diff --git a/data/xml/2021.scil.xml b/data/xml/2021.scil.xml index b3b93bf83d..6ce73683cd 100644 --- a/data/xml/2021.scil.xml +++ b/data/xml/2021.scil.xml @@ -130,8 +130,10 @@ Information flow, artificial phonology and typology AdamantiosGafos 148–157 - 2021.scil-1.14 + 2021.scil-1.14 gafos-2021-information + + Added references and corrected typos. Learnability of indexed constraint analyses of phonological opacity @@ -169,8 +171,10 @@ BrandonWaldon JudithDegen 206–215 - 2021.scil-1.19 + 2021.scil-1.19 waldon-degen-2021-modeling + + Corrected typos. Multiple alignments of inflectional paradigms diff --git a/data/xml/2022.blackboxnlp.xml b/data/xml/2022.blackboxnlp.xml index 97567f7412..b49b38e745 100644 --- a/data/xml/2022.blackboxnlp.xml +++ b/data/xml/2022.blackboxnlp.xml @@ -278,7 +278,7 @@ Garden Path Traversal in <fixed-case>GPT</fixed-case>-2 WilliamJurayj WilliamRudman - CarstenEickhof + CarstenEickhoff 305-313 In recent years, large-scale transformer decoders such as the GPT-x family of models have become increasingly popular. Studies examining the behavior of these models tend to focus only on the output of the language modeling head and avoid analysis of the internal states of the transformer decoder. In this study, we present a collection of methods to analyze the hidden states of GPT-2 and use the model’s navigation of garden path sentences as a case study. To enable this, we compile the largest currently available dataset of garden path sentences. We show that Manhattan distances and cosine similarities provide more reliable insights compared to established surprisal methods that analyze next-token probabilities computed by a language modeling head. Using these methods, we find that negating tokens have minimal impacts on the model’s representations for unambiguous forms of sentences with ambiguity solely over what the object of a verb is, but have a more substantial impact of representations for unambiguous sentences whose ambiguity would stem from the voice of a verb. Further, we find that analyzing the decoder model’s hidden states reveals periods of ambiguity that might conclude in a garden path effect but happen not to, whereas surprisal analyses routinely miss this detail. 2022.blackboxnlp-1.25 diff --git a/data/xml/2022.conll.xml b/data/xml/2022.conll.xml index 79f9860a4e..dffdcf1e35 100644 --- a/data/xml/2022.conll.xml +++ b/data/xml/2022.conll.xml @@ -44,8 +44,10 @@ KathleenCarley 27-39 This paper investigates how hate speech varies in systematic ways according to the identities it targets. Across multiple hate speech datasets annotated for targeted identities, we find that classifiers trained on hate speech targeting specific identity groups struggle to generalize to other targeted identities. This provides empirical evidence for differences in hate speech by target identity; we then investigate which patterns structure this variation. We find that the targeted demographic category (e.g. gender/sexuality or race/ethnicity) appears to have a greater effect on the language of hate speech than does the relative social power of the targeted identity group. We also find that words associated with hate speech targeting specific identities often relate to stereotypes, histories of oppression, current social movements, and other social contexts specific to identities. These experiments suggest the importance of considering targeted identity, as well as the social contexts associated with these identities, in automated hate speech classification - 2022.conll-1.3 + 2022.conll-1.3 yoder-etal-2022-hate + + Updated wording. Continual Learning for Natural Language Generations with Transformer Calibration diff --git a/data/xml/2022.eamt.xml b/data/xml/2022.eamt.xml index 5f55efb801..36ebf9939d 100644 --- a/data/xml/2022.eamt.xml +++ b/data/xml/2022.eamt.xml @@ -39,7 +39,7 @@ Neural Speech Translation: From Neural Machine Translation to Direct Speech Translation - Mattia Antonino DiGangi + Mattia AntoninoDi Gangi 7–8 2022.eamt-1.2 gangi-2022-neural @@ -783,7 +783,7 @@ Automatic Video Dubbing at <fixed-case>A</fixed-case>pp<fixed-case>T</fixed-case>ek - Mattia DiGangi + MattiaDi Gangi NickRossenbach AlejandroPérez ParniaBahar diff --git a/data/xml/2022.emnlp.xml b/data/xml/2022.emnlp.xml index 5ab4ab5e28..0c1fc5c941 100644 --- a/data/xml/2022.emnlp.xml +++ b/data/xml/2022.emnlp.xml @@ -3775,8 +3775,10 @@ YiChang 4746-4758 Weakly-supervised text classification aims to train a classifier using