the ReLU-family of activation functions that allows them to shift the mean activation across a layer towards zero. Combined with proper weight initialization, this alleviates the need for normalization layers. We explore the training of deep vanilla recurrent neural networks (RNNs) with up to 144 layers, and show that bipolar activation functions help learning in this setting. On the Penn Treebank and Text8 language modeling tasks we obtain competitive results, improving on the best reported results for non-gated networks. In experiments with convolutional neural networks without batch normalization, we find that bipolar activations produce a faster drop in training error, and results in a lower test error on the CIFAR-10 classification task.
In this study, we presented pictorial representations of happy, neutral, and fearful expressions projected in the eye regions to determine whether the eye region alone is sufficient to produce a context effect. Participants were asked to judge the valence of surprised faces that had been preceded by a picture of an eye region. Behavioral results showed that affective ratings of surprised faces were context dependent. Prime-related ERPs with presentation of happy eyes elicited a larger P1 than those for neutral and fearful eyes, likely due to the recognition advantage provided by a happy expression. Target-related ERPs showed that surprised faces in the context of fearful and happy eyes elicited dramatically larger C1 than those in the neutral context, which reflected the modulation by predictions during the earliest stages of face processing. There were larger N170 with neutral and fearful eye contexts compared to the happy context, suggesting faces were being integrated with contextual threat information. The P3 component exhibited enhanced brain activity in response to faces preceded by happy and fearful eyes compared with neutral eyes, indicating motivated attention processing may be involved at this stage. Altogether, these results indicate for the first time that the influence of isolated eye regions on the perception of surprised faces involves preferential processing at the early stages and elaborate processing at the late stages. Moreover, higher cognitive processes such as predictions and attention can modulate face processing from the earliest stages in a top-down manner.
It is widely believed that different parts of a classical Chinese poem vary in syntactic properties. The middle part is usually parallel, i.e. the two lines in a couplet have similar sentence structure and part of speech; in contrast, the beginning and final parts tend to be non-parallel. Imagistic language, dominated by noun phrases evoking images, is concentrated in the middle; propositional language, with more complex grammatical structures, is more often found at the end. We present the first quantitative analysis on these linguistic phenomena—syntactic parallelism, imagistic language, and propositional language—on a treebank of selected poems from the Complete Tang Poems. Written during the Tang Dynasty between the 7th and 9th centuries CE, these poems are often considered the pinnacle of classical Chinese poetry. Our analysis affirms the traditional observation that the final couplet is rarely parallel; the middle couplets are more frequently parallel, especially at the phrase rather than the word level. Further, the final couplet more often takes a non-declarative mood, uses function words, and adopts propositional language. In contrast, the beginning and middle couplets employ more content words and tend toward imagistic language.
This article is about concept of electronic service that detects violations of normality in the creating and using of terminology units and provides recommendations for term using. This concept is adapted for specialists in electric power engineering and can be used for websites about this industry. Using these websites ensure compliance with linguistic norms in professional communication. Scheme of functioning of terminological online assistant for electric power engineering specialists is developed. The search and terms adding algorithm of terminological online assistant for electric power engineering specialists is described in this article. Entering a term into the search box, checking normality of term using database system, proposing list of recommended term equivalent, adding term to database system and giving results are the main components of developed algorithm.
We present the TurkuNLP entry in the CoNLL 2017 Shared Task on Multilingual Parsing from Raw Text to Universal Dependencies. The system is based on the UDPipe parser with our focus being in exploring various techniques to pre-train the word embeddings used by the parser in order to improve its performance especially on languages with small training sets. The system ranked 11th among the 33 participants overall, being 8th on the small treebanks, 10th on the large treebanks, 12th on the parallel test sets, and 26th on the surprise languages.
Unsupervised dependency parsing aims to learn a dependency parser from unannotated sentences. Existing work focuses on either learning generative models using the expectation-maximization algorithm and its variants, or learning discriminative models using the discriminative clustering algorithm. In this paper, we propose a new learning strategy that learns a generative model and a discriminative model jointly based on the dual decomposition method. Our method is simple and general, yet effective to capture the advantages of both models and improve their learning results. We tested our method on the UD treebank and achieved a state-ofthe-art performance on thirty languages.
