Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
18265 papers
<h1> TaPvex: A Tagged and Phrased word2vec Model </h1> Benjamin J. Radford <br> September 29, 2017 <h2> Summary </h2> <i>TaPvex</i> is a trained word2vec model of part-of-speech-tagged and named-entity-tagged words and phrases. The model was trained on a large corpus of English language news text from the early 2010s. Words have been tagged using Stanford CoreNLP to include <a href="https://nlp.stanford.edu/software/CRF-NER.shtml">named entities</a> (NER) and <a href="https://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos.html">Penn Treebank</a> parts-of-speech (POS). Tagged words have been concatenated into n-gram phrases.<br> The model contains 1.17 million unique words and phrases. Word vectors are of size 150. <h2> Use </h2> All three files (TaPvex, TaPvex.syn0.npy, TaPvex.syn1.npy) must be located in the same directory. The file can be opened with the <a href="https://radimrehurek.com/gensim/models/word2vec.html"><i>gensim</i></a> Python module using: <pre> from gensim.models import Word2Vec model = Word2Vec.load("/path/to/model/TaPvex") </pre> <h2> Examples </h2> Tokens are of the form: <pre>[WORD]:[NER]:[POS]</pre> Phrases are of the form: <pre>[WORD]:[NER]:[POS]_[WORD]:[NER]:[POS]</pre> Example tokens include: <pre> BUSH:O:NN BUSHES:O:NNS BUSH:PERSON:NNP GEORGE:PERSON:NNP_BUSH:PERSON:NNP GEORGE:PERSON:NNP_W:PERSON:NNP_BUSH:PERSON:NNP NEW:O:JJ NEW:LOCATION:NNP_YORK:LOCATION:NNP NEW:ORGANIZATION:NNP_YORK:ORGANIZATION:NNP_TIMES:ORGANIZATION:NNP </pre>
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.
Among groups of humans, the team structure has been argued to be the most effective way for people to organize to accomplish work. Research suggests that humans and autonomous agents can be more effective when working together. However, the drive toward capable autonomous teammates has focused on design characteristics while ignoring the importance of social interactions between teammates. In the present study we created team structure though task interdependence and observed teamwork outcomes in the form of affect, behavior, and performance outcomes. A team structure resulted in improved affect and performance outcomes relative to a non-team structure. However, team structure did not elicit significant behavioral differences. Human partners received higher affect ratings and elicited significantly more communication from the participant than an autonomous partner. These findings suggest that social interactions between humans and autonomous teammates should be an important design consideration. While the current data is promising, team structure alone may not be sufficient to ensure effective teams, so further research should explore the utility of team development interventions between humans and autonomous agents.
CzeDLex 0.5 is a pilot version of a lexicon of Czech discourse connectives. The lexicon contains connectives partially automatically extracted from the Prague Discourse Treebank 2.0 (PDiT 2.0), a large corpus annotated manually with discourse relations. The most frequent entries in the lexicon (covering more than 2/3 of the discourse relations annotated in the PDiT 2.0) have been manually checked, translated to English and supplemented with additional linguistic information.
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.
With the advent of word embeddings, lexicons are no longer fully utilized for sentiment analysis although they still provide important features in the traditional setting. This paper introduces a novel approach to sentiment analysis that integrates lexicon embeddings and an attention mechanism into Convolutional Neural Networks. Our approach performs separate convolutions for word and lexicon embeddings and provides a global view of the document using attention. Our models are experimented on both the SemEval'16 Task 4 dataset and the Stanford Sentiment Treebank and show comparative or better results against the existing state-of-the-art systems. Our analysis shows that lexicon embeddings allow building high-performing models with much smaller word embeddings, and the attention mechanism effectively dims out noisy words for sentiment analysis.
