Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
16504 papers
We propose a shared task on multilingual SurfaceRealization, i.e., on mapping unorderedand uninflected universal dependency trees tocorrectly ordered and inflected sentences in anumber of languages. A second deeper inputwill be available in which, in addition,functional words, fine-grained PoS and morphologicalinformation will be removed fromthe input trees. The first shared task on SurfaceRealization was carried out in 2011 witha similar setup, with a focus on English. Wethink that it is time for relaunching such ashared task effort in view of the arrival of UniversalDependencies annotated treebanks fora large number of languages on the one hand,and the increasing dominance of Deep Learning,which proved to be a game changer forNLP, on the other hand.
This paper presents a novel neural machine translation model which jointly learns translation and source-side latent graph representations of sentences. Unlike existing pipelined approaches using syntactic parsers, our end-to-end model learns a latent graph parser as part of the encoder of an attention-based neural machine translation model, and thus the parser is optimized according to the translation objective. In experiments, we first show that our model compares favorably with state-of-the-art sequential and pipelined syntax-based NMT models. We also show that the performance of our model can be further improved by pre-training it with a small amount of treebank annotations. Our final ensemble model significantly outperforms the previous best models on the standard English-to-Japanese translation dataset.
A novel character-level neural language model is proposed in this paper. The proposed model incorporates a biologically inspired temporal hierarchy in the architecture for representing multiple compositions of language in order to handle longer sequences for the character-level language model. The temporal hierarchy is introduced in the language model by utilizing a Gated Recurrent Neural Network with multiple timescales. The proposed model incorporates a timescale adaptation mechanism for enhancing the performance of the language model. We evaluate our proposed model using the popular Penn Treebank and Text8 corpora. The experiments show that the use of multiple timescales in a Neural Language Model (NLM) enables improved performance despite having fewer parameters and with no additional computation requirements. Our experiments also demonstrate the ability of the adaptive temporal hierarchies to represent multiple compositonality without the help of complex hierarchical architectures and shows that better representation of the longer sequences lead to enhanced performance of the probabilistic language model.
Summarizing, extracting keywords, sorting and filtering large quantities of texts were subject of various algorithms based on lexical databases because this was a difficult and time consuming task for a human operator. Our proposed algorithm is based on WordNet lexical database. It eliminates the connection words. For the remaining words (only nouns or verbs) we build a tree with several levels of more generic terms like hypernym or lexicographer file. Using custom weights for each tree level and statistical analysis, we extract a restricted number of words which are used to define the keywords of a document. These results can be used to sort and filter a document based on relevance.
Previous research showed that a bitter taste in the mouth is able to enhance hostile response tendencies to social rejection. The present event-related potential (ERP) study sought to investigate neuronal components of this effect. We presented 52 participants (39 women and 13 men; mean age = 23.3 years) with images of facial expressions signaling social rejection (angry, disgusted) or no rejection (happy, neural), whereas they either experienced a bitter aftertaste (bitter group [BG]: n = 26) or rinsed their mouth with water (control group [CG]: n = 26). The BG rated the aftertaste as extremely intense and disgusting and showed a decreased parietal P200 to all facial expressions, as well as a lowered parietal P300 to cues of nonrejection. The bitter intervention neither influenced the affective ratings for the images nor self-reported hostility. In conclusion, the ERP findings indicated that bitterness first reduced visual attention to social cues in general (P200) and then specifically to cues of nonrejection (P300). Bitterness was not associated with increased sensitivity to disgust/anger signaled by others neither on a neuronal nor self-report level.
Latent-variable probabilistic context-free grammars are latent-variable models that are based on context-free grammars. Nonterminals are associated with latent states that provide contextual information during the top-down rewriting process of the grammar. We survey a few of the techniques used to estimate such grammars and to parse text with them. We also give an overview of what the latent states represent for English Penn treebank parsing, and provide an overview of extensions and related models to these grammars.
A recently proposed encoding for noncrossing digraphs can be used to implement generic inference over families of these digraphs and to carry out first-order factored dependency parsing. It is now shown that the recent proposal can be substantially streamlined without information loss. The improved encoding is less dependent on hierarchical processing and it gives rise to a high-coverage boundeddepth approximation of the space of noncrossing digraphs. This subset is presented elegantly by a finite-state machine that recognizes an infinite set of encoded graphs. The set includes more than 99.99% of the 0.6 million noncrossing graphs obtained from the UDv2 treebanks through planarisation. Rather than taking the low probability of the residual as a flat rate, it can be modelled with a joint probability distribution that is factorised into two underlying stochastic processes -the sentence length distribution and the related conditional distribution for deep nesting. This model points out that deep nesting in the streamlined code requires extreme sentence lengths. High depth is categorically out in common sentence lengths but emerges slowly at infrequent lengths that prompt further inquiry.
Discourse connectives (e.g. however, because) are terms that can explicitly convey a discourse relation within a text. While discourse connectives have been shown to be an effective clue to automatically identify discourse relations, they are not always used to convey such relations, thus they should first be disambiguated between discourse-usage non-discourse-usage. In this paper, we investigate the applicability of features proposed for the disambiguation of English discourse connectives for French. Our results with the French Discourse Treebank (FDTB) show that syntactic and lexical features developed for English texts are as effective for French and allow the disambiguation of French discourse connectives with an accuracy of 94.2%.
