Subjects -> COMPUTER SCIENCE (Total: 2313 journals)
    - ANIMATION AND SIMULATION (33 journals)
    - ARTIFICIAL INTELLIGENCE (133 journals)
    - AUTOMATION AND ROBOTICS (116 journals)
    - COMPUTER ARCHITECTURE (11 journals)
    - COMPUTER ENGINEERING (12 journals)
    - COMPUTER GAMES (23 journals)
    - COMPUTER PROGRAMMING (25 journals)
    - COMPUTER SCIENCE (1305 journals)
    - COMPUTER SECURITY (59 journals)
    - DATA BASE MANAGEMENT (21 journals)
    - DATA MINING (50 journals)
    - E-BUSINESS (21 journals)
    - E-LEARNING (30 journals)
    - IMAGE AND VIDEO PROCESSING (42 journals)
    - INFORMATION SYSTEMS (109 journals)
    - INTERNET (111 journals)
    - SOCIAL WEB (61 journals)
    - SOFTWARE (43 journals)
    - THEORY OF COMPUTING (10 journals)

COMPUTER SCIENCE (1305 journals)            First | 1 2 3 4 5 6 7     

Showing 1201 - 872 of 872 Journals sorted alphabetically
Software:Practice and Experience     Hybrid Journal   (Followers: 12)
Southern Communication Journal     Hybrid Journal   (Followers: 3)
Spatial Cognition & Computation     Hybrid Journal   (Followers: 6)
Spreadsheets in Education     Open Access   (Followers: 1)
Statistics, Optimization & Information Computing     Open Access   (Followers: 3)
Stochastic Analysis and Applications     Hybrid Journal   (Followers: 3)
Stochastic Processes and their Applications     Hybrid Journal   (Followers: 6)
Structural and Multidisciplinary Optimization     Hybrid Journal   (Followers: 12)
Studia Universitatis Babeș-Bolyai Informatica     Open Access  
Studies in Digital Heritage     Open Access   (Followers: 3)
Supercomputing Frontiers and Innovations     Open Access   (Followers: 1)
Superhero Science and Technology     Open Access   (Followers: 5)
Sustainability Analytics and Modeling     Full-text available via subscription   (Followers: 5)
Sustainable Computing : Informatics and Systems     Hybrid Journal  
Sustainable Energy, Grids and Networks     Hybrid Journal   (Followers: 4)
Sustainable Operations and Computers     Open Access   (Followers: 1)
Swarm Intelligence     Hybrid Journal   (Followers: 3)
Swiss Journal of Geosciences     Hybrid Journal   (Followers: 1)
Synthese     Hybrid Journal   (Followers: 20)
Synthesis Lectures on Biomedical Engineering     Full-text available via subscription  
Synthesis Lectures on Communication Networks     Full-text available via subscription  
Synthesis Lectures on Communications     Full-text available via subscription  
Synthesis Lectures on Computer Architecture     Full-text available via subscription   (Followers: 4)
Synthesis Lectures on Computer Science     Full-text available via subscription   (Followers: 1)
Synthesis Lectures on Computer Vision     Full-text available via subscription   (Followers: 2)
Synthesis Lectures on Digital Circuits and Systems     Full-text available via subscription   (Followers: 3)
Synthesis Lectures on Human Language Technologies     Full-text available via subscription  
Synthesis Lectures on Mobile and Pervasive Computing     Full-text available via subscription   (Followers: 1)
Synthesis Lectures on Quantum Computing     Full-text available via subscription   (Followers: 2)
Synthesis Lectures on Signal Processing     Full-text available via subscription   (Followers: 1)
Synthesis Lectures on Speech and Audio Processing     Full-text available via subscription   (Followers: 2)
System analysis and applied information science     Open Access  
Systems & Control Letters     Hybrid Journal   (Followers: 4)
Systems and Soft Computing     Full-text available via subscription   (Followers: 5)
Systems Research & Behavioral Science     Hybrid Journal   (Followers: 2)
Techné : Research in Philosophy and Technology     Full-text available via subscription   (Followers: 2)
Technical Report Electronics and Computer Engineering     Open Access  
Technology Transfer: fundamental principles and innovative technical solutions     Open Access   (Followers: 1)
Technology, Knowledge and Learning     Hybrid Journal   (Followers: 3)
Technometrics     Full-text available via subscription   (Followers: 8)
TECHSI : Jurnal Teknik Informatika     Open Access  
TechTrends     Hybrid Journal   (Followers: 8)
Telematics and Informatics     Hybrid Journal   (Followers: 4)