Large-scale distributed training requires significant communication bandwidth for gradient exchange that limits the scalability of multi-node training, and requires expensive high-bandwidth network infrastructure. The situation gets even worse with distributed training on mobile devices (federated learning), which suffers from higher latency, lower throughput, and intermittent poor connections. In this paper, we find 99.9% of the gradient exchange in distributed SGD is redundant, and propose Deep Gradient Compression (DGC) to greatly reduce the communication bandwidth. To preserve accuracy during compression, DGC employs four methods: momentum correction, local gradient clipping, momentum factor masking, and warm-up training. We have applied Deep Gradient Compression to image classification, speech recognition, and language modeling with multiple datasets including Cifar10, ImageNet, Penn Treebank, and Librispeech Corpus. On these scenarios, Deep Gradient Compression achieves a gradient compression ratio from 270x to 600x without losing accuracy, cutting the gradient size of ResNet-50 from 97MB to 0.35MB, and for DeepSpeech from 488MB to 0.74MB. Deep gradient compression enables large-scale distributed training on inexpensive commodity 1Gbps Ethernet and facilitates distributed training on mobile. Code is available at: https://github.com/synxlin/deep-gradient-compression.
We systematically explore regularizing neural networks by penalizing low\nentropy output distributions. We show that penalizing low entropy output\ndistributions, which has been shown to improve exploration in reinforcement\nlearning, acts as a strong regularizer in supervised learning. Furthermore, we\nconnect a maximum entropy based confidence penalty to label smoothing through\nthe direction of the KL divergence. We exhaustively evaluate the proposed\nconfidence penalty and label smoothing on 6 common benchmarks: image\nclassification (MNIST and Cifar-10), language modeling (Penn Treebank), machine\ntranslation (WMT'14 English-to-German), and speech recognition (TIMIT and WSJ).\nWe find that both label smoothing and the confidence penalty improve\nstate-of-the-art models across benchmarks without modifying existing\nhyperparameters, suggesting the wide applicability of these regularizers.\n
The use of the senses of vision and audition as interactive means has dominated the field of Human-Computer Interaction (HCI) for decades, even though nature has provided us with many more senses for perceiving and interacting with the world around us. That said, it has become attractive for HCI researchers and designers to harness touch, taste, and smell in interactive tasks and experience design. In this paper, we present research and design insights gained throughout an interdisciplinary collaboration on a six-week multisensory display – Tate Sensorium – exhibited at the Tate Britain art gallery in London, UK. This is a unique and first time case study on how to design art experiences whilst considering all the senses (i.e., vision, sound, touch, smell, and taste), in particular touch, which we exploited by capitalizing on a novel haptic technology, namely, mid-air haptics. We first describe the overall set up of Tate Sensorium and then move on to describing in detail the design process of the mid-air haptic feedback and its integration with sound for the Full Stop painting by John Latham (1961). This was the first time that mid-air haptic technology was used in a museum context over a prolonged period of time and integrated with sound to enhance the experience of visual art. As part of an interdisciplinary team of curators, sensory designers, sound artists, we selected a total of three variations of the mid-air haptic experience (i.e., haptic patterns), which were alternated at dedicated times throughout the six-week exhibition. We collected questionnaire-based feedback from 2500 visitors and conducted 50 interviews to gain quantitative and qualitative insights on visitors’ experiences and emotional reactions. Whilst the questionnaire results are generally very positive with only a small variation of the visitors’ arousal ratings across the three tactile experiences designed for the Full Stop painting, the interview data shed light on the differences in the visitors’ subjective experiences. Our findings suggest multisensory designers and art curators can ensure a balance between surprising experiences versus the possibility of free exploration for visitors. In addition, participants expressed that experiencing art with the combination of mid-air haptic and sound was immersive and provided an up-lifting experience of touching without touch. We are convinced that the insights gained from this large-scale and real-world field exploration of multisensory experience design exploiting a new and emerging technology provide a solid starting point for the HCI community, creative industries, and art curators to think beyond conventional art experiences. Specifically, our work demonstrates how novel mid-air technology can make art more emotionally engaging and stimulating, especially abstract art that is often open to interpretation.
In this contribution, I review Augustinus's (2015) dissertation on the syntax of verb clusters. While the main theoretical aspects of this book (within the HPSG framework) may not be of interest to everyone, the corpus methodology used and the GrETEL tool that was developed in the course of this project are impressive, The book contains previously unknown descriptive details about possible clustering verbs. Due to its interdisciplinary nature, there should be something of interest here for anyone who is interested in verb clusters.
