Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
16504 papers
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.
This paper formalizes a sound extension of dynamic oracles to global training, in the frame of transition-based dependency parsers. By dispensing with the precomputation of references, this extension widens the training strategies that can be entertained for such parsers; we show this by revisiting two standard training procedures, early-update and max-violation, to correct some of their search space sampling biases. Experimentally, on the SPMRL treebanks, this improvement increases the similarity between the train and test distributions and yields performance improvements up to 0.7 UAS, without any computation overhead.
The availability of the Rhetorical Structure Theory (RST) Discourse Treebank has spurred substantial research into discourse analysis of written texts; however, limited research has been conducted to date on RST annotation and parsing of spoken language, in particular, nonnative spontaneous speech. Considering that the measurement of discourse coherence is typically a key metric in human scoring rubrics for assessments of spoken language, we initiated a research effort to obtain RST annotations of a large number of non-native spoken responses from a standardized assessment of academic English proficiency. The resulting inter-annotator agreements on the three different levels of Span, Nuclearity, and Relation are 0.848, 0.766, and 0.653, respectively. Furthermore, a set of features was explored to evaluate the discourse structure of non-native spontaneous speech based on these annotations; the highest performing feature showed a correlation of 0.612 with scores of discourse coherence provided by expert human raters.
The main objective of this research was to study the comprehension level of heritage speakers of Turkish with regard to Turkish proverbs. The familiarity factor in relation to its role in comprehending proverbs is also examined. Familiarity judgments of proverbs were made by heritage speakers of Turkish to determine whether the familiarity ratings of the heritage speakers of Turkish could be associated with their understanding of proverbs. The results of the proverb comprehension tests indicate that the difference between the bilingual heritage speakers of Turkish and baseline monolingual speakers in their comprehension of proverbs was significant. Yet, when the arithmetic mean rank is taken into consideration, both heritage speakers of Turkish and monolinguals display high level performance in their comprehension of proverbs. However, there appears to be a noteworthy difference between the frequency level of heritage speakers’ and monolinguals’ in their encounter with proverbs. Monolinguals outperformed bilinguals in comprehension of proverbs and familiarity rating. Results also showed that familiarity had a nonsignificant correlation with participants’ performance on proverb comprehension.
OBJECTIVE: Previous studies have reported that brain-injured patients frequently suffer from cognitive impairments such as attention and concentration deficits. Numerous rehabilitation clinics offer animal-assisted therapy (AAT) to address these difficulties. The authors' aim was to investigate the immediate effects of AAT on the concentration and attention span of brain-injured patients. METHOD: Nineteen patients with acquired brain injury were included in a randomized, controlled, within-subject trial. The patients alternately received 12 standard therapy sessions (speech therapy, physiotherapy, occupational therapy) and 12 paralleled AAT sessions with comparable content. A total of 429 therapy sessions was analyzed consisting of 214 AAT and 215 control sessions. Attention span and instances of distraction were assessed via video coding in Noldus Observer. The Mehrdimensionaler Befindlichkeitsbogen ([Multidimensional Affect Rating Scale] MDBF questionnaire; Steyer, Schwenkmezger, Notz, & Eid, 1997) was used to measure the patient's self-rated alertness. Concentration was assessed through Visual Analogue Scale (VAS) via self-assessment and therapist's ratings. RESULTS: The patients' attention span did not differ whether an animal was present or not. However, patients displayed more instances of distraction during AAT. Moreover, patients rated themselves more concentrated and alert during AAT sessions. Further, therapists' evaluation of patients' concentration indicated that patients were more concentrated in AAT compared with the control condition. CONCLUSIONS: Although the patients displayed more instances of distraction while in the presence of an animal, it did not have a negative impact on their attention span. In addition, patients reported to be more alert and concentrated when an animal was present. Future studies should examine other attentional processes such as divided attention and include neurobiological correlates of attention. (PsycINFO Database Record
Two experiments examined if exposure to emotionally valent image-based secondary tasks introduced at different points of a free recall working memory (WM) task impair memory performance. Images from the International Affective Picture System (IAPS) varied in the degree of negative or positive valance (mild, moderate, strong) and were positioned at low, moderate and high WM load points with participants rating them based upon perceived valence. As predicted, and based on previous research and theory, the higher the degree of negative (Experiment 1) and positive (Experiment 2) valence and the higher the WM load when a secondary task was introduced, the greater the impairment to recall. Secondary task images with strong negative valance were more disruptive than negative images with lower valence at moderate and high WM load task points involving encoding and/or rehearsal of primary task words (Experiment 1). This was not the case for secondary tasks involving positive images (Experiment 2), although participant valence ratings for positive IAPS images classified as moderate and strong were in fact very similar. Implications are discussed in relation to research and theory on task interruption and attentional narrowing and literature concerning the effects of emotive stimuli on cognition.