Telemedicine and e-Health     Hybrid Journal   (Followers: 12)
Telemedicine Reports     Full-text available via subscription   (Followers: 6)
TELKOMNIKA (Telecommunication, Computing, Electronics and Control)     Open Access   (Followers: 2)
The Bible and Critical Theory     Full-text available via subscription   (Followers: 3)
The Charleston Advisor     Full-text available via subscription   (Followers: 10)
The Communication Review     Hybrid Journal   (Followers: 5)
The Electronic Library     Hybrid Journal   (Followers: 964)
The Information Society: An International Journal     Hybrid Journal   (Followers: 399)
The International Journal on Media Management     Hybrid Journal   (Followers: 7)
The Journal of Architecture     Hybrid Journal   (Followers: 15)
The Journal of Supercomputing     Hybrid Journal   (Followers: 1)
The Lancet Digital Health     Open Access   (Followers: 9)
The R Journal     Open Access   (Followers: 3)
The Visual Computer     Hybrid Journal   (Followers: 3)
Theoretical Computer Science     Hybrid Journal   (Followers: 8)
Theory & Psychology     Hybrid Journal   (Followers: 4)
Theory and Applications of Mathematics & Computer Science     Open Access   (Followers: 2)
Theory and Decision     Hybrid Journal   (Followers: 4)
Theory and Research in Education     Hybrid Journal   (Followers: 20)
Theory and Society     Hybrid Journal   (Followers: 20)
Theory in Biosciences     Hybrid Journal  
Theory of Computing Systems     Hybrid Journal   (Followers: 2)
Theory of Probability and its Applications     Hybrid Journal   (Followers: 2)
Topology and its Applications     Full-text available via subscription  
Transactions In Gis     Hybrid Journal   (Followers: 9)
Transactions of the Association for Computational Linguistics     Open Access  
Transactions on Computer Science and Technology     Open Access   (Followers: 2)
Transactions on Cryptographic Hardware and Embedded Systems     Open Access   (Followers: 1)
Transforming Government: People, Process and Policy     Hybrid Journal   (Followers: 21)
Trends in Cognitive Sciences     Full-text available via subscription   (Followers: 182)
Trends in Computer Science and Information Technology     Open Access  
Ubiquity     Hybrid Journal  
Unisda Journal of Mathematics and Computer Science     Open Access  
Universal Access in the Information Society     Hybrid Journal   (Followers: 11)
Universal Journal of Computational Mathematics     Open Access   (Followers: 2)
University of Sindh Journal of Information and Communication Technology     Open Access  
User Modeling and User-Adapted Interaction     Hybrid Journal   (Followers: 5)
VAWKUM Transaction on Computer Sciences     Open Access   (Followers: 1)
Veri Bilimi     Open Access  
Vietnam Journal of Computer Science     Open Access   (Followers: 2)
Vilnius University Proceedings     Open Access  
Virtual Reality     Hybrid Journal   (Followers: 9)
Virtual Reality & Intelligent Hardware     Open Access   (Followers: 1)
Virtual Worlds     Open Access  
Virtualidad, Educación y Ciencia     Open Access  
Visual Communication     Hybrid Journal   (Followers: 11)
Visual Communication Quarterly     Hybrid Journal   (Followers: 7)
VLSI Design     Open Access   (Followers: 19)
VRA Bulletin     Open Access   (Followers: 3)
Water SA     Open Access   (Followers: 1)
Wearable Technologies     Open Access   (Followers: 2)
West African Journal of Industrial and Academic Research     Open Access   (Followers: 2)
Wiley Interdisciplinary Reviews - Computational Statistics     Hybrid Journal   (Followers: 1)
Wireless and Mobile Technologies     Open Access   (Followers: 4)
Wireless Communications & Mobile Computing     Hybrid Journal   (Followers: 10)
Wireless Networks     Hybrid Journal   (Followers: 6)
Wireless Sensor Network     Open Access   (Followers: 3)
World Englishes     Hybrid Journal   (Followers: 5)
Written Communication     Hybrid Journal   (Followers: 9)
Xenobiotica     Hybrid Journal   (Followers: 7)
XRDS     Full-text available via subscription   (Followers: 3)
ZDM     Hybrid Journal   (Followers: 2)
Zeitschrift fur Energiewirtschaft     Hybrid Journal  
Труды Института системного программирования РАН     Open Access  
Труды СПИИРАН     Open Access  