only class descriptions and unlabeled data. Recent research shows that keyword-driven methods can achieve state-of-the-art performance on various tasks. However, these methods not only rely on carefully-crafted class descriptions to obtain class-specific keywords but also require substantial amount of unlabeled data and takes a long time to train. This paper proposes FastClass, an efficient weakly-supervised classification approach. It uses dense text representation to retrieve class-relevant documents from external unlabeled corpus and selects an optimal subset to train a classifier. Compared to keyword-driven methods, our approach is less reliant on initial class descriptions as it no longer needs to expand each class description into a set of class-specific keywords.Experiments on a wide range of classification tasks show that the proposed approach frequently outperforms keyword-driven models in terms of classification accuracy and often enjoys orders-of-magnitude faster training speed. - 2022.emnlp-main.313 + 2022.emnlp-main.313 xia-etal-2022-fastclass + + Corrected author name. Neural-Symbolic Inference for Robust Autoregressive Graph Parsing via Compositional Uncertainty Quantification @@ -5284,8 +5286,10 @@ RuifengXu 6485-6498 Aspect Sentiment Triplet Extraction (ASTE) aims to extract the aspect terms along with the corresponding opinion terms and the expressed sentiments in the review, which is an important task in sentiment analysis. Previous research efforts generally address the ASTE task in an end-to-end fashion through the table-filling formalization, in which the triplets are represented by a two-dimensional (2D) table of word-pair relations. Under this formalization, a term-level relation is decomposed into multiple independent word-level relations, which leads to relation inconsistency and boundary insensitivity in the face of multi-word aspect terms and opinion terms. To overcome these issues, we propose Boundary-Driven Table-Filling (BDTF), which represents each triplet as a relation region in the 2D table and transforms the ASTE task into detection and classification of relation regions. We also notice that the quality of the table representation greatly affects the performance of BDTF. Therefore, we develop an effective relation representation learning approach to learn the table representation, which can fully exploit both word-to-word interactions and relation-to-relation interactions. Experiments on several public benchmarks show that the proposed approach achieves state-of-the-art performances. - 2022.emnlp-main.435 + 2022.emnlp-main.435 zhang-etal-2022-boundary + + Corrected Figure 2. Attention and Edge-Label Guided Graph Convolutional Networks for Named Entity Recognition @@ -8396,9 +8400,9 @@ Dictionary-Assisted Supervised Contrastive Learning - PatrickWu + Patrick Y.Wu RichardBonneau - JoshuaTucker + Joshua A.Tucker JonathanNagler 10217-10235 Text analysis in the social sciences often involves using specialized dictionaries to reason with abstract concepts, such as perceptions about the economy or abuse on social media. These dictionaries allow researchers to impart domain knowledge and note subtle usages of words relating to a concept(s) of interest. We introduce the dictionary-assisted supervised contrastive learning (DASCL) objective, allowing researchers to leverage specialized dictionaries when fine-tuning pretrained language models. The text is first keyword simplified: a common, fixed token replaces any word in the corpus that appears in the dictionary(ies) relevant to the concept of interest. During fine-tuning, a supervised contrastive objective draws closer the embeddings of the original and keyword-simplified texts of the same class while pushing further apart the embeddings of different classes. The keyword-simplified texts of the same class are more textually similar than their original text counterparts, which additionally draws the embeddings of the same class closer together. Combining DASCL and cross-entropy improves classification performance metrics in few-shot learning settings and social science applications compared to using cross-entropy alone and alternative contrastive and data augmentation methods. diff --git a/data/xml/2022.eurali.xml b/data/xml/2022.eurali.xml index 5cb531c4c3..22c9b9317e 100644 --- a/data/xml/2022.eurali.xml +++ b/data/xml/2022.eurali.xml @@ -111,7 +111,7 @@ MaksimMelenchenko DmitryNovokshanov 61–64 - This poster describes the