Speech community concept can be seen/shown through three approaches; Firstly, on the basis of their common language forms, secondly by rules that regulate those common language forms, and thirdly from the perspective of the common cultural concepts. Speech community is possibly created if certain group of individuals, for the reason of common territory, professions, hobbies have exactly the same language and possess the common judgement on any linguistic norms. The same case can also be projected to any speech communities in certain social, household, governmental, or religious domains to mention a few possibilitites. Keywords: linguis politnes, sociolinguistic, speech commuity.
Describing implicit phenomena in discourse is known to be a problematic task, from both theoretical and empirical perspectives. The present article contributes to this topic by a novel comparative analysis of two prominent annotation approaches to discourse relations (coherence relations) that were carried out on the same texts. We compare the annotation of implicit relations in the Penn Discourse Treebank 2.0, i.e. discourse relations not signaled by an explicit discourse connective, to the recently released analysis of signals of rhetorical relations in the RST Signalling Corpus (RST-SC). The intersection of corresponding pairs of relations is rather a small one, but it shows a clear tendency: unlike the overall signal distribution in the RST-SC, more than half of the signals in the studied intersection are of semantic type, formed mostly by loosely defined lexical chains. Our data transformation allows for a simultaneous depiction and detailed study of the two resources.
Most fetal brain MRI reconstruction algorithms rely only on brain tissue-relevant voxels of low-resolution (LR) images to enhance the quality of inter-slice motion correction and image reconstruction. Consequently the fetal brain needs to be localized and extracted as a first step, which is usually a laborious and time consuming manual or semi-automatic task. We have proposed in this work to use age-matched template images as prior knowledge to automatize brain localization and extraction. This has been achieved through a novel automatic brain localization and extraction method based on robust template-to-slice block matching and deformable slice-to-template registration. Our template-based approach has also enabled the reconstruction of fetal brain images in standard radiological anatomical planes in a common coordinate space. We have integrated this approach into our new reconstruction pipeline that involves intensity normalization, inter-slice motion correction, and super-resolution (SR) reconstruction. To this end we have adopted a novel approach based on projection of every slice of the LR brain masks into the template space using a fusion strategy. This has enabled the refinement of brain masks in the LR images at each motion correction iteration. The overall brain localization and extraction algorithm has shown to produce brain masks that are very close to manually drawn brain masks, showing an average Dice overlap measure of 94.5%. We have also demonstrated that adopting a slice-to-template registration and propagation of the brain mask slice-by-slice leads to a significant improvement in brain extraction performance compared to global rigid brain extraction and consequently in the quality of the final reconstructed images. Ratings performed by two expert observers show that the proposed pipeline can achieve similar reconstruction quality to reference reconstruction based on manual slice-by-slice brain extraction. The proposed brain mask refinement and reconstruction method has shown to provide promising results in automatic fetal brain MRI segmentation and volumetry in 26 fetuses with gestational age range of 23 to 38 weeks.
Connections play a crucial role in neural network (NN) learning because they determine how information flows in NNs. Suitable connection mechanisms may extensively enlarge the learning capability and reduce the negative effect of gradient problems. In this paper, a new delay connection is proposed for Long Short-Term Memory (LSTM) unit to develop a more sophisticated recurrent unit, called Delay Connected LSTM (DCLSTM). The proposed delay connection brings two main merits to DCLSTM with introducing no extra parameters. First, it allows the output of the DCLSTM unit to maintain LSTM, which is absent in the LSTM unit. Second, the proposed delay connection helps to bridge the error signals to previous time steps and allows it to be back-propagated across several layers without vanishing too quickly. To evaluate the performance of the proposed delay connections, the DCLSTM model with and without peephole connections was compared with four state-of-the-art recurrent model on two sequence classification tasks. DCLSTM model outperformed the other models with higher accuracy and F1[Formula: see text]score. Furthermore, the networks with multiple stacked DCLSTM layers and the standard LSTM layer were evaluated on Penn Treebank (PTB) language modeling. The DCLSTM model achieved lower perplexity (PPL)/bit-per-character (BPC) than the standard LSTM model. The experiments demonstrate that the learning of the DCLSTM models is more stable and efficient.