  First | 1 2 3 4 5 6 7     

Similar Journals
Journal Cover
Transactions of the Association for Computational Linguistics
Number of Followers: 0  

  This is an Open Access Journal Open Access journal
ISSN (Online) 2307-387X
Published by MIT Press Homepage  [39 journals]
  • Improving the Domain Adaptation of Retrieval Augmented Generation (RAG)
           Models for Open Domain Question Answering

    • Pages: 1 - 17
      Abstract: AbstractRetrieval Augment Generation (RAG) is a recent advancement in Open-Domain Question Answering (ODQA). RAG has only been trained and explored with a Wikipedia-based external knowledge base and is not optimized for use in other specialized domains such as healthcare and news. In this paper, we evaluate the impact of joint training of the retriever and generator components of RAG for the task of domain adaptation in ODQA. We propose RAG-end2end, an extension to RAG that can adapt to a domain-specific knowledge base by updating all components of the external knowledge base during training. In addition, we introduce an auxiliary training signal to inject more domain-specific knowledge. This auxiliary signal forces RAG-end2end to reconstruct a given sentence by accessing the relevant information from the external knowledge base. Our novel contribution is that, unlike RAG, RAG-end2end does joint training of the retriever and generator for the end QA task and domain adaptation. We evaluate our approach with datasets from three domains: COVID-19, News, and Conversations, and achieve significant performance improvements compared to the original RAG model. Our work has been open-sourced through the HuggingFace Transformers library, attesting to our work’s credibility and technical consistency.
      PubDate: Thu, 12 Jan 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00530
      Issue No: Vol. 11 (2023)
  • Assessing the Capacity of Transformer to Abstract Syntactic
           Representations: A Contrastive Analysis Based on Long-distance Agreement

    • Pages: 18 - 33
      Abstract: Many studies have shown that transformers are able to predict subject-verb agreement, demonstrating their ability to uncover an abstract representation of the sentence in an unsupervised way. Recently, Li et al. (2021) found that transformers were also able to predict the object-past participle agreement in French, the modeling of which in formal grammar is fundamentally different from that of subject-verb agreement and relies on a movement and an anaphora resolution.To better understand transformers’ internal working, we propose to contrast how they handle these two kinds of agreement. Using probing and counterfactual analysis methods, our experiments on French agreements show that (i) the agreement task suffers from several confounders that partially question the conclusions drawn so far and (ii) transformers handle subject-verb and object-past participle agreements in a way that is consistent with their modeling in theoretical linguistics.
      PubDate: Thu, 12 Jan 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00531
      Issue No: Vol. 11 (2023)
  • On the Role of Negative Precedent in Legal Outcome Prediction