To test how preexisting long-term memory influences visual STM, this study takes advantage of individual differences in participants' prior familiarity with Pokémon characters and uses an ERP component, the contralateral delay activity (CDA), to assess whether observers' prior stimulus familiarity affects STM consolidation and storage capacity. In two change detection experiments, consolidation speed, as indexed by CDA fractional area latency and/or early-window (500-800 msec) amplitude, was significantly associated with individual differences in Pokémon familiarity. In contrast, the number of remembered Pokémon stimuli, as indexed by Cowan's K and late-window (1500-2000 msec) CDA amplitude, was significantly associated with individual differences in Pokémon familiarity when STM consolidation was incomplete because of a short presentation of Pokémon stimuli (500 msec, Experiment 2), but not when STM consolidation was allowed to complete given sufficient encoding time (1000 msec, Experiment 1). Similar findings were obtained in between-group analyses when participants were separated into high-familiarity and low-familiarity groups based on their Pokémon familiarity ratings. Together, these results suggest that stimulus familiarity, as a proxy for the strength of preexisting long-term memory, primarily speeds up STM consolidation, which may subsequently lead to an increase in the number of remembered stimuli if consolidation is incomplete. These findings thus highlight the importance of research assessing how effects on representations (e.g., STM capacity) are in general related to (or even caused by) effects on processes (e.g., STM consolidation) in cognition.
Norms are essential to the human condition. Whether in the guise of tradition, culture, canon or rules, norms are therefore central to studies in the humanities. This book focuses on Russian language culture of the post-revolutionary and post-Soviet periods, times when norms — linguistic and otherwise — have been eagerly debated, challenged, broken and redefined. Exploring the intersections between linguistic authority and creative response, an international team of scholars examines different realms of linguistic practice (literary fiction, internet slang, literary criticism and aesthetics, writers’ blogs, linguistic play) and various arenas for “talk about talk” (the classroom, blogs, the media, or the courtroom). By combining various approaches and disciplines — linguistics, literary criticism, new media studies — the book as a whole explores the multiplicity of meanings that are accorded to the notion of linguistic norms in the Russian community. The result is both a broad and a detailed picture of important trends in modern Russian language culture.
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.
This study attempts to determine the common features and differences between the Latin language of the inscriptions of Aquincum, Salona, Aquileia and the provincial countries of Pannonia Inferior, Dalmatia and Venetia et Histria, compared with each other and the rest of the Latin speaking provinces of the Roman empire, and we intend to demonstrate whether a regional dialect area over the Alps–Danube–Adria region of the Roman empire existed, a hypothesis suggested by József Herman. For our research, we use all relevant linguistic data from the Computerized Historical Linguistic Database of Latin Inscriptions of the Imperial Age. We will examine the relative distribution of diverse types of non-standard data found in the inscriptions, contrasting the linguistic phenomena of an earlier period with a later stage of Vulgar Latin. The focus of our analysis will be on the changes in the vowel system and the grammatical cases between the two chronological periods within each of the three examined cities. If we succeed in identifying similar tendencies in the Vulgar Latin of these three cities, the shared linguistic phenomena may suggest the existence of a regional variant of Latin in the Alps–Danube–Adria region.
Darwin (1872) postulated that emotional expressions contain universals that are retained across species. We recently showed that human rating responses were strongly affected by a listener's familiarity with vocalization types, whereas evidence for universal cross-taxa emotion recognition was limited. To disentangle the impact of evolutionarily retained mechanisms (phylogeny) and experience-driven cognitive processes (familiarity), we compared the temporal unfolding of event-related potentials (ERPs) in response to agonistic and affiliative vocalizations expressed by humans and three animal species. Using an auditory oddball novelty paradigm, ERPs were recorded in response to task-irrelevant novel sounds, comprising vocalizations varying in their degree of phylogenetic relationship and familiarity to humans. Vocalizations were recorded in affiliative and agonistic contexts. Offline, participants rated the vocalizations for valence, arousal, and familiarity. Correlation analyses revealed a significant correlation between a posteriorly distributed early negativity and arousal ratings. More specifically, a contextual category effect of this negativity was observed for human infant and chimpanzee vocalizations but absent for other species vocalizations. Further, a significant correlation between the later and more posteriorly P3a and P3b responses and familiarity ratings indicates a link between familiarity and attentional processing. A contextual category effect of the P3b was observed for the less familiar chimpanzee and tree shrew vocalizations. Taken together, these findings suggest that early negative ERP responses to agonistic and affiliative vocalizations may be influenced by evolutionary retained mechanisms, whereas the later orienting of attention (positive ERPs) may mainly be modulated by the prior experience.