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
This paper reports on a suite of experiments that evaluates how the linguistic granularity of part-of-speech tagsets impacts the performance of tagging and syntactic dependency parsing. Our results show that parsing accuracy can be significantly improved by introducing more finegrained morphological information in the tagset, even if tagger accuracy is compromised. Our taggers and parsers are trained and tested using the annotations of the Norwegian Dependency Treebank.
This paper describes the Amobee sentiment analysis system, adapted to compete in SemEval 2017 task 4. The system consists of two parts: a supervised training of RNN models based on a Twitter sentiment treebank, and the use of feedforward NN, Naive Bayes and logistic regression classifiers to produce predictions for the different sub-tasks. The algorithm reached the 3rd place on the 5-label classification task (sub-task C).
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.
Humans are sensitive to gaze direction from early life, and gaze has social and affective values. Borderline personality disorder (BPD) is a clinical condition characterized by emotional dysregulation and enhanced sensitivity to affective and social cues. In this study we wanted to investigate the temporal-spatial dynamics of spontaneous gaze processing in BPD. We used a 2-back-working-memory task, in which neutral faces with direct and averted gaze were presented. Gaze was used as an emotional modulator of event-related-potentials to faces. High density EEG data were acquired in 19 females with BPD and 19 healthy women, and analyzed with a spatio-temporal microstates analysis approach. Independently of gaze direction, BPD patients showed altered N170 and P200 topographies for neutral faces. Source localization revealed that the anterior cingulate and other prefrontal regions were abnormally activated during the N170 component related to face encoding, while middle temporal deactivations were observed during the P200 component. Post-task affective ratings showed that BPD patients had difficulty to disambiguate neutral gaze. This study provides first evidence for an early neural bias toward neutral faces in BPD independent of gaze direction and also suggests the importance of considering basic aspects of social cognition in identifying biological risk factors of BPD.
The PARSEME shared task aims at identifying verbal MWEs in running texts. Verbal MWEs include idioms (let the cat out of the bag), light verb constructions (make a decision), verb-particle constructions (give up), and inherently reflexive verbs (se suicider 'to suicide' in French). VMWEs were annotated according to the universal guidelines in 18 languages. The corpora are provided in the parsemetsv format, inspired by the CONLL-U format. For most languages, paired files in the CONLL-U format - not necessarily using UD tagsets - containing parts of speech, lemmas, morphological features and/or syntactic dependencies are also provided. Depending on the language, the information comes from treebanks (e.g., Universal Dependencies) or from automatic parsers trained on treebanks (e.g., UDPipe). This item contains training and test data, tools and the universal guidelines file.
Singlish can be interesting to the ACL community both linguistically as a major creole based on English, and computationally for information extraction and sentiment analysis of regional social media. We investigate dependency parsing of Singlish by constructing a dependency treebank under the Universal Dependencies scheme, and then training a neural network model by integrating English syntactic knowledge into a state-of-the-art parser trained on the Singlish treebank. Results show that English knowledge can lead to 25% relative error reduction, resulting in a parser of 84.47% accuracies. To the best of our knowledge, we are the first to use neural stacking to improve cross-lingual dependency parsing on low-resource languages. We make both our annotation and parser available for further research.