    • Pages: 34 - 48
      Abstract: AbstractEvery legal case sets a precedent by developing the law in one of the following two ways. It either expands its scope, in which case it sets positive precedent, or it narrows it, in which case it sets negative precedent. Legal outcome prediction, the prediction of positive outcome, is an increasingly popular task in AI. In contrast, we turn our focus to negative outcomes here, and introduce a new task of negative outcome prediction. We discover an asymmetry in existing models’ ability to predict positive and negative outcomes. Where the state-of-the-art outcome prediction model we used predicts positive outcomes at 75.06 F1, it predicts negative outcomes at only 10.09 F1, worse than a random baseline. To address this performance gap, we develop two new models inspired by the dynamics of a court process. Our first model significantly improves positive outcome prediction score to 77.15 F1 and our second model more than doubles the negative outcome prediction performance to 24.01 F1. Despite this improvement, shifting focus to negative outcomes reveals that there is still much room for improvement for outcome prediction models.
      PubDate: Thu, 12 Jan 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00532
      Issue No: Vol. 11 (2023)
  • Meta-Learning a Cross-lingual Manifold for Semantic Parsing

    • Pages: 49 - 67
      Abstract: AbstractLocalizing a semantic parser to support new languages requires effective cross-lingual generalization. Recent work has found success with machine-translation or zero-shot methods, although these approaches can struggle to model how native speakers ask questions. We consider how to effectively leverage minimal annotated examples in new languages for few-shot cross-lingual semantic parsing. We introduce a first-order meta-learning algorithm to train a semantic parser with maximal sample efficiency during cross-lingual transfer. Our algorithm uses high-resource languages to train the parser and simultaneously optimizes for cross-lingual generalization to lower-resource languages. Results across six languages on ATIS demonstrate that our combination of generalization steps yields accurate semantic parsers sampling ≤10% of source training data in each new language. Our approach also trains a competitive model on Spider using English with generalization to Chinese similarly sampling ≤10% of training data.11
      PubDate: Thu, 12 Jan 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00533
      Issue No: Vol. 11 (2023)
  • OPAL: Ontology-Aware Pretrained Language Model for End-to-End
           Task-Oriented Dialogue

    • Pages: 68 - 84
      Abstract: AbstractThis paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD). Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modules: Dialogue state tracker (DST) and response generator (RG). The dialogue state consists of the domain-slot-value triples, which are regarded as the user’s constraints to search the domain-related databases. The large-scale task-oriented dialogue data with the annotated structured dialogue state usually are inaccessible. It prevents the development of the pretrained language model for the task-oriented dialogue. We propose a simple yet effective pretraining method to alleviate this problem, which consists of two pretraining phases. The first phase is to pretrain on large-scale contextual text data, where the structured information of the text is extracted by the information extracting tool. To bridge the gap between the pretraining method and downstream tasks, we design two pretraining tasks: ontology-like triple recovery and next-text generation, which simulates the DST and RG, respectively. The second phase is to fine-tune the pretrained model on the TOD data. The experimental results show that our proposed method achieves an exciting boost and obtains competitive performance even without any TOD data on CamRest676 and MultiWOZ benchmarks.
      PubDate: Thu, 12 Jan 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00534
      Issue No: Vol. 11 (2023)
  • Helpful Neighbors: Leveraging Neighbors in Geographic Feature

    • Pages: 85 - 101
      Abstract: AbstractIf one sees the place name Houston Mercer Dog Run in New York, how does one know how to pronounce it' Assuming one knows that Houston in New York is pronounced and not like the Texas city (), then one can probably guess that is also used in the name of the dog park. We present a novel architecture that learns to use the pronunciations of neighboring names in order to guess the pronunciation of a given target feature. Applied to Japanese place names, we demonstrate the utility of the model to finding and proposing corrections for errors in Google Maps.To demonstrate the utility of this approach to structurally similar problems, we also report on an application to a totally different task: Cognate reflex prediction in comparative historical linguistics. A version of the code has been open-sourced.11
      PubDate: Thu, 12 Jan 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00535
      Issue No: Vol. 11 (2023)
  • Locally Typical Sampling