<strong>Berkeley parser model for Korean: Sejong treebank</strong> Jungyeul Park, Jeen-Pyo Hong, and Jeong-Won Cha (2016). Korean Language Resources for Everyone. In Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation (PACLIC 30). Seoul, Korea. [pdf] @inproceedings{park-hong-cha:2016:PACLIC, <br> address = {Seoul, Korea}, <br> author = {Park, Jungyeul and Hong, Jeen-Pyo and Cha, Jeong-Won}, <br> booktitle = {Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation (PACLIC 30)}, <br> pages = {49--58}, <br> title = {{Korean Language Resources for Everyone}}, <br> year = {2016} <br> } It requires Espresso's POS tagging results for input. Espresso is available at https://zenodo.org/record/884606
Several recent studies have demonstrated that people intuitively make consistent matches between classical music and specific wines. It is not clear, however, what governs such crossmodal mappings. Here, we assess the role of emotion—specifically different dimensional aspects of valence, arousal, and dominance—in mediating such mappings. Participants matched three different red wines to three different pieces of classical music. Subsequently, they made emotion ratings separately for each wine and each musical selection. The results revealed that certain wine–music pairings were rated as being significantly better matches than others. More importantly, there was evidence that the participants’ dominance and arousal ratings for the wines and the music predicted their matching rating for each wine–music pairing. These results therefore support the view that wine–music associations are not arbitrary but can be explained, at least in part, by common emotional associations.
Representing multiple compositions of human language has been a difficult task due to the complex hierarchical and compositional nature of language. Hierarchical structures are one of the architectures which can be used to capture such compositionalities. In this paper, we introduce temporal hierarchies to the Neural Language Model (NLM) with the help of a Deep Gated Recurrent Neural Network with adaptive timescales to help represent multiple compositions of language. We demonstrate that by representing multiple compositions of language in a deep recurrent neural network architecture, we can improve the performance of Language Models without complex hierarchical architectures. We report the performance of the proposed model using the popular Penn Treebank (PTB) dataset. The results show that by using the multiple timescale concept in an NLM, we can achieve better perplexities compared to the existing baselines.
142:337-350), this study examined whether these abnormalities also characterize individuals at clinical high risk for MDD. We systematically explored the impact of family risk status and personal history of depression and anxiety on three distinct stages of emotional processing comprising the late positive potential (LPP). ERPs (72 channels) were recorded from 74 high and 53 low risk individuals (age 13-59 years, 58 male) during a visual half-field paradigm using highly-controlled pictures of cosmetic surgery patients showing disordered (negative) or healed (neutral) facial areas before or after treatment. Reference-free current source density (CSD) transformations of ERP waveforms were quantified by temporal principal components analysis (tPCA). Component scores of prominent CSD-tPCA factors sensitive to emotional content were analyzed via permutation tests and repeated measures ANOVA for mixed factorial designs with unstructured covariance matrix, including gender, age and clinical covariates. Factor-based distributed inverse solutions provided descriptive estimates of emotional brain activations at group level corresponding to hierarchical activations along ventral visual processing stream. Risk status affected emotional responsivity (increased positivity to negative-than-neutral stimuli) overlapping early N2 sink (peak latency 212 ms), P3 source (385 ms), and a late centroparietal source (630 ms). High risk individuals had reduced right-greater-than-left emotional lateralization involving occipitotemporal cortex (N2 sink) and bilaterally reduced emotional effects involving posterior cingulate (P3 source) and inferior temporal cortex (630 ms) when compared to those at low risk. While the early emotional effects were enhanced for left hemifield (right hemisphere) presentations, hemifield modulations did not differ between risk groups, suggesting top-down rather than bottom-up effects of risk. Groups did not differ in their stimulus valence or arousal ratings. Similar effects were seen for individuals with a lifetime history of depression or anxiety disorder in comparison to those without. However, there was no evidence that risk status and history of MDD or anxiety disorder interacted in their impact on emotional responsivity, suggesting largely independent attenuation of attentional resource allocation to enhance perceptual processing of motivationally salient stimuli. These findings further suggest that a deficit in motivated attention preceding conscious awareness may be a marker of risk for depression.
We tackle the prediction of instructor intervention in student posts from discussion forums in Massive Open Online Courses (MOOCs). Our key finding is that using automatically obtained discourse relations improves the prediction of when instructors intervene in student discussions, when compared with a state-of-the-art, feature-rich baseline. Our supervised classifier makes use of an automatic discourse parser which outputs Penn Discourse Treebank (PDTB) tags that represent in-post discourse features. We show PDTB relation-based features increase the robustness of the classifier and complement baseline features in recalling more diverse instructor intervention patterns. In comprehensive experiments over 14 MOOC offerings from several disciplines, the PDTB discourse features improve performance on average. The resultant models are less dependent on domain-specific vocabulary, allowing them to better generalize to new courses.