Discourse relations can either be explicitly marked by discourse connectives (DCs), such as therefore and but, or implicitly conveyed in natural language utterances. How speakers choose between the two options is a question that is not well understood. In this study, we propose a psycholinguistic model that predicts whether or not speakers will produce an explicit marker given the discourse relation they wish to express. Our model is based on two information-theoretic frameworks: (1) the Rational Speech Acts model, which models the pragmatic interaction between language production and interpretation by Bayesian inference, and (2) the Uniform Information Density theory, which advocates that speakers adjust linguistic redundancy to maintain a uniform rate of information transmission. Specifically, our model quantifies the utility of using or omitting a DC based on the expected surprisal of comprehension, cost of production, and availability of other signals in the rest of the utterance. Experiments based on the Penn Discourse Treebank show that our approach outperforms the state-of-the-art performance at predicting the presence of DCs (Patterson and Kehler, 2013), in addition to giving an explanatory account of the speaker’s choice.
The negativity bias has been shown in many fields, including in face processing. We assume that this bias stems from the potential threat inlayed in the stimuli (e.g., negative moral behaviors) in previous studies. In the present study, we conducted one behavioral and one event-related potentials (ERPs) experiments to test whether the positivity bias rather than negativity bias will arise when participants process information whose negative aspect involves no threat, i.e., the ability information. In both experiments, participants first completed a valence rating (negative-to-positive) of neutral facial expressions. Further, in the learning period, participants associated the neutral faces with high-ability, low-ability, or control sentences. Finally, participants rated these facial expressions again. Results of the behavioral experiment showed that compared with pre-learning, the expressions of the faces associated with high ability sentences were classified as more positive in the post-learning expression rating task, and the faces associated with low ability sentences were evaluated as more negative. Meanwhile, the change in the high-ability group was greater than that of the low-ability group. The ERP data showed that the faces associated with high-ability sentences elicited a larger early posterior negativity, an ERP component considered to reflect early sensory processing of the emotional stimuli, than the faces associated with control sentences. However, no such effect was found in faces associated with low-ability sentences. To conclude, high ability sentences exerted stronger influence on expression perception than did low ability ones. Thus, we found a positivity bias in this ability-related facial perceptual task. Our findings demonstrate an effect of valenced ability information on face perception, thereby adding to the evidence on the opinion that person-related knowledge can influence face processing. What's more, the positivity bias in non-threatening surroundings increases scope for studies on processing bias.
This paper is concerned with whether deep syntactic information can help surface parsing, with a particular focus on empty categories. We design new algorithms to produce dependency trees in which empty elements are allowed, and evaluate the impact of information about empty category on parsing overt elements. Such information is helpful to reduce the approximation error in a structured parsing model, but increases the search space for inference and accordingly the estimation error. To deal with structure-based overfitting, we propose to integrate disambiguation models with and without empty elements, and perform structure regularization via joint decoding. Experiments on English and Chinese TreeBanks with different parsing models indicate that incorporating empty elements consistently improves surface parsing.
In this paper, an effective machine translation system from Thai to Khmer language on a website is proposed. To create a web application for a high performance Thai-Khmer machine translation (ThKh-MT), the principles and methods of translation involve with lexical base. Word reordering is applied by considering the previous word, the next word and subject-verb agreement. The word adjustment is also required to attain acceptable outputs. Additional steps related to structure patterns are added in a combination with the classical methods to deal with translation issues. PHP is implemented to build the application with MySQL as a tool to create lexical databases. For testing, 5,100 phrases and sentences are selected to evaluate the system. The result shows 89.25 percent of accuracy and 0.84 for F-Measure which infers to a higher efficiency than that of Google and other systems.
Cultural differences may influence interactions between humans with different social norms and cultural traits, incurring different emotional and behavioral responses. The same applies to human-robot interaction (HRI). We believe that controlling robot emotions based on the cultural context can help robots adapt to humans from culturally diverse backgrounds. Such culturally aligned robots are expected to be easily accepted by humans as part of daily life. In this paper, we aim at investigating the role of culture in representing robot emotions which are injected by humans during its early stage of development and subject to change through their own experience thereafter. Several public data sets of pictures labeled with affective ratings by Indian, American, and European subjects are presented to social humanoid Pepper robots. The result shows that robots can learn to behave socially in alignment with an individual's cultural background. Moreover, we have demonstrated that robots under the effect of different cultures can generate different behavioral responses to the same stimuli, which is considered one of the most important issues in socially assitive robotics.