Shughni Documentation Project consisting of the Online Shughni Dictionary, morphological analyzer, orthography converter, and Shughni corpus. The online dictionary has not only basic functions such as finding words but also facilitates more complex tasks. Representing a lexeme as a network of database sections makes it possible to search in particular domains (e.g., in meanings only), and the system of labels facilitates conditional search queries. Apart from this, users can make search queries and view entries in different orthographies of the Shughni language and send feedback in case they spot mistakes. Editors can add, modify, or delete entries without programming skills via an intuitive interface. In future, such website architecture can be applied to creating a lexical database of Iranian languages. The morphological analyzer performs automatic analysis of Shughni texts, which is useful for linguistic research and documentation. Once the analysis is complete, homonymy resolution must be conducted so that the annotated texts are ready to be uploaded to the corpus. The analyzer makes use of the orthographic converter, which helps to tackle the problem of spelling variability in Shughni, a language with no standard literary tradition. + This paper describes the Shughni Documentation Project consisting of the Online Shughni Dictionary, morphological analyzer, orthography converter, and Shughni corpus. The online dictionary has not only basic functions such as finding words but also facilitates more complex tasks. Representing a lexeme as a network of database sections makes it possible to search in particular domains (e.g., in meanings only), and the system of labels facilitates conditional search queries. Apart from this, users can make search queries and view entries in different orthographies of the Shughni language and send feedback in case they spot mistakes. Editors can add, modify, or delete entries without programming skills via an intuitive interface. In future, such website architecture can be applied to creating a lexical database of Iranian languages. The morphological analyzer performs automatic analysis of Shughni texts, which is useful for linguistic research and documentation. Once the analysis is complete, homonymy resolution must be conducted so that the annotated texts are ready to be uploaded to the corpus. The analyzer makes use of the orthographic converter, which helps to tackle the problem of spelling variability in Shughni, a language with no standard literary tradition. 2022.eurali-1.9 makarov-etal-2022-digital diff --git a/data/xml/2022.findings.xml b/data/xml/2022.findings.xml index 216e15210a..2ca83c921a 100644 --- a/data/xml/2022.findings.xml +++ b/data/xml/2022.findings.xml @@ -2779,7 +2779,7 @@ <fixed-case>C</fixed-case>hart<fixed-case>QA</fixed-case>: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning AhmedMasry - DoLong + Xuan LongDo Jia QingTan ShafiqJoty EnamulHoque @@ -8943,7 +8943,7 @@ oguz-etal-2022-chop - "#<fixed-case>D</fixed-case>isabled<fixed-case>O</fixed-case>n<fixed-case>I</fixed-case>ndian<fixed-case>T</fixed-case>witter” : A Dataset towards Understanding the Expression of People with Disabilities on <fixed-case>I</fixed-case>ndian <fixed-case>T</fixed-case>witter + “#<fixed-case>D</fixed-case>isabled<fixed-case>O</fixed-case>n<fixed-case>I</fixed-case>ndian<fixed-case>T</fixed-case>witter” : A Dataset towards Understanding the Expression of People with Disabilities on <fixed-case>I</fixed-case>ndian <fixed-case>T</fixed-case>witter IshaniMondal SukhnidhKaur KalikaBali @@ -9998,7 +9998,7 @@ You Truly Understand What <fixed-case>I</fixed-case> Need : Intellectual and Friendly Dialog Agents grounding Persona and Knowledge JungwooLim - MyugnhoonKang + MyunghoonKang YunaHur Seung WonJeong JinsungKim @@ -11262,6 +11262,7 @@ Faster and Smaller Speech Translation without Quality Compromise <fixed-case>TAPE</fixed-case>: Assessing Few-shot <fixed-case>R</fixed-case>ussian Language Understanding EkaterinaTaktasheva + TatianaShavrina AlenaFenogenova DenisShevelev NadezhdaKatricheva @@ -11270,10 +11271,9 @@ Faster and Smaller Speech Translation without Quality Compromise OlegZinkevich AnastasiiaBashmakova SvetlanaIordanskaia - ValentinaKurenshchikova AlenaSpiridonova + ValentinaKurenshchikova EkaterinaArtemova - TatianaShavrina VladislavMikhailov 2472-2497 Recent advances in zero-shot and few-shot learning have shown promise for a scope of research and practical