We explore the concept of hybrid grammars, which formalize and generalize a range of existing frameworks for dealing with discontinuous syntactic structures. Covered are both discontinuous phrase structures and non-projective dependency structures. Technically, hybrid grammars are related to synchronous grammars, where one grammar component generates linear structures and another generates hierarchical structures. By coupling lexical elements of both components together, discontinuous structures result. Several types of hybrid grammars are characterized. We also discuss grammar induction from treebanks. The main advantage over existing frameworks is the ability of hybrid grammars to separate discontinuity of the desired structures from time complexity of parsing. This permits exploration of a large variety of parsing algorithms for discontinuous structures, with different properties. This is confirmed by the reported experimental results, which show a wide variety of running time, accuracy, and frequency of parse failures.
We present a simple LSTM-based transition-based dependency parser. Our model is composed of a single LSTM hidden layer replacing the hidden layer in the usual feed-forward network architecture. We also propose a new initialization method that uses the pre-trained weights from a feed-forward neural network to initialize our LSTM-based model. We also show that using dropout on the input layer has a positive effect on performance. Our final parser achieves a 93.06% unlabeled and 91.01% labeled attachment score on the Penn Treebank. We additionally replace LSTMs with GRUs and Elman units in our model and explore the effectiveness of our initialization method on individual gates constituting all three types of RNN units.
Discourse-annotated corpora are an important resource for the community, but they are often annotated according to different frameworks. This makes comparison of the annotations difficult, thereby also preventing researchers from searching the corpora in a unified way, or using all annotated data jointly to train computational systems. Several theoretical proposals have recently been made for mapping the relational labels of different frameworks to each other, but these proposals have so far not been validated against existing annotations. The two largest discourse relation annotated resources, the Penn Discourse Treebank and the Rhetorical Structure Theory Discourse Treebank, have however been annotated on the same text, allowing for a direct comparison of the annotation layers. We propose a method for automatically aligning the discourse segments, and then evaluate existing mapping proposals by comparing the empirically observed against the proposed mappings. Our analysis highlights the influence of segmentation on subsequent discourse relation labeling, and shows that while agreement between frameworks is reasonable for explicit relations, agreement on implicit relations is low. We identify several sources of systematic discrepancies between the two annotation schemes and discuss consequences of these discrepancies for future annotation and for the training of automatic discourse relation labellers.
This paper investigates interactions in parser performance for the two official standards for written Norwegian: Bokmål and Nynorsk. We demonstrate that while applying models across standards yields poor performance, combining the training data for both standards yields better results than previously achieved for each of them in isolation. This has immediate practical value for processing Norwegian, as it means that a single parsing pipeline is sufficient to cover both varieties, with no loss in accuracy. Based on the Norwegian Universal Dependencies treebank we present results for multiple taggers and parsers, experimenting with different ways of varying the training data given to the learners, including the use of machine translation.
This study examined to what extent children and adults differ in how they process negative emotions during reading, and how they rate their own and protagonists’ emotional states. Results show that both children’s and adults’ processing of target sentences was facilitated when they described negative emotions. Processing of spill-over sentences was facilitated for adults but inhibited for children, suggesting children needed additional time to process protagonists’ emotional states and integrate them into coherent mental representations. Children and adults were similar in their valence and arousal ratings as they rated protagonists’ emotional states as more negative and more intense than their own emotional states. However, they differed in that children rated their own emotional states as relatively neutral, whereas adults’ ratings of their own emotional states more closely matched the negative emotional states of the protagonists. This suggests a possible difference between children and adults in the mechanism underlying emotional inferencing.
This paper describes the system for our participation of team Wanghao-ftd-SJTU in the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. In this work, we design a system based on UDPipe 1 for universal dependency parsing, where transitionbased models are trained for different treebanks. Our system directly takes raw texts as input, performing several intermediate steps like tokenizing and tagging, and finally generates the corresponding dependency trees. For the special surprise languages for this task, we adopt a delexicalized strategy and predict based on transfer learning from other related languages. In the final evaluation of the shared task, our system achieves a result of 66.53% in macro-averaged LAS F1-score.