Universal Dependencies (UD) is becoming a standard annotation scheme crosslinguistically, but it is argued that this scheme centering on content words is harder to parse than the conventional one centering on function words. To improve the parsability of UD, we propose a backand-forth conversion algorithm, in which we preprocess the training treebank to increase parsability, and reconvert the parser outputs to follow the UD scheme as a postprocess. We show that this technique consistently improves LAS across languages even with a state-of-the-art parser, in particular on core dependency arcs such as nominal modifier. We also provide an in-depth analysis to understand why our method increases parsability. 1
Recent work on the problem of latent tree learning has made it possible to train neural networks that learn to both parse a sentence and use the resulting parse to interpret the sentence, all without exposure to ground-truth parse trees at training time. Surprisingly, these models often perform better at sentence understanding tasks than models that use parse trees from conventional parsers. This paper aims to investigate what these latent tree learning models learn. We replicate two such models in a shared codebase and find that (i) only one of these models outperforms conventional tree-structured models on sentence classification, (ii) its parsing strategies are not especially consistent across random restarts, (iii) the parses it produces tend to be shallower than standard Penn Treebank (PTB) parses, and (iv) they do not resemble those of PTB or any other semantic or syntactic formalism that the authors are aware of.
Nous presentons de nouvelles instanciations de trois corpus arbores en constituants du francais, ou certains phenomenes syntaxiques a l’origine de dependances a longue distance sont representes directement a l’aide de constituants discontinus. Les arbres obtenus relevent de formalismes grammaticaux legerement sensibles au contexte (LCFRS). Nous montrons ensuite qu’il est possible d’analyser automatiquement de telles structures de maniere efficace a condition de s’appuyer sur une methode d’inference approximative. Pour cela, nous presentons un analyseur syntaxique par transitions, qui realise egalement l’analyse morphologique et l’etiquetage fonctionnel des mots de la phrase. Enfin, nos experiences montrent que la rarete des phenomenes concernes dans les donnees francaises pose des difficultes pour l’apprentissage et l’evaluation des structures discontinues.
Speakers constantly learn language from the environment by sampling their linguistic input and adjusting their representations accordingly. Logically, people should attend more to the environment and adjust their behavior in accordance with it more the lower their success in the environment is. We test whether the learning of linguistic input follows this general principle in two studies: a corpus analysis of a TV game show, Jeopardy, and a laboratory task modeled after Go Fish. We show that lower (non-linguistic) success in the task modulates learning of and reliance on linguistic patterns in the environment. In Study 1, we find that poorer performance increases conformity with linguistic norms, as reflected by increased preference for frequent grammatical structures. In Study 2, which consists of a more interactive setting, poorer performance increases learning from the immediate social environment, as reflected by greater repetition of others’ grammatical structures. We propose that these results have implications for models of language production and language learning and for the propagation of language change. In particular, they suggest that linguistic changes might spread more quickly in times of crisis, or when the gap between more and less successful people is larger. The results might also suggest that innovations stem from successful individuals while their propagation would depend on relatively less successful individuals. We provide a few historical examples that are in line with the first suggested implication, namely, that the spread of linguistic changes is accelerated during difficult times, such as war time and an economic downturn.
Scientific research within the humanities is different from what it was a few decades ago. For instance, new sources of information, such as digital grammars, lexical databases and large corpora of real-language data offer new opportunities for linguistics. The Taalportaal grammatical database, with its links to other linguistic resources via the CLARIN infrastructure, is a prime example of a new type of tool for linguistic research.
Following We trained our transition-based projective parser in UD version 2.0 datasets without any additional data. The parser is fast, lightweight and effective on big treebanks.
Abstract This conversation analytic study explores the nexus of goal orientation and linguistic identity (particularly of L1 English speakers) in ELF interaction. While goal orientation constitutes a hallmark of ELF scholarship, the latter notion has received limited scholarly attention. To address this gap, this study examines a dyadic, institutional interaction between two students in the United States (L1 British English and L1 Arabic) who met for an intercultural conversation assigned by their instructors. In the interest of accomplishing the goal of obtaining intercultural information, the participants did not bring their differences in linguistic identity to the fore of the interaction, while it was also found that the pursuit of an institutional goal can at times manifest itself as orientations to linguistic norms. The examination of these overt orientations to the institutional goal is followed by a study of deviant cases in which the L1 speaking participant appeared to make relevant his superior linguistic identity at first glance. While they could be interpreted as claims of linguistic superiority, a closer look revealed that these instances also reflected the participants’ cooperative orientations to the emergent communicative needs so as to jointly accomplish the shared goal. Highlighting the problem of presuming a correlation between interactional behavior and linguistic identity, the study suggests the need for the analyst to withhold his/her preconceptions about interactants’ identities. Further research involving diverse groups of interactants, including L1 speakers of English, is needed to contribute to the recent theoretical developments that characterize ELF interaction as situated within diverse linguacultural ecologies and power dynamics.