    • Pages: 102 - 121
      Abstract: Today’s probabilistic language generators fall short when it comes to producing coherent and fluent text despite the fact that the underlying models perform well under standard metrics (e.g., perplexity). This discrepancy has puzzled the language generation community for the last few years. In this work, we posit that the abstraction of natural language generation as a discrete stochastic process—which allows for an information-theoretic analysis—can provide new insights into the behavior of probabilistic language generators, for example, why high-probability texts can be dull or repetitive. Humans use language as a means of communicating information, aiming to do so in a simultaneously efficient and error-minimizing manner; in fact, psycholinguistics research suggests humans choose each word in a string with this subconscious goal in mind. We formally define the set of strings that meet this criterion: Those for which each word has an information content close to the expected information content, namely, the conditional entropy of our model. We then propose a simple and efficient procedure for enforcing this criterion when generating from probabilistic models, which we call locally typical sampling. Automatic and human evaluations show that, in comparison to nucleus and top-k sampling, locally typical sampling offers competitive performance (in both abstractive summarization and story generation) in terms of quality while consistently reducing degenerate repetitions.
      PubDate: Thu, 12 Jan 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00536
      Issue No: Vol. 11 (2023)
  • Improving Low-Resource Cross-lingual Parsing with Expected Statistic

    • Pages: 122 - 138
      Abstract: AbstractWe present Expected Statistic Regulariza tion (ESR), a novel regularization technique that utilizes low-order multi-task structural statistics to shape model distributions for semi- supervised learning on low-resource datasets. We study ESR in the context of cross-lingual transfer for syntactic analysis (POS tagging and labeled dependency parsing) and present several classes of low-order statistic functions that bear on model behavior. Experimentally, we evaluate the proposed statistics with ESR for unsupervised transfer on 5 diverse target languages and show that all statistics, when estimated accurately, yield improvements to both POS and LAS, with the best statistic improving POS by +7.0 and LAS by +8.5 on average. We also present semi-supervised transfer and learning curve experiments that show ESR provides significant gains over strong cross-lingual-transfer-plus-fine-tuning baselines for modest amounts of label data. These results indicate that ESR is a promising and complementary approach to model-transfer approaches for cross-lingual parsing.11
      PubDate: Thu, 12 Jan 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00537
      Issue No: Vol. 11 (2023)
  • Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation

    • Pages: 139 - 156
      Abstract: Multilingual task-oriented dialogue (ToD) facilitates access to services and information for many (communities of) speakers. Nevertheless, its potential is not fully realized, as current multilingual ToD datasets—both for modular and end-to-end modeling—suffer from severe limitations. 1) When created from scratch, they are usually small in scale and fail to cover many possible dialogue flows. 2) Translation-based ToD datasets might lack naturalness and cultural specificity in the target language. In this work, to tackle these limitations we propose a novel outline-based annotation process for multilingual ToD datasets, where domain-specific abstract schemata of dialogue are mapped into natural language outlines. These in turn guide the target language annotators in writing dialogues by providing instructions about each turn’s intents and slots. Through this process we annotate a new large-scale dataset for evaluation of multilingual and cross-lingual ToD systems. Our Cross-lingual Outline-based Dialogue dataset (cod) enables natural language understanding, dialogue state tracking, and end-to-end dialogue evaluation in 4 diverse languages: Arabic, Indonesian, Russian, and Kiswahili. Qualitative and quantitative analyses of cod versus an equivalent translation-based dataset demonstrate improvements in data quality, unlocked by the outline-based approach. Finally, we benchmark a series of state-of-the-art systems for cross-lingual ToD, setting reference scores for future work and demonstrating that cod prevents over-inflated performance, typically met with prior translation-based ToD datasets.
      PubDate: Thu, 12 Jan 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00539
      Issue No: Vol. 11 (2023)
  • Modeling Emotion Dynamics in Song Lyrics with State Space Models

    • Pages: 157 - 175
      Abstract: AbstractMost previous work in music emotion recognition assumes a single or a few song-level labels for the whole song. While it is known that different emotions can vary in intensity within a song, annotated data for this setup is scarce and difficult to obtain. In this work, we propose a method to predict emotion dynamics in song lyrics without song-level supervision. We frame each song as a time series and employ a State Space Model (SSM), combining a sentence-level emotion predictor with an Expectation-Maximization (EM) procedure to generate the full emotion dynamics. Our experiments show that applying our method consistently improves the performance of sentence-level baselines without requiring any annotated songs, making it ideal for limited training data scenarios. Further analysis through case studies shows the benefits of our method while also indicating the limitations and pointing to future directions.
      PubDate: Tue, 14 Feb 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00541
      Issue No: Vol. 11 (2023)
  • FeelingBlue: A Corpus for Understanding the Emotional Connotation of Color
           in Context