This study explores the translators’ agency and translation norms in institutional translation, namely at the European Central Bank (E.C.B.), illustrated by metaphors translated from English into Romanian. Two methods are used in the study: (1) quantitative and qualitative analysis of a corpus of texts produced at the E.C.B. – around 2 million tokens each for the English and the Romanian language version sub-corpora and (2) ethnographic observation. The strategies employed for translating metaphorical expressions belonging to the conceptual metaphor THE ECONOMY IS A MACHINE are used to illustrate the choices translators make. The findings of the study show that the translators use a number of strategies, from retaining the metaphor and the metaphorical expression to completely demetaphorising the expressions. Their choices are influenced by internal requirements of the institution (e.g. using translation memory tools) as well as by the linguistic norms and language conventions of Romanian – the target language, the formal style of the documents, and the expectations of the target audience. Moreover, different expressions in English are translated using the same expression in Romanian, which shows that the Romanian economic vocabulary is still developing and this fact also influences translation choices.
<h3>Introduction</h3><br> BOLT English Discussion Forums was developed by the Linguistic Data Consortium (LDC) and consists of 830,440 discussion forum threads in English harvested from the Internet using a combination of manual and automatic processes. <br> The DARPA <a href="https://www.ldc.upenn.edu/collaborations/current-projects/bolt">BOLT</a> (Broad Operational Language Translation) program developed machine translation and information retrieval for less formal genres, focusing particularly on user-generated content. LDC supported the BOLT program by collecting informal data sources -- discussion forums, text messaging and chat -- in Chinese, Egyptian Arabic and English. The collected data was translated and annotated for various tasks including word alignment, treebanking, propbanking and co-reference. The material in this release represents the unannotated English source data in the discussion forum genre. <br> <h3>Data</h3><br> Collection was seeded based on the results of manual data scouting by native speaker annotators. Scouts were instructed to seek content in English that was original, interactive and informal. Upon locating an appropriate thread, scouts submitted the URL and some simple judgments about it to a database, via a web browser plug-in. When multiple threads from a forum were submitted, the entire forum was automatically harvested and added to the collection. The scale of the collection precluded manual review of all data. Only a small portion of the threads included in this release were manually reviewed, and it is expected that there may be some offensive or otherwise undesired content as well as some threads that contain a large amount of non-English content. Language identification was performed on all threads in this corpus (using <a href="https://github.com/CLD2Owners/cld2">CLD2</a>), and threads for which the results indicate a high probability of largely non-English content are listed in eng_suspect_LID.txt in the docs directory of this package. <br> The corpus is comprised of zipped HTML and XML files. The HTML files are a raw HTML file downloaded from the discussion thread. If the thread spanned multiple URLs, it was stored as a concatenation of the downloaded HTML files. The XML files were converted from the raw HTML. <br> <br> <h3>Acknowledgement</h3><br> This material is based upon work supported by the Defense Advanced Research Projects Agency (DARPA) under Contract No. HR0011-11-C-0145. The content does not necessarily reflect the position or the policy of the Government, and no official endorsement should be inferred. <br> <h3>Samples</h3><br> Please view this <a href="desc/addenda/LDC2017T11.html">html sample</a> and <a href="desc/addenda/LDC2017T11.xml">xml sample</a>. <br> <h3>Updates</h3><br> None at this time. </br> Portions © 2017 Trustees of the University of Pennsylvania
Motivated form-meaning mappings are pervasive in signlanguages, and iconicity has recently been shown to facilitatesign learning from early on. This study investigated the role oficonicity for language acquisition in Turkish Sign Language(TID). Participants were 43 signing children (aged 10 to 45months) of deaf parents. Sign production ability was recordedusing the adapted version of MacArthur Bates CommunicativeDevelopmental Inventory (CDI) consisting of 500 items forTID. Iconicity and familiarity ratings for a subset of 104 signswere available. Our results revealed that the iconicity of a signwas positively correlated with the percentage of childrenproducing a sign and that iconicity significantly predicted thepercentage of children producing a sign, independent offamiliarity or phonological complexity. Our results areconsistent with previous findings on sign language acquisitionand provide further support for the facilitating effect of iconicform-meaning mappings in sign learning.