Unsupervised dependency parsing, which tries to discover linguistic dependency structures from unannotated data, is a very challenging task. Almost all previous work on this task focuses on learning generative models. In this paper, we develop an unsupervised dependency parsing model based on the CRF autoencoder. The encoder part of our model is discriminative and globally normalized which allows us to use rich features as well as universal linguistic priors. We propose an exact algorithm for parsing as well as a tractable learning algorithm. We evaluated the performance of our model on eight multilingual treebanks and found that our model achieved comparable performance with state-of-the-art approaches.
Related to Herman (2000) and Herman (1987=2006), the present study deals with the problem of the deletion of word-final -s as evidenced in Latin inscriptions of the Empire. By reconsidering all items of the omission of -s recorded to date in the Computerized Historical Linguistic Database of Latin Inscriptions of the Imperial Age, the morphosyntactic explanation proposed by Herman (1987=2006) as for relevant omissions will be replaced by a phonetic and phonosyntactic approach which evidences the all-time prevalence of the consonantal environment in the omission of word final -s. Accordingly, the phonosyntactically determined deletion of word final -s before a subsequent consonant existed continuously but to various degrees from the Old Latin age onward all along the history of Latin. This situation might have been inherited by the Romance languages, where different and complex morphological innovations led either to the discontinuation of the phenomenon of phonosyntactically determined deletion and the stabilization of word final -s (as in Western Romance), or to the completion of the deletion process and the complete loss of word final -s (as in Eastern Romance).
Identifying the sense of a word within a context is a challenging problem and has many applications in natural language processing. This assignment problem is called word sense disambiguation (WSD). Many papers in the literature focus on English language and data. Our dataset consists of 1400 sentences translated to Turkish from the Penn Treebank Corpus. This paper seeks to address and discuss 6 different feature extraction methods and its classification performances using C4.5, Random Forests, Rocchio, Naive Bayes, KNN, Linear and multilayer Perceptron. This paper calls into question how the described features perform on a morphologically rich language (Turkish) with several classifiers.
The generalized valency patterns cover both obligatory arguments and optional adjuncts of valency carriers in authentic texts. Such a valency is defined as the number of all the dependents of the valency carrier. With a motif defined as the longest sequence with non-decreasing values, this paper chooses two news-genre dependency treebanks, one in Chinese and one in English and examines the motifs of generalized valencies in them and their lengths. They both are found to abide by the right truncated modified Zipf-Alekseev distribution. In addition, the Hyperpoisson model captures the interrelation between motif lengths and length frequencies. These research findings validate valency motifs as basic language entities and as results of a diversification process.
Adding context information into recurrent neural network language models (RNNLMs) have been investigated recently to improve the effectiveness of learning RNNLM. Conventionally, a fast approximate topic representation for a block of words was proposed by using corpus-based topic distribution of word incorporating latent Dirichlet allocation (LDA) model. It is then updated for each subsequent word using an exponential decay. However, words could represent different topics in different documents. In this paper, we form document-based distribution over topics for each word using LDA model and apply it in the computation of fast approximate exponentially decaying features. We have shown experimental results on a well known Penn Treebank corpus and found that our approach outperforms the conventional LDA-based context RNNLM approach. Moreover, we carried out speech recognition experiments on Wall Street Journal corpus and achieved word error rate (WER) improvements over the other approach.