purposes. However, this fast-growing area lacks standardized evaluation suites for non-English languages, hindering progress outside the Anglo-centric paradigm. To address this line of research, we propose TAPE (Text Attack and Perturbation Evaluation), a novel benchmark that includes six more complex NLU tasks for Russian, covering multi-hop reasoning, ethical concepts, logic and commonsense knowledge. The TAPE’s design focuses on systematic zero-shot and few-shot NLU evaluation: (i) linguistic-oriented adversarial attacks and perturbations for analyzing robustness, and (ii) subpopulations for nuanced interpretation. The detailed analysis of testing the autoregressive baselines indicates that simple spelling-based perturbations affect the performance the most, while paraphrasing the input has a more negligible effect. At the same time, the results demonstrate a significant gap between the neural and human baselines for most tasks. We publicly release TAPE (https://tape-benchmark.com) to foster research on robust LMs that can generalize to new tasks when little to no supervision is available. @@ -11301,8 +11301,10 @@ Faster and Smaller Speech Translation without Quality Compromise SimyungChang 2510-2517 Transformer language models such as GPT-2 are difficult to quantize because of outliers in the activations leading to a large quantization error. To adapt to the error, one must use quantization-aware training, which entails a fine-tuning process based on the dataset and the training pipeline identical to those for the original model. Pretrained language models, however, often do not grant access to their datasets and training pipelines, forcing us to rely on arbitrary ones for fine-tuning. In that case, it is observed that quantization-aware training overfits the model to the fine-tuning data. To this end introduced is a quantization adapter (Quadapter), a small set of parameters that are learned to make activations quantization-friendly by scaling them channel-wise.For quantization without overfitting, we introduce a quantization adapter (Quadapter), a small set of parameters that are learned to make activations quantization-friendly by scaling them channel-wise. It keeps the model parameters unchanged. By applying our method to the challenging task of quantizing GPT-2, we demonstrate that it effectively prevents the overfitting and improves the quantization performance. - 2022.findings-emnlp.185 + 2022.findings-emnlp.185 park-etal-2022-quadapter + + Author info correction. <fixed-case>B</fixed-case>angla<fixed-case>RQA</fixed-case>: A Benchmark Dataset for Under-resourced <fixed-case>B</fixed-case>angla Language Reading Comprehension-based Question Answering with Diverse Question-Answer Types @@ -14791,6 +14793,7 @@ Faster and Smaller Speech Translation without Quality Compromise PeeratLimkonchotiwat WuttikornPonwitayarat LalitaLowphansirikul + CanUdomcharoenchaikit EkapolChuangsuwanich SaranaNutanong 6467-6480 diff --git a/data/xml/2022.inlg.xml b/data/xml/2022.inlg.xml index 6ed38a7d63..e10d9d33b4 100644 --- a/data/xml/2022.inlg.xml +++ b/data/xml/2022.inlg.xml @@ -10,7 +10,7 @@
Waterville, Maine, USA and virtual meeting
July 2022 - 2022.inlg-main + 2022.inlg-main inlg @@ -300,6 +300,16 @@ 2022.inlg-main.24.software.zip chaudhary-etal-2022-current + + Analogy Generation by Prompting Large Language Models: A Case Study of InstructGPT + BhavyaBhavya + JinjunXiong + ChengXiangZhai + 298-312 + + 2022.inlg-main.25 + bhavya-etal-2022-analogy + diff --git a/data/xml/2022.lrec.xml b/data/xml/2022.lrec.xml index fcfb269fc5..c48de9c4e6 100644 --- a/data/xml/2022.lrec.xml +++ b/data/xml/2022.lrec.xml @@ -7616,7 +7616,7 @@ <fixed-case>HADREB</fixed-case>: Human Appraisals and (<fixed-case>E</fixed-case>nglish) Descriptions of Robot Emotional Behaviors - JosueTorres-Fonsesca + JosueTorres-Fonseca CaseyKennington 5739–5748 Humans sometimes anthropomorphize everyday objects, but especially robots that have human-like qualities and that are often able to interact with and respond to humans in ways that other objects cannot. Humans especially attribute emotion to robot behaviors, partly because humans often use and interpret emotions when interacting with other humans, and they apply that capability when interacting with robots. Moreover, emotions are a fundamental part of the human language system and emotions are used as scaffolding for language learning, making them an integral part of language learning and