It has recently been demonstrated that the reported tastes/flavours of food/beverages can be modulated by means of external visual and auditory stimuli such as typeface, shapes, and music. The present study was designed to assess the role of the emotional valence of the product-extrinsic stimuli in such crossmodal modulations of taste. Participants evaluated samples of mixed fruit juice whilst simultaneously being presented with auditory or visual stimuli having either positive or negative valence. The soundtracks had either been harmonised with consonant (positive valence) or dissonant (negative valence) musical intervals. The visual stimuli consisted of images of emotional faces from the International Affective Picture System (IAPS) with valence ratings matched to the soundtracks. Each juice sample was rated on two computer-based scales: One anchored with the words sour and sweet, while the other scale required hedonic ratings. Those participants who tasted the juice sample while presented with the positively-valenced stimuli rated the juice as tasting sweeter compared to negatively-valenced stimuli, regardless of whether the stimuli were visual or auditory. These results suggest that the emotional valence of food-extrinsic stimuli can play a role in shaping food flavour evaluation and liking. PMID: 28994341
BACKGROUND: Blunted facial affect is a common negative symptom of schizophrenia. Additionally, assessing the trustworthiness of faces is a social cognitive ability that is impaired in schizophrenia. Currently available pharmacological agents are ineffective at improving either of these symptoms, despite their clinical significance. The hypothalamic neuropeptide oxytocin has multiple prosocial effects when administered intranasally to healthy individuals and shows promise in decreasing negative symptoms and enhancing social cognition in schizophrenia. Although two small studies have investigated oxytocin's effects on ratings of facial trustworthiness in schizophrenia, its effects on facial expressivity have not been investigated in any population. METHOD: We investigated the effects of oxytocin on facial emotional expressivity while participants performed a facial trustworthiness rating task in 33 individuals with schizophrenia and 35 age-matched healthy controls using a double-blind, placebo-controlled, cross-over design. Participants rated the trustworthiness of presented faces interspersed with emotionally evocative photographs while being video-recorded. Participants' facial expressivity in these videos was quantified by blind raters using a well-validated manualized approach (i.e. the Facial Expression Coding System; FACES). RESULTS: While oxytocin administration did not affect ratings of facial trustworthiness, it significantly increased facial expressivity in individuals with schizophrenia (Z = -2.33, p = 0.02) and at trend level in healthy controls (Z = -1.87, p = 0.06). CONCLUSIONS: These results demonstrate that oxytocin administration can increase facial expressivity in response to emotional stimuli and suggest that oxytocin may have the potential to serve as a treatment for blunted facial affect in schizophrenia.
Adversarial training (AT) is a powerful regularization method for neural networks, aiming to achieve robustness to input perturbations. Yet, the specific effects of the robustness obtained from AT are still unclear in the context of natural language processing. In this paper, we propose and analyze a neural POS tagging model that exploits AT. In our experiments on the Penn Treebank WSJ corpus and the Universal Dependencies (UD) dataset (27 languages), we find that AT not only improves the overall tagging accuracy, but also 1) prevents over-fitting well in low resource languages and 2) boosts tagging accuracy for rare / unseen words. We also demonstrate that 3) the improved tagging performance by AT contributes to the downstream task of dependency parsing, and that 4) AT helps the model to learn cleaner word representations. 5) The proposed AT model is generally effective in different sequence labeling tasks. These positive results motivate further use of AT for natural language tasks.
We present a novel recurrent neural network (RNN) based model that combines the remembering ability of unitary RNNs with the ability of gated RNNs to effectively forget redundant/irrelevant information in its memory. We achieve this by extending unitary RNNs with a gating mechanism. Our model is able to outperform LSTMs, GRUs and Unitary RNNs on several long-term dependency benchmark tasks. We empirically both show the orthogonal/unitary RNNs lack the ability to forget and also the ability of GORU to simultaneously remember long term dependencies while forgetting irrelevant information. This plays an important role in recurrent neural networks. We provide competitive results along with an analysis of our model on many natural sequential tasks including the bAbI Question Answering, TIMIT speech spectrum prediction, Penn TreeBank, and synthetic tasks that involve long-term dependencies such as algorithmic, parenthesis, denoising and copying tasks.
A number of firms in northern Europe and especially in Denmark are owned by private foundations similarly to what would have been the case if the Ford Foundation had owned a majority of the shares in Ford Motor Company. Foundation-owned companies appear to perform surprisingly well in terms of profitability and growth, despite lacking governance mechanisms such as profit incentives or takeover threats. Given their non-profit ownership, they might be expected to behave more responsibly towards stakeholders, such as employees or customers (Hansmann, 1980), but so far there has been little empirical evidence to support this hypothesis. This paper presents new research on the reputation and responsibility of foundation-owned companies. In a panel of large Danish companies 2001–11 we find that foundation-owned firms have better reputations and are regarded as more socially responsible in corporate image ratings. Secondary evidence on labour market behaviour is consistent with these findings. Using matched employer–employee data we show that foundation-owned companies are more stable employers, pay their employees better, and keep them for longer. Altogether, the evidence indicates that foundation-ownership is associated with more responsible business behaviour towards employees.