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
This study examined to what extent children and adults differ in how they process negative emotions during reading, and how they rate their own and protagonists’ emotional states. Results show that both children’s and adults’ processing of target sentences was facilitated when they described negative emotions. Processing of spill-over sentences was facilitated for adults but inhibited for children, suggesting children needed additional time to process protagonists’ emotional states and integrate them into coherent mental representations. Children and adults were similar in their valence and arousal ratings as they rated protagonists’ emotional states as more negative and more intense than their own emotional states. However, they differed in that children rated their own emotional states as relatively neutral, whereas adults’ ratings of their own emotional states more closely matched the negative emotional states of the protagonists. This suggests a possible difference between children and adults in the mechanism underlying emotional inferencing.
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.
BACKGROUND: Formulaic expressions, including idioms and other fixed expressions, comprise a significant proportion of discourse. Although much has been written about this topic, controversy remains about their psychological status. An important claim about formulaic expressions, that they are known to native speakers, has seldom been directly demonstrated. This study tested the hypothesis that formulaic expressions are known and stored as whole unit mental representations by performing three perceptual experiments. METHOD: Listeners transcribed two kinds of spectrally-degraded spoken sentences, half formulaic, and half novel, newly created expressions, matched for grammar and length. Two familiarity ratings, usage and exposure, were obtained from listeners for each expression. Text frequency data for the stimuli and their constituent words were obtained using a spoken corpus. RESULTS: Participants transcribed formulaic more successfully than literal utterances. Usage and familiarity ratings correlated with accuracy, but formulaic utterances with low ratings were also transcribed correctly. Phrase types differed significantly in text frequency, but word frequency counts did not differentiate the two kinds of expressions. DISCUSSION: These studies provide new converging evidence that formulaic expressions are encoded and processed as whole units, supporting a dual-process model of language processing, which assumes that grammatical and formulaic expressions are differentially processed.
Generative neural models have recently achieved state-of-the-art results for constituency parsing. However, without a feasible search procedure, their use has so far been limited to reranking the output of external parsers in which decoding is more tractable. We describe an alternative to the conventional action-level beam search used for discriminative neural models that enables us to decode directly in these generative models. We then show that by improving our basic candidate selection strategy and using a coarse pruning function, we can improve accuracy while exploring significantly less of the search space. Applied to the model of Choe and Charniak (2016), our inference procedure obtains 92.56 F1 on section 23 of the Penn Treebank, surpassing prior state-of-the-art results for single-model systems.
Natural Language Processing (NLP) systems conventionally treat words as distinct atomic symbols. The model can leverage small amounts of information regarding the relationship between the individual symbols. Today when it comes to texts; one common technique to extract fixed-length features is bag-of-words. Despite its popularity the bag-of-words feature has two major weaknesses: it ignores semantics of the words and the order of words. In this paper, we propose a neural language model that relies on Convolutional Neural Network (CNN) and Bidirectional Recurrent Neural Network (BRNN) over pre-trained word vectors. We utilize bidirectional layers as a substitute of pooling layers in CNN in order to reduce the loss of detailed local information, and to capture long-term dependencies across input sequences. We validate the proposed model on two benchmark sentiment analysis datasets, Stanford Large Movie Review (IMDB), and Stanford Sentiment Treebank (SSTb). Our model achieves a competitive advantage compared with neural language models on the sentiment analysis datasets.
Translanguaging is a rapidly developing concept in bilingual education. Working from the theoretical background of dynamic bilingualism, a translanguaging lens posits that bilingual learners draw on a holistic linguistic repertoire to make sense of the world and to communicate effectively with texts. What is relatively underdeveloped is the pedagogical aspects of translanguaging. This classroom-based study conducted in the southeastern US asks 2 questions: (a) How might teachers create a translanguaging space for students, and (b) what would this space look like? The authors, 1 classroom teacher and 1 researcher, engaged emergent bilingual students in small group reading of a culturally relevant text and observed students’ active participation through strategic and fluid translanguaging practices. The authors argue that the linguistic norms of schooling should reflect the discursive norms of emergent bilingual students, and that teachers create translanguaging spaces as a path to educational equity
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%.