The performance of Neural Network (NN)-based language models is steadily improving due to the emergence of new architectures, which are able to learn different natural language characteristics. This paper presents a novel framework, which shows that a significant improvement can be achieved by combining different existing heterogeneous models in a single architecture. This is done through 1) a feature layer, which separately learns different NN-based models and 2) a mixture layer, which merges the resulting model features. In doing so, this architecture benefits from the learning capabilities of each model with no noticeable increase in the number of model parameters or the training time. Extensive experiments conducted on the Penn Treebank (PTB) and the Large Text Compression Benchmark (LTCB) corpus showed a significant reduction of the perplexity when compared to state-of-the-art feedforward as well as recurrent neural network architectures.
Recurrent neural networks (RNNs) are important class of architectures among neural networks useful for language modeling and sequential prediction. However, optimizing RNNs is known to be harder compared to feed-forward neural networks. A number of techniques have been proposed in literature to address this problem. In this paper we propose a simple technique called fraternal dropout that takes advantage of dropout to achieve this goal. Specifically, we propose to train two identical copies of an RNN (that share parameters) with different dropout masks while minimizing the difference between their (pre-softmax) predictions. In this way our regularization encourages the representations of RNNs to be invariant to dropout mask, thus being robust. We show that our regularization term is upper bounded by the expectation-linear dropout objective which has been shown to address the gap due to the difference between the train and inference phases of dropout. We evaluate our model and achieve state-of-the-art results in sequence modeling tasks on two benchmark datasets - Penn Treebank and Wikitext-2. We also show that our approach leads to performance improvement by a significant margin in image captioning (Microsoft COCO) and semi-supervised (CIFAR-10) tasks.
It is in our nature to measure the intensity of an unseen event by observing its impact on the affected entity. Since reaction of the trader crowd to a financial event in form of stock price movement very closely reflects the severity of that event, words used in the news to describe that event also exhibit similar degree of emotion. Thus, we can assign emotional valence rating to the most relevant words in the news using this reversed relationship of causality instead of assigning assumed emotional valence to words, like it has been the case in many previous works. We have gathered data for financial events of the past from stock exchange and have mathematically analyzed it to quantify the impact of those events. These results are then applied to assign ratings to more than 7000 PoS-tagged English stems extracted from financial news articles for the corresponding events using Natural Language Processing techniques. In this way, a domain-specific word-emotion lexicon has been created.
We propose a shared task on multilingual Surface Realization, i.e., on mapping unordered and uninflected universal dependency trees to correctly ordered and inflected sentences in a number of languages. A second deeper input will be available in which, in addition, functional words, fine-grained PoS and morphological information will be removed from the input trees. The first shared task on Surface Realization was carried out in 2011 with a similar setup, with a focus on English. We think that it is time for relaunching such a shared task effort in view of the arrival of Universal Dependencies annotated treebanks for a large number of languages on the one hand, and the increasing dominance of Deep Learning, which proved to be a game changer for NLP, on the other hand.
In this paper, we introduce the novel concept of densely connected layers into recurrent neural networks. We evaluate our proposed architecture on the Penn Treebank language modeling task. We show that we can obtain similar perplexity scores with six times fewer parameters compared to a standard stacked 2layer LSTM model trained with dropout In contrast with the current usage of skip connections, we show that densely connecting only a few stacked layers with skip connections already yields significant perplexity reductions.
In several domains, including healthcare and home automation, it is important to unobtrusively monitor the activities of daily living (ADLs) executed by people at home. A popular approach consists in the use of sensors attached to everyday objects to capture user interaction, and ADL models to recognize the current activity based on the temporal sequence of used objects. However, both knowledge-based and data-driven approaches to object-based ADL recognition have different issues that limit their applicability in real-world deployments. Hence, in this paper, we pursue an alternative approach, which consists in mining ADL models from the Web. Existing attempts in this sense are mainly based on Web page mining and lexical analysis. One issue with those attempts relies on the high level of noise found in the textual content of Web pages. In order to overcome that issue, our intuition is that pictures illustrating the execution of a given activity offer much more compact and expressive information than the textual content of a Web page regarding the same activity. Hence, we present a novel method to couple Web mining and computer vision for automatically extracting ADL models from visual items. Our method relies on Web image search engines to select the most relevant pictures for each considered activity. We use off-the-shelf computer vision APIs and a lexical database to extract the key objects appearing in those pictures. We introduce a probabilistic technique to measure the relevance among activities and objects. Through experiments with a large dataset of real-world ADLs, we show that our method significantly improves the existing approach.