This paper proposes a reinforcing method that refines the output layers of existing Recurrent Neural Network (RNN) language models. We refer to our proposed method as Input-to-Output Gate (IOG). IOG has an extremely simple structure, and thus, can be easily combined with any RNN language models. Our experiments on the Penn Treebank and WikiText-2 datasets demonstrate that IOG consistently boosts the performance of several different types of current topline RNN language models.
These data supplement the article Schomaker, J., Walper, D., Wittmann, B.C., & Einhäuser, W. (2017). Attention in natural scenes: Affective-motivational factors guide gaze independently of visual salience. Vision Research, 133, 161-175. Use is free for academic purposes, provided the aforementioned article is appropriately cited. The directory contains the following files stimuli.tar.gz - stimuli used in this study; note that this is based on the MONS database, but some deviations from the final version of the database do exist. ratings.mat contains the variables<br> arousal - mean arousal rating<br> valence - mean valence rating<br> valence2 - squared mean valence rating (after subtracting midpoint)<br> motivationalValue - mean motivation rating<br> motivaionalValue2 - squared mean motivation rating (after subtracting midpoint) All variables are 104x3, where the first dimension is the stimulus number, and the second dimension the motivation ground truth (aversive, neutral, appetitive) <br> Experiment 1 fixationsExperiment1.mat contains the variables fixationX, fixationY, fixationDuration, fixaitonOnset, fixationInitial, which contain for each fixation horizontal and vertical coordinate, the duration, the time of the onset relative to the trial onset and whether it is the initial fixation. All variables have dimensions 16x104x3x50, where the first dimension is the observer, the second the scene, the third the condition and the forth a counter of fixations. Whenever there are less than 50 fixations the remainder are filled with NaN. <br> boundingBoxesExperiment1.mat contains for each critical object the bounding box coordinates x,y of upper left corner and width and height as variables boundingBoxX, boundingBoxY, boundingBoxW, boundingBoxH respectively. Note that this is relative to the eyetracker coordinates of experiment 1 (full display 1024x768, presentation in the center) and will therefore not match the coordinates of the images in the archive or the bounding box coordinates of experiment 2. Dimensions are 104x3, the dimensions representing scene number and condition, respectively. <br> figure2.m uses these data to computes figure 2 of the article from these data <br> dataForExperiment1.Rdata contains the data frame data, which contains for each fixation the values of the predictors used in the model of table 1. This is computed from the matlab data listed above in addition to the peak values of the AWS salience in the object. <br> table1.R computes and prints the models for table 1 Experiment 2 fixationsExperiment2.mat contains fixation data for experiment 2. Variable names as in experiment 1. Dimensions are 18x99x3x3x50, where the first dimension is the observer, the second the image number, the third the visual condition, the third the motivational condition and the fifth the fixation count. Since only one visual condition was shown to each observer per motivational condition, there is an additional variable 'hasData', which is 1 if the image was presented to the observer in this condition and 0 otherwise. Since fixations can be outside the image and will therefore be excluded, there is also an additional variable fixationNumber to keep a correct count of the fixation number in the trial. boundingBoxesExperiment2.mat contains bounding box data for experiment 2 in image (and fixation) coordinates. Notation as for experiment 1, but coordinates refer to image and eyetracking coordinates used for experiment 2 and therefore can differ occasionally. <br> figure3and4.m generates figures 3 and 4 of the article from these data files. dataForExperiment2.Rdata contains the data frame data, which contains for each fixation the values of the predictors used in the model of tables 2 amd 3. This is computed from the matlab data listed above in addition to the peak values of the AWS salience in the object. The fields imgMot and imgVis contain the motivational ground truth and the salience manipulation, respectively. table2.R uses the Rdata file to compute the models for table 2 of the article and print summary results table3.R uses the Rdata file to compute the models for table 3 of the article and print summary results. Note that the computation can take substantial time; results might deviate slightly depending on the exact version of R and its libraries used.
In this chapter, I will describe the characteristics of WordNet as a powerful lexicographical tool in the field of foreign language didactics, showing some illustrative examples of its applications in different tasks with Galnet, a multilingual digital lexicographical resource which extends the original WordNet lexical database of English with their correspondences in Galician, Spanish, Portuguese, Catalan and Basque.