In this paper we focus on collocations, which have been studied in computational linguistics since they constitute a key factor when processing natural languages. For instance, they usually represent a challenge in automatic translation because the association of two terms is not easily computed. We proposed that the parser should be provided with a lexical database in order to make more effective the identification of collocations during the parsing process. We assessed this claim by using a corpus of 6’000 sentences retrieved from the British magazine The Economist Espresso. The corpus was parsed twice, first with the collocation detection component turned on and then with it turned off, and to make the comparison the Fips tagger was used. The results showed an improvement of the quality when the parser has access to collocation knowledge.
Norms are essential to the human condition. Whether in the guise of tradition, culture, canon or rules, norms are therefore central to studies in the humanities. This book focuses on Russian language culture of the post-revolutionary and post-Soviet periods, times when norms — linguistic and otherwise — have been eagerly debated, challenged, broken and redefined. Exploring the intersections between linguistic authority and creative response, an international team of scholars examines different realms of linguistic practice (literary fiction, internet slang, literary criticism and aesthetics, writers’ blogs, linguistic play) and various arenas for “talk about talk” (the classroom, blogs, the media, or the courtroom). By combining various approaches and disciplines — linguistics, literary criticism, new media studies — the book as a whole explores the multiplicity of meanings that are accorded to the notion of linguistic norms in the Russian community. The result is both a broad and a detailed picture of important trends in modern Russian language culture.
Despite the global spread of English, it seems that voices from nonnative English teachers concerning English as an international language (EIL) are under-represented. To address the issue, this study sought to investigate the nonnative teachers’ perceptions of idealized native-speaker linguistic and pragmatic norms in the EIL context. Participants included 125 nonnative English-speaking teachers from the Persian context, falling within the expanding circle. Questionnaires and interviews were used to explore the teachers’ perceptions of native-speaker norms. Findings showed that the nonnative teachers gave preference to native-speaker linguistic norms despite the emerging nonnative EIL norms. Although most of the teachers accepted the existence of a number of accents in English, they preferred the standard American or British accent for language education. As to EIL pragmatic norms, the teachers argued that some degree of flexibility is acceptable with regard to the use of L1 pragmatic norms in the EIL context. The EFL teachers in the present study maintained that the transfer of L1 pragmatic norms to the nativized English makes English a legitimate and culturally appropriate variety in communication between nonnative speakers. The findings contribute to the reappraisal of ELT practices and the premises underpinning teaching EIL.
We describe our submission to the CoNLL 2017 shared task, which exploits the shared common knowledge of a language across different domains via a domain adaptation technique. Our approach is an extension to the recently proposed adversarial training technique for domain adaptation, which we apply on top of a graph-based neural dependency parsing model on bidirectional LSTMs. In our experiments, we find our baseline graphbased parser already outperforms the official baseline model (UDPipe) by a large margin. Further, by applying our technique to the treebanks of the same language with different domains, we observe an additional gain in the performance, in particular for the domains with less training data.
In this paper, we present how the principles of universal dependencies and morphology have been adapted to Hungarian. We report the most challenging grammatical phenomena and our solutions to those. On the basis of the adapted guidelines, we have converted and manually corrected 1,800 sentences from the Szeged Treebank to universal dependency format. We also introduce experiments on this manually annotated corpus for evaluating automatic conversion and the added value of language-specific, i.e. non-universal, annotations. Our results reveal that converting to universal dependencies is not necessarily trivial, moreover, using languagespecific morphological features may have an impact on overall performance.
This paper proposes a reinforcing method that refines the output layers of existing Recurrent Neural Network (RNN) language models. We refer to our proposed method as Input-to-Output Gate (IOG). IOG has an extremely simple structure, and thus, can be easily combined with any RNN language models. Our experiments on the Penn Treebank and WikiText-2 datasets demonstrate that IOG consistently boosts the performance of several different types of current topline RNN language models.
Abstract In this article we present a novel linguistically driven evaluation method and apply it to the main approaches of Machine Translation (Rule-based, Phrase-based, Neural) to gain insights into their strengths and weaknesses in much more detail than provided by current evaluation schemes. Translating between two languages requires substantial modelling of knowledge about the two languages, about translation, and about the world. Using English-German IT-domain translation as a case-study, we also enhance the Phrase-based system by exploiting parallel treebanks for syntax-aware phrase extraction and by interfacing with Linked Open Data (LOD) for extracting named entity translations in a post decoding framework.