    • Pages: 176 - 190
      Abstract: While the link between color and emotion has been widely studied, how context-based changes in color impact the intensity of perceived emotions is not well understood. In this work, we present a new multimodal dataset for exploring the emotional connotation of color as mediated by line, stroke, texture, shape, and language. Our dataset, FeelingBlue, is a collection of 19,788 4-tuples of abstract art ranked by annotators according to their evoked emotions and paired with rationales for those annotations. Using this corpus, we present a baseline for a new task: Justified Affect Transformation. Given an image I, the task is to 1) recolor I to enhance a specified emotion e and 2) provide a textual justification for the change in e. Our model is an ensemble of deep neural networks which takes I, generates an emotionally transformed color palette p conditioned on I, applies p to I, and then justifies the color transformation in text via a visual-linguistic model. Experimental results shed light on the emotional connotation of color in context, demonstrating both the promise of our approach on this challenging task and the considerable potential for future investigations enabled by our corpus.11
      PubDate: Tue, 14 Mar 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00540
      Issue No: Vol. 11 (2023)
  • An Empirical Survey of Data Augmentation for Limited Data Learning in NLP

    • Pages: 191 - 211
      Abstract: AbstractNLP has achieved great progress in the past decade through the use of neural models and large labeled datasets. The dependence on abundant data prevents NLP models from being applied to low-resource settings or novel tasks where significant time, money, or expertise is required to label massive amounts of textual data. Recently, data augmentation methods have been explored as a means of improving data efficiency in NLP. To date, there has been no systematic empirical overview of data augmentation for NLP in the limited labeled data setting, making it difficult to understand which methods work in which settings. In this paper, we provide an empirical survey of recent progress on data augmentation for NLP in the limited labeled data setting, summarizing the landscape of methods (including token-level augmentations, sentence-level augmentations, adversarial augmentations, and hidden-space augmentations) and carrying out experiments on 11 datasets covering topics/news classification, inference tasks, paraphrasing tasks, and single-sentence tasks. Based on the results, we draw several conclusions to help practitioners choose appropriate augmentations in different settings and discuss the current challenges and future directions for limited data learning in NLP.
      PubDate: Tue, 14 Mar 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00542
      Issue No: Vol. 11 (2023)
  • Coreference Resolution through a seq2seq Transition-Based System

    • Pages: 212 - 226
      Abstract: AbstractMost recent coreference resolution systems use search algorithms over possible spans to identify mentions and resolve coreference. We instead present a coreference resolution system that uses a text-to-text (seq2seq) paradigm to predict mentions and links jointly. We implement the coreference system as a transition system and use multilingual T5 as an underlying language model. We obtain state-of-the-art accuracy on the CoNLL-2012 datasets with 83.3 F1-score for English (a 2.3 higher F1-score than previous work [Dobrovolskii, 2021]) using only CoNLL data for training, 68.5 F1-score for Arabic (+4.1 higher than previous work), and 74.3 F1-score for Chinese (+5.3). In addition we use the SemEval-2010 data sets for experiments in the zero-shot setting, a few-shot setting, and supervised setting using all available training data. We obtain substantially higher zero-shot F1-scores for 3 out of 4 languages than previous approaches and significantly exceed previous supervised state-of-the-art results for all five tested languages. We provide the code and models as open source.11
      PubDate: Tue, 14 Mar 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00543
      Issue No: Vol. 11 (2023)
  • Transformers for Tabular Data Representation: A Survey of Models and

    • Pages: 227 - 249
      Abstract: In the last few years, the natural language processing community has witnessed advances in neural representations of free texts with transformer-based language models (LMs). Given the importance of knowledge available in tabular data, recent research efforts extend LMs by developing neural representations for structured data. In this article, we present a survey that analyzes these efforts. We first abstract the different systems according to a traditional machine learning pipeline in terms of training data, input representation, model training, and supported downstream tasks. For each aspect, we characterize and compare the proposed solutions. Finally, we discuss future work directions.
      PubDate: Tue, 14 Mar 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00544
      Issue No: Vol. 11 (2023)
  • Generative Spoken Dialogue Language Modeling