This paper describes and compares two straightforward approaches for dependency parsing with partial annotations (PA). The first approach is based on a forest-based training objective for two CRF parsers, i.e., a biaffine neural network graph-based parser (Biaffine) and a traditional log-linear graph-based parser (LLGPar). The second approach is based on the idea of constrained decoding for three parsers, i.e., a traditional linear graph-based parser (LGPar), a globally normalized neural network transition-based parser (GN3Par) and a traditional linear transition-based parser (LTPar). For the test phase, constrained decoding is also used for completing partial trees. We conduct experiments on Penn Treebank under three different settings for simulating PA, i.e., random, most uncertain, and divergent outputs from the five parsers. The results show that LLGPar is most effective in directly learning from PA, and other parsers can achieve best performance when PAs are completed into full trees by LLGPar.
We investigate the effective memory depth of RNN models by using them for $n$-gram language model (LM) smoothing. Experiments on a small corpus (UPenn Treebank, one million words of training data and 10k vocabulary) have found the LSTM cell with dropout to be the best model for encoding the $n$-gram state when compared with feed-forward and vanilla RNN models. When preserving the sentence independence assumption the LSTM $n$-gram matches the LSTM LM performance for $n=9$ and slightly outperforms it for $n=13$. When allowing dependencies across sentence boundaries, the LSTM $13$-gram almost matches the perplexity of the unlimited history LSTM LM. LSTM $n$-gram smoothing also has the desirable property of improving with increasing $n$-gram order, unlike the Katz or Kneser-Ney back-off estimators. Using multinomial distributions as targets in training instead of the usual one-hot target is only slightly beneficial for low $n$-gram orders. Experiments on the One Billion Words benchmark show that the results hold at larger scale: while LSTM smoothing for short $n$-gram contexts does not provide significant advantages over classic N-gram models, it becomes effective with long contexts ($n > 5$); depending on the task and amount of data it can match fully recurrent LSTM models at about $n=13$. This may have implications when modeling short-format text, e.g. voice search/query LMs. Building LSTM $n$-gram LMs may be appealing for some practical situations: the state in a $n$-gram LM can be succinctly represented with $(n-1)*4$ bytes storing the identity of the words in the context and batches of $n$-gram contexts can be processed in parallel. On the downside, the $n$-gram context encoding computed by the LSTM is discarded, making the model more expensive than a regular recurrent LSTM LM.
A better understanding of factors that differentiate those who only experience suicidal ideation from those who engage in self-directed violence (SDV) is critical for suicide prevention efforts (Klonsky & May, 2014; May & Klonsky, 2016). To identify who is at greatest risk for death by suicide, it is imperative that new innovative assessment tools be created to facilitate behavioral measurement of key constructs associated with increased risk for SDV. The aim of the current study was to develop and validate a set of suicide-specific images, called the Self-Directed Violence Picture System (SDVPS), to help meet this need. A sample of 119 U.S. military veterans provided valence, arousal, and dominance ratings on the SDVPS. These ratings were compared to International Affective Picture System (IAPS) negative, neutral, and positive images. SDVPS images were rated with significantly greater negative valence and elicited decreased feelings of being in control than did IAPS positive (p <.001, p <.001), IAPS negative (p =.03, p =.001), and IAPS neutral (p <.001, p <.001) images. SDVPS images were also rated with significantly greater arousal than were IAPS neutral images (p <.001). Initial validation data support that the SDVPS images functioned as intended. Although continued validation of the SDVPS in other populations is necessary, the SDVPS may become a new tool by which researchers can begin to systematically and reliably examine reactions to suicide-related content using behavioral and/or experimental paradigms. (PsycINFO Database Record
Positive emotional perceptions and healthy emotional intelligence (EI) are important for social functioning. In this study, we investigated whether loving kindness meditation (LKM) combined with anodal transcranial direct current stimulation (tDCS) would facilitate improvements in EI and changes in affective experience of visual stimuli. LKM has been shown to increase positive emotional experiences and we hypothesized that tDCS could enhance these effects. Eighty-seven undergraduates were randomly assigned to 30 minutes of LKM or a relaxation control recording with anodal tDCS applied to the left dorsolateral prefrontal cortex (left dlPFC) or right temporoparietal junction (right TPJ) at 0.1 or 2.0 milliamps. The primary outcomes were self-reported affect ratings of images from the International Affective Picture System and EI as measured by the Mayer, Salovey and Caruso Emotional Intelligence Test. Results indicated no effects of training on EI, and no main effects of LKM, electrode placement, or tDCS current strength on affect ratings. There was a significant interaction of electrode placement by meditation condition (p = 0.001), such that those assigned to LKM and right TPJ tDCS, regardless of current strength, rated neutral and positive images more positively after training. Results suggest that LKM may enhance positive affective experience.