In this chapter we describe the web application PaQu (Parse and Query), and carry out a small case study to illustrate its use. PaQu is an application for searching in Dutch treebanks and for analysing the search results. One can search in the LASSY and CGN treebanks, or upload one’s own Dutch corpus, which is then parsed and made available for search and analysis. PaQu offers, next to an interface to formulate Xpath queries, a dedicated interface for searching for dependency triples. This makes it easy to search in treebanks for grammatical dependencies, which would otherwise require very complex queries. It offers extensive functionality for analysing the search results. The dedicated search interface makes PaQu a prime example of the kind of applications that CLARIN promotes. The case study provides an analysis of the syntactic selectional differences between two near-synonymous verbs.
We introduce an attention-based Bi-LSTM for Chinese implicit discourse relations and demonstrate that modeling argument pairs as a joint sequence can outperform word order-agnostic approaches. Our model benefits from a partial sampling scheme and is conceptually simple, yet achieves state-of-the-art performance on the Chinese Discourse Treebank. We also visualize its attention activity to illustrate the model's ability to selectively focus on the relevant parts of an input sequence.
Mondzish (Mangish) lexical database, including transcriptions of my audio recordings collected in China in from 2012-2015.
We describe the improvements to the interface of GrETEL, an online tool for querying treebanks. We demonstrate how we employed the results of two usability tests and individual user feedback in order to create a more user-friendly interface which meets the users’ needs.
OBJECTIVES: Research has suggested that older adults are less optimistic about their future than younger adults; however, a limitation of prior studies is that younger and older adults were forecasting to different ages and stages of life. To address this, we investigated whether there are age differences in future optimism when people project to the exact same age. We also tested whether optimism differs when projecting one's own future versus another person's future. METHOD: Participants were 285 younger and 292 older adults recruited from Amazon Mechanical Turk. Participants completed writing and word-rating tasks in which they imagined their own future in 15 years, their own future at age 85, or the average person's future at age 85. RESULTS: Younger adults were more optimistic than older adults about their own future in 15 years. In contrast, both age groups were similarly optimistic about their future at age 85 and expected it to be more positive than others' future at age 85. DISCUSSION: Contrary to previous research, younger and older adults had comparable future forecasts when projecting to the exact same age. These findings emphasize the need to consider age and stage of life when examining age differences in future optimism.
Sequential LSTMs have been extended to model tree structures, giving competitive results for a number of tasks. Existing methods model constituent trees by bottom-up combinations of constituent nodes, making direct use of input word information only for leaf nodes. This is different from sequential LSTMs, which contain references to input words for each node. In this paper, we propose a method for automatic head-lexicalization for tree-structure LSTMs, propagating head words from leaf nodes to every constituent node. In addition, enabled by head lexicalization, we build a tree LSTM in the top-down direction, which corresponds to bidirectional sequential LSTMs in structure. Experiments show that both extensions give better representations of tree structures. Our final model gives the best results on the Stanford Sentiment Treebank and highly competitive results on the TREC question type classification task.
A number of firms in northern Europe and especially in Denmark are owned by private foundations similarly to what would have been the case if the Ford Foundation had owned a majority of the shares in Ford Motor Company. Foundation-owned companies appear to perform surprisingly well in terms of profitability and growth, despite lacking governance mechanisms such as profit incentives or takeover threats. Given their non-profit ownership, they might be expected to behave more responsibly towards stakeholders, such as employees or customers (Hansmann, 1980), but so far there has been little empirical evidence to support this hypothesis. This paper presents new research on the reputation and responsibility of foundation-owned companies. In a panel of large Danish companies 2001–11 we find that foundation-owned firms have better reputations and are regarded as more socially responsible in corporate image ratings. Secondary evidence on labour market behaviour is consistent with these findings. Using matched employer–employee data we show that foundation-owned companies are more stable employers, pay their employees better, and keep them for longer. Altogether, the evidence indicates that foundation-ownership is associated with more responsible business behaviour towards employees.