meaning. However, there are very few datasets that explore how humans perceive the emotional states of robots and how emotional behaviors relate to human language. To address this gap we have collected HADREB, a dataset of human appraisals and English descriptions of robot emotional behaviors collected from over 30 participants. These descriptions and human emotion appraisals are collected using the Mistyrobotics Misty II and the Digital Dream Labs Cozmo (formerly Anki) robots. The dataset contains English descriptions and emotion appraisals of more than 500 descriptions and graded valence labels of 8 emotion pairs for each behavior and each robot. In this paper we describe the process of collecting and cleaning the data, give a general analysis of the data, and evaluate the usefulness of the dataset in two experiments, one using a language model to map descriptions to emotions, the other maps robot behaviors to emotions. diff --git a/data/xml/2022.mrl.xml b/data/xml/2022.mrl.xml index 292efc9de4..e0120a411a 100644 --- a/data/xml/2022.mrl.xml +++ b/data/xml/2022.mrl.xml @@ -97,8 +97,10 @@ AmirZeldesGeorgetown University 86-99 BERT-style contextualized word embedding models are critical for good performance in most NLP tasks, but they are data-hungry and therefore difficult to train for low-resource languages. In this work, we investigate whether a combination of greatly reduced model size and two linguistically rich auxiliary pretraining tasks (part-of-speech tagging and dependency parsing) can help produce better BERTs in a low-resource setting. Results from 7 diverse languages indicate that our model, MicroBERT, is able to produce marked improvements in downstream task evaluations, including gains up to 18% for parser LAS and 11% for NER F1 compared to an mBERT baseline, and we achieve these results with less than 1% of the parameter count of a multilingual BERT base–sized model. We conclude that training very small BERTs and leveraging any available labeled data for multitask learning during pretraining can produce models which outperform both their multilingual counterparts and traditional fixed embeddings for low-resource languages. - 2022.mrl-1.9 + 2022.mrl-1.9 gessler-zeldes-2022-microbert + + Updated Section 6 and Appendix C. Transformers on Multilingual Clause-Level Morphology diff --git a/data/xml/2022.naacl.xml b/data/xml/2022.naacl.xml index 5a00ebffca..261eadccaa 100644 --- a/data/xml/2022.naacl.xml +++ b/data/xml/2022.naacl.xml @@ -1587,7 +1587,7 @@ PatrickFernandes AntónioFarinhas RicardoRei - JoséDe Souza + José G.C. de Souza PerezOgayo GrahamNeubig AndreMartins diff --git a/data/xml/2022.nllp.xml b/data/xml/2022.nllp.xml index 04f3f93582..660dc3172e 100644 --- a/data/xml/2022.nllp.xml +++ b/data/xml/2022.nllp.xml @@ -307,12 +307,12 @@ Legal Named Entity Recognition with Multi-Task Domain Adaptation - Răzvan-alexandruSmăduUniversity Politehnica of Bucharest - Ion-robertDinicăUniversity Politehnica of Bucharest - Andrei-mariusAvramResearch Institute for Artificial Intelligence, Romanian Academy - Dumitru-clementinCercelUniversity Politehnica of Bucharest + Răzvan-AlexandruSmăduUniversity Politehnica of Bucharest + Ion-RobertDinicăUniversity Politehnica of Bucharest + Andrei-MariusAvramResearch Institute for Artificial Intelligence, Romanian Academy + Dumitru-ClementinCercelUniversity Politehnica of Bucharest FlorinPopUniversity Politehnica of Bucharest - Mihaela-claudiaCercelFirst District Court of Giurgiu + Mihaela-ClaudiaCercelFirst District Court of Giurgiu 305-321 Named Entity Recognition (NER) is a well-explored area from Information Retrieval and Natural Language Processing with an extensive research community. Despite that, few languages, such as English and German, are well-resourced, whereas many other languages, such as Romanian, have scarce resources, especially in domain-specific applications. In this work, we address the NER problem in the legal domain from both Romanian and German languages and evaluate the performance of our proposed method based on domain adaptation. We employ multi-task learning to jointly train a neural network on two legal and general domains and perform adaptation among them. The results show that domain adaptation increase performances by a small amount, under 1%, while considerable improvements are in the recall metric. 