    • Pages: 250 - 266
      Abstract: AbstractWe introduce dGSLM, the first “textless” model able to generate audio samples of naturalistic spoken dialogues. It uses recent work on unsupervised spoken unit discovery coupled with a dual-tower transformer architecture with cross-attention trained on 2000 hours of two-channel raw conversational audio (Fisher dataset) without any text or labels. We show that our model is able to generate speech, laughter, and other paralinguistic signals in the two channels simultaneously and reproduces more naturalistic and fluid turn taking compared to a text-based cascaded model.11,22
      PubDate: Tue, 14 Mar 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00545
      Issue No: Vol. 11 (2023)
  • Discontinuous Combinatory Constituency Parsing

    • Pages: 267 - 283
      Abstract: AbstractWe extend a pair of continuous combinator-based constituency parsers (one binary and one multi-branching) into a discontinuous pair. Our parsers iteratively compose constituent vectors from word embeddings without any grammar constraints. Their empirical complexities are subquadratic. Our extension includes 1) a swap action for the orientation-based binary model and 2) biaffine attention for the chunker-based multi-branching model. In tests conducted with the Discontinuous Penn Treebank and TIGER Treebank, we achieved state-of-the-art discontinuous accuracy with a significant speed advantage.
      PubDate: Wed, 22 Mar 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00546
      Issue No: Vol. 11 (2023)
  • Efficient Long-Text Understanding with Short-Text Models

    • Pages: 284 - 299
      Abstract: AbstractTransformer-based pretrained language models (LMs) are ubiquitous across natural language understanding, but cannot be applied to long sequences such as stories, scientific articles, and long documents due to their quadratic complexity. While a myriad of efficient transformer variants have been proposed, they are typically based on custom implementations that require expensive pretraining from scratch. In this work, we propose SLED: SLiding-Encoder and Decoder, a simple approach for processing long sequences that re-uses and leverages battle-tested short-text pretrained LMs. Specifically, we partition the input into overlapping chunks, encode each with a short-text LM encoder and use the pretrained decoder to fuse information across chunks (fusion-in-decoder). We illustrate through controlled experiments that SLED offers a viable strategy for long text understanding and evaluate our approach on SCROLLS, a benchmark with seven datasets across a wide range of language understanding tasks. We find that SLED is competitive with specialized models that are up to 50x larger and require a dedicated and expensive pretraining step.
      PubDate: Wed, 22 Mar 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00547
      Issue No: Vol. 11 (2023)
  • Hate Speech Classifiers Learn Normative Social Stereotypes

    • Pages: 300 - 319
      Abstract: AbstractSocial stereotypes negatively impact individuals’ judgments about different groups and may have a critical role in understanding language directed toward marginalized groups. Here, we assess the role of social stereotypes in the automated detection of hate speech in the English language by examining the impact of social stereotypes on annotation behaviors, annotated datasets, and hate speech classifiers. Specifically, we first investigate the impact of novice annotators’ stereotypes on their hate-speech-annotation behavior. Then, we examine the effect of normative stereotypes in language on the aggregated annotators’ judgments in a large annotated corpus. Finally, we demonstrate how normative stereotypes embedded in language resources are associated with systematic prediction errors in a hate-speech classifier. The results demonstrate that hate-speech classifiers reflect social stereotypes against marginalized groups, which can perpetuate social inequalities when propagated at scale. This framework, combining social-psychological and computational-linguistic methods, provides insights into sources of bias in hate-speech moderation, informing ongoing debates regarding machine learning fairness.
      PubDate: Wed, 22 Mar 2023 00:00:00 GMT
      DOI: 10.1162/tacl_a_00550
      Issue No: Vol. 11 (2023)
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Tel: +00 44 (0)131 4513762

Your IP address:
Home (Search)
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-