We introduce context embeddings, dense vectors derived from a language model that represent the left/right context of a word instance, and demonstrate that context embeddings significantly improve the accuracy of our transition based parser. Our model consists of a bidirectional LSTM (BiLSTM) based language model that is pre-trained to predict words in plain text, and a multi-layer perceptron (MLP) decision model that uses features from the language model to predict the correct actions for an ArcHybrid transition based parser. We participated in the CoNLL 2017 UD Shared Task as the "Koc University" team and our system was ranked 7th out of 33 systems that parsed 81 treebanks in 49 languages.
Cognitive mechanisms for sign language lexical access are fairly unknown. This study investigated whether phonological similarity facilitates lexical retrieval in sign languages using measures from a new lexical database for American Sign Language. Additionally, it aimed to determine which similarity metric best fits the present data in order to inform theories of how phonological similarity is constructed within the lexicon and to aid in the operationalization of phonological similarity in sign language. Sign repetition latencies and accuracy were obtained when native signers were asked to reproduce a sign displayed on a computer screen. Results indicated that, as predicted, phonological similarity facilitated repetition latencies and accuracy as long as there were no strict constraints on the type of sublexical features that overlapped. The data converged to suggest that one similarity measure, MaxD, defined as the overlap of any 4 sublexical features, likely best represents mechanisms of phonological similarity in the mental lexicon. Together, these data suggest that lexical access in sign language is facilitated by phonologically similar lexical representations in memory and the optimal operationalization is defined as liberal constraints on overlap of 4 out of 5 sublexical features-similar to the majority of extant definitions in the literature.
Transition-based dependency parsers often need sequences of local shift and reduce operations to produce certain attachments. Correct individual decisions hence require global information about the sentence context and mistakes cause error propagation. This paper proposes a novel transition system, arc-swift, that enables direct attachments between tokens farther apart with a single transition. This allows the parser to leverage lexical information more directly in transition decisions. Hence, arc-swift can achieve significantly better performance with a very small beam size. Our parsers reduce error by 3.7--7.6% relative to those using existing transition systems on the Penn Treebank dependency parsing task and English Universal Dependencies.
A word may have multiple meanings or senses, it could be modeled by considering that words in a sentence have a fuzzy set that contains words with similar meaning, which make detecting plagiarism a hard task especially when dealing with semantic meaning, and even harder for cross language plagiarism detection. Arabic is known by its richness, word’s constructions and meanings diversity, hence changing texts from/to Arabic is a complex task, and therefore adopting a fuzzy semantic-based approach seems to be the best solution. In this paper, we propose a detailed fuzzy semantic-based similarity model for analyzing and comparing texts in CLP cases, in accordance with the WordNet lexical database, to detect plagiarism in documents translated from/to Arabic, a preprocessing phase is essential to form operable data for the fuzzy process. The proposed method was applied to two texts (Arabic/English), taking into consideration the specificities of the Arabic language. The result shows that the proposed method can detect 85% of the plagiarism cases.
In this work, we propose a novel, implicitly-defined neural network architecture and describe a method to compute its components. The proposed architecture forgoes the causality assumption used to formulate recurrent neural networks and instead couples the hidden states of the network, allowing improvement on problems with complex, long-distance dependencies. Initial experiments demonstrate the new architecture outperforms both the Stanford Parser and baseline bidirectional networks on the Penn Treebank Part-of-Speech tagging task and a baseline bidirectional network on an additional artificial random biased walk task.
This article describes MetaRomance, a rule-based cross-lingual parser for Romance languages submitted to CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. The system is an almost delexicalized parser which does not need training data to analyze Romance languages. It contains linguistically motivated rules based on PoS-tag patterns. The rules included in MetaRomance were developed in about 12 hours by one expert with no prior knowledge in Universal Dependencies, and can be easily extended using a transparent formalism. In this paper we compare the performance of MetaRomance with other supervised systems participating in the competition, paying special attention to the parsing of different treebanks of the same language. We also compare our system with a delexicalized parser for Romance languages, and take advantage of the harmonized annotation of Universal Dependencies to propose a language ranking based on the syntactic distance each variety has from Romance languages.