This paper addresses the problem of sentence-level sentiment analysis. In recent years, Convolution and Recursive Neural Networks have been proven to be effective network architecture for sentence-level sentiment analysis. Nevertheless, each of them has their own potential drawbacks. For alleviating their weaknesses, we combined Convolution and Recursive Neural Networks into a new network architecture. In addition, we employed transfer learning from a large document-level labeled sentiment dataset to improve the word embedding in our models. The resulting models outperform all recent Convolution and Recursive Neural Networks. Beyond that, our models achieve comparable performance with state-of-the-art systems on Stanford Sentiment Treebank.
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.
In recent years, the research on Treebank has made great progress. However, the application of the Treebank research in international Chinese teaching is not very satisfactory. In view of international Chinese teaching, this paper constructs a diagrammatic Treebank based on the Li Jinxi's Sentence-based Grammar. With the constructing of the diagrammatic Treebank, we have made an exploration in word interpretation based on context, accurate example sentences recommendations based on word senses, words exercise based on dynamic word patterns, and specific grammar point example sentences recommendation.
While dependency parsers reach very high overall accuracy, some dependency relations are much harder than others. In particular, dependency parsers perform poorly in coordination construction (i.e., correctly attaching the conj relation). We extend a state-of-the-art dependency parser with conjunction-specific features, focusing on the similarity between the conjuncts head words. Training the extended parser yields an improvement in conj attachment as well as in overall dependency parsing accuracy on the Stanford dependency conversion of the Penn TreeBank.
BACKGROUND: Apart from a progressive decline of motor functions, Parkinson's disease (PD) is also characterized by non-motor symptoms, including disturbed processing of emotions. This study aims at assessing emotional processing and its neurobiological correlates in PD with the focus on how medicated Parkinson patients may achieve normal emotional responsiveness despite basal ganglia dysfunction. METHODS: Nineteen medicated patients with mild to moderate PD (without dementia or depression) and 19 matched healthy controls passively viewed positive, negative, and neutral pictures in an event-related blood oxygen level-dependent functional magnetic resonance imaging study (BOLD-fMRI). Individual subjective ratings of valence and arousal levels for these pictures were obtained right after the scanning. RESULTS: Parkinson patients showed similar valence and arousal ratings as controls, denoting intact emotional processing at the behavioral level. Yet, Parkinson patients showed decreased bilateral putaminal activation and increased activation in the right dorsomedial prefrontal cortex (PFC), compared to controls, both most pronounced for highly arousing emotional stimuli. CONCLUSIONS: Our findings revealed for the first time a possible compensatory neural mechanism in Parkinson patients during emotional processing. The increased medial PFC activity may have modulated emotional responsiveness in patients via top-down cognitive control, therewith restoring emotional processing at the behavioral level, despite striatal dysfunction. These results may impact upon current treatment strategies of affective disorders in PD as patients may benefit from this intact or even compensatory influence of prefrontal areas when therapeutic strategies are applied that rely on cognitive control to modulate disturbed processing of emotions.
We present a novel recurrent neural network (RNN) based model that combines the remembering ability of unitary RNNs with the ability of gated RNNs to effectively forget redundant/irrelevant information in its memory. We achieve this by extending unitary RNNs with a gating mechanism. Our model is able to outperform LSTMs, GRUs and Unitary RNNs on several long-term dependency benchmark tasks. We empirically both show the orthogonal/unitary RNNs lack the ability to forget and also the ability of GORU to simultaneously remember long term dependencies while forgetting irrelevant information. This plays an important role in recurrent neural networks. We provide competitive results along with an analysis of our model on many natural sequential tasks including the bAbI Question Answering, TIMIT speech spectrum prediction, Penn TreeBank, and synthetic tasks that involve long-term dependencies such as algorithmic, parenthesis, denoising and copying tasks.
Abstract Punctuated equilibrium theory (PET) suggests that the policy process is characterized by long periods of incremental change and short periods of punctuated change. The impetus for the latter is usually a focusing event that breaks open policy monopolies, allowing for major changes in legislative decision making. While a burgeoning body of literature, a shortcoming in the PET literature is that it has yet to explain why focusing events and subsequent breakdowns in policy monopolies sometimes fail to result in punctuated policy. We integrate theories on cultural change with punctuated equilibrium to explain why focusing events do not always result in the dramatic policy changes that we might expect. Specifically, we use the context of national energy policy and the lexical database, Google Ngram Viewer, to trace punctuating energy‐related events and the occurrence or lack thereof subsequent policy change from 1952 to 2000.