Targeted sentiment analysis investigates the sentiment polarities on given target mentions from input texts. Different from sentence level sentiment, it offers more fine-grained knowledge on each entity mention. While early work leveraged syntactic information, recent research has used neural representation learning to induce features automatically, thereby avoiding error propagation of syntactic parsers, which are particularly severe on social media texts. We study a method to leverage syntactic information without explicitly building the parser outputs, by training an encoder-decoder structure parser model on standard syntactic treebanks, and then leveraging its hidden encoder layers when analysing tweets. Such hidden vectors do not contain explicit syntactic outputs, yet encode rich syntactic features. We use them to augment the inputs to a baseline state-of-the-art targeted sentiment classifier, observing significant improvements on various benchmark datasets. We obtain the best accuracies on all test sets.
Huntington's disease (HD) is a neurodegenerative movement disorder associated with deficits in the processing of emotional stimuli, including alterations in the self-reported subjective experience of emotion when presented with pictures of emotional scenes. The aim of this study was to determine whether individuals with HD, compared to unaffected controls, display abnormal visual scanning of emotionally evocative natural scenes. Using eye-tracking, we recorded eye-movements of 25 HD participants (advanced pre-symptomatic and early symptomatic) and 25 age-matched unaffected control participants during a picture viewing task. Participants viewed pictures of natural scenes associated with different emotions: anger, fear, disgust, happiness, or neutral, and evaluated those pictures on a valence rating scale. Individuals with HD displayed abnormal visual scanning patterns, but did not differ from controls with respect to their valence ratings. Specifically, compared to controls, HD participants spent less time fixating on the pictures and made longer scan paths. This finding highlights the importance of taking visual scanning behavior into account when investigating emotion processing in HD. The visual scanning patterns displayed by HD participants could reflect a heightened, but possibly unfocussed, search for information, and might be linked to attentional deficits or to altered subjective emotional experiences in HD. Another possibility is that HD participants may have found it more difficult than controls to evaluate the emotional valence of the scenes, and the heightened search for information was employed as a compensatory strategy.
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.
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.
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.
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).
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.
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.
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.
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.
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.
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.
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.
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
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.
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.
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.
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.
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.
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.
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
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.
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.
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.
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.
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.
Universal Dependency (UD) annotations, despite their usefulness for cross-lingual tasks and semantic applications, are not optimised for statistical parsing.In the paper, we ask what exactly causes the decrease in parsing accuracy when training a parser on UD-style annotations and whether the effect is similarly strong for all languages.We conduct a series of experiments where we systematically modify individual annotation decisions taken in the UD scheme and show that this results in an increased accuracy for most, but not for all languages.We show that the encoding in the UD scheme, in particular the decision to encode content words as heads, causes an increase in dependency length for nearly all treebanks and an increase in arc direction entropy for many languages, and evaluate the effect this has on parsing accuracy.
A method is presented which applies Long Short-Term Memory Recurrent Neural Networks on real market-research voice recordings in order to automatically predict emotional arousal from speech. While most previous work has dealt with evaluations of algorithms within the same speech corpus, the novelty of this paper lies in an extensive evaluation across corpora and languages. The approach is evaluated on seven large data sets collected in real tests of TV commercials and new product concepts across four languages. We observe excellent performance within and between the different corpora when compared against the gold standard of arousal ratings by human annotators. Even in the cross-language validation the models show good performance which almost reaches human rater agreement.
This paper attempts to submit an evaluation plan based on word naming tes perspectives. The uniqueness of the evaluation of this perspective is the use of psycholinguistic norms to identify inhibiting factors as well as supporting kanji recognition by learners. In addition, a detailed analysis of the kanji constituents is to be tested. The psycholinguistic norms and characteristics of the kanji constituents are exemplified in the design of the evaluation in this paper, including: frequency effects, cumulative frequency effects, family size effects, word complexity, and so on. While the kanji constituent seen from the visual form of kanji graphics on the phonetic and semantic radicals; a nd consistency of compound kanji pronunciation. This evaluation is based on a study of how information processing takes place in the mind of the learners. In the field of visual recognition of words, the task commonly used to test cognitive learning abilities is the word naming test. In this test the learners are asked to pronounce the visible kanji on the computer monitor quickly and accurately within the specified response time limit. Learners' answers will be recorded and then analyzed offline. Advantage of this evaluation is teacher or lecturer can identify factors causing learners difficulties in recognizing kanji. Keywords: word naming tes, ability to read kanji, evaluation
We propose to exploit the potential of multiple word clusterings in class-based recurrent neural network (RNN) language models for ensemble RNN language modeling. By varying the clustering criteria and the space of word embedding, different word clusterings are obtained to define different word/class factorizations. For each such word/class factorization, several base RNNLMs are learned, and the word prediction probabilities of the base RNNLMs are then combined to form an ensemble prediction. We use a greedy backward model selection procedure to select a subset of models and combine these models for word prediction. The proposed ensemble language modeling method has been evaluated on Penn Treebank test set as well as Wall Street Journal (WSJ) Eval 92 and 93 test sets, where it improved test set perplexity and word error rate over the state-of-the-art single RNNLMs as well as multiple RNNLMs produced by varying RNN learning conditions.
Discourse parsing is an integral part of understanding information flow and argumentative structure in documents. Most previous research has focused on inducing and evaluating models from the English RST Discourse Treebank. However, discourse treebanks for other languages exist, including Spanish, German, Basque, Dutch and Brazilian Portuguese. The treebanks share the same underlying linguistic theory, but differ slightly in the way documents are annotated. In this paper, we present (a) a new discourse parser which is simpler, yet competitive (significantly better on 2/3 metrics) to state of the art for English, (b) a harmonization of discourse treebanks across languages, enabling us to present (c) what to the best of our knowledge are the first experiments on cross-lingual discourse parsing.
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.
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.