This article describes a model of otherinitiated self-repair for a chatbot that helps to practice conversation in a foreign language. The model was developed using a corpus of instant messaging conversations between German native and non-native speakers. Conversation Analysis helped to create computational models from a small number of examples. The model has been validated in an AIML-based chatbot. Unlike typical retrieval-based dialogue systems, the explanations are generated at run-time from a linguistic database.
Automatic identification of authorship in disputed documents has benefited from complex network theory as this approach does not require human expertise or detailed semantic knowledge. Networks modeling entire books can be used to discriminate texts from different sources and understand network growth mechanisms, but only a few studies have probed the suitability of networks in modeling small chunks of text to grasp stylistic features. In this study, we introduce a methodology based on the dynamics of word co-occurrence networks representing written texts to classify a corpus of 80 texts by 8 authors. The texts were divided into sections with equal number of linguistic tokens, from which time series were created for 12 topological metrics. Since 73% of all series were stationary (ARIMA(p, 0, q)) and the remaining were integrable of first order (ARIMA(p, 1, q)), probability distributions could be obtained for the global network metrics. The metrics exhibit bell-shaped non-Gaussian dist)
Previous word recognition studies have shown that the pupillary response is sensitive to a word’s frequency. However, such a pupillary effect may be due to the process of executing a response, instead of being an index of word processing. With the aim of exploring this possibility, we recorded the pupillary responses in two experiments involving a lexical decision task (LDT). In the first experiment, participants completed a standard LDT, whereas in the second they performed a delayed LDT. The delay in the response allowed us to compare pupil dilations with and without the response execution component. The results showed that pupillary response was modulated by word frequency in both the standard and the delayed LDT. This finding supports the reliability of using pupillometry for word recognition research. Importantly, our results also suggest that tasks that do not require a response during pupil recording lead to clearer and stronger effects.
In the present study, we explored the linguistic nature of specific memories generated with the Autobiographical Memory Test (AMT) by developing a computerized classifier that distinguishes between specific and nonspecific memories. The AMT is regarded as one of the most important assessment tools to study memory dysfunctions (e.g., difficulty recalling the specific details of memories) in psychopathology. In Study 1, we utilized the Japanese corpus data of 12,400 cue-recalled memories tagged with observer-rated specificity. We extracted linguistic features of particular relevance to memory specificity, such as past tense, negation, and adverbial words and phrases pertaining to time and location. On the basis of these features, a support vector machine (SVM) was trained to classify the memories into specific and nonspecific categories, which achieved an area under the curve (AUC) of .92 in a performance test. In Study 2, the trained SVM was tested in terms of its robustness in classifying novel memories (n = 8,478) that were retrieved in response to cue words that were different from those used in Study 1. The SVM showed an AUC of .89 in classifying the new memories. In Study 3, we extended the binary SVM to a five-class classification of the AMT, which achieved 64%–65% classification accuracy, against the chance level (20%) in the performance tests. Our data suggest that memory specificity can be identified with a relatively small number of words, capturing the universal linguistic features of memory specificity across memories in diverse contents.
nodeGame is a free, open-source JavaScript/ HTML5 framework for conducting synchronous experiments online and in the lab directly in the browser window. It is specifically designed to support behavioral research along three dimensions: (i) larger group sizes, (ii) real-time (but also discrete time) experiments, and (iii) batches of simultaneous experiments. nodeGame has a modular source code, and defines an API (application programming interface) through which experimenters can create new strategic environments and configure the platform. With zero-install, nodeGame can run on a great variety of devices, from desktop computers to laptops, smartphones, and tablets. The current version of the software is 3.0, and extensive documentation is available on the wiki pages at http://nodegame.org.
Speakers not always maintain all grammatical norms in oral speech. However, before the Internet came into being the written public speech was predominantly based on preservation of Armenian language norms, which was largely a subject to censorship and editing. Today the situation has dramatically changed. Alongside with numerous mistakes (spelling, punctuation, lexical), a great variety of cases regarding the violation of grammatical norms are evident. The given article is dedicated to the study of these cases. Particularly, the mistakes concerning the plural, the incorrect usage of dates, pronouns and link words, cases of violation of verbal norms, as well as penetration of some common expressions of everyday language into written speech have been considered.