2022.nllp-1.29 diff --git a/data/xml/2022.sigdial.xml b/data/xml/2022.sigdial.xml index fd4e4476e0..25eec3b9a0 100644 --- a/data/xml/2022.sigdial.xml +++ b/data/xml/2022.sigdial.xml @@ -181,7 +181,7 @@ Symbol and Communicative Grounding through Object Permanence with a Mobile Robot - JosueTorres-Foncesca + JosueTorres-Fonseca CatherineHenry CaseyKennington 124–134 diff --git a/data/xml/2022.sustainlp.xml b/data/xml/2022.sustainlp.xml index 12948d71f5..f9eb9a7c16 100644 --- a/data/xml/2022.sustainlp.xml +++ b/data/xml/2022.sustainlp.xml @@ -99,8 +99,10 @@ ChrisEmezue 52-64 In recent years, multilingual pre-trained language models have gained prominence due to their remarkable performance on numerous downstream Natural Language Processing tasks (NLP). However, pre-training these large multilingual language models requires a lot of training data, which is not available for African Languages. Active learning is a semi-supervised learning algorithm, in which a model consistently and dynamically learns to identify the most beneficial samples to train itself on, in order to achieve better optimization and performance on downstream tasks. Furthermore, active learning effectively and practically addresses real-world data scarcity. Despite all its benefits, active learning, in the context of NLP and especially multilingual language models pretraining, has received little consideration. In this paper, we present AfroLM, a multilingual language model pretrained from scratch on 23 African languages (the largest effort to date) using our novel self-active learning framework. Pretrained on a dataset significantly (14x) smaller than existing baselines, AfroLM outperforms many multilingual pretrained language models (AfriBERTa, XLMR-base, mBERT) on various NLP downstream tasks (NER, text classification, and sentiment analysis). Additional out-of-domain sentiment analysis experiments show that AfroLM is able to generalize well across various domains. We release the code source, and our datasets used in our framework at https://github.com/bonaventuredossou/MLM_AL. - 2022.sustainlp-1.11 + 2022.sustainlp-1.11 dossou-etal-2022-afrolm + + Crucial fixes to the paper. Towards Fair Dataset Distillation for Text Classification diff --git a/data/xml/2022.tsar.xml b/data/xml/2022.tsar.xml index 954caa5b93..95b85aa6c4 100644 --- a/data/xml/2022.tsar.xml +++ b/data/xml/2022.tsar.xml @@ -15,7 +15,7 @@
Abu Dhabi, United Arab Emirates (Virtual)
December 2022 - 2022.tsar-1 + 2022.tsar-1 tsar @@ -323,5 +323,19 @@ 2022.tsar-1.30 north-etal-2022-gmu + + Findings of the TSAR-2022 Shared Task on Multilingual Lexical Simplification + HoracioSaggionUniversitat Pompeu Fabra + SanjaŠtajnerKarlsruhe + DanielFerrésUniversitat Pompeu Fabra + Kim ChengSheangUniversitat Pompeu Fabra + MatthewShardlowManchester Metropolitan University + KaiNorthGeorge Mason University + MarcosZampieriGeorge Mason University + 271-283 + We report findings of the TSAR-2022 shared task on multilingual lexical simplification, organized as part of the Workshop on Text Simplification, Accessibility, and Readability TSAR-2022 held in conjunction with EMNLP 2022. The task called the Natural Language Processing research community to contribute with methods to advance the state of the art in multilingual lexical simplification for English, Portuguese, and Spanish. A total of 14 teams submitted the results of their lexical simplification systems for the provided test data. Results of the shared task indicate new benchmarks in Lexical Simplification with English lexical simplification quantitative results noticeably higher than those obtained for Spanish and (Brazilian) Portuguese. + 2022.tsar-1.31 + saggion-etal-2022-findings + diff --git a/data/xml/2022.wanlp.xml b/data/xml/2022.wanlp.xml index 0f0f616649..787b8dd63b 100644 --- a/data/xml/2022.wanlp.xml +++ b/data/xml/2022.wanlp.xml @@ -149,8 +149,10 @@ PreslavNakovMohamed bin Zayed University of Artificial Intelligence 108-118 Propaganda is defined as an expression of opinion or action by individuals or groups deliberately designed to influence opinions or actions of other individuals or groups with reference to predetermined ends and this is achieved by means of well-defined rhetorical and psychological devices. Currently, propaganda (or persuasion) techniques have been commonly used on social media to manipulate or mislead social media users. Automatic detection of propaganda techniques from textual, visual, or multimodal content has been studied recently, however, major of such efforts are focused on English language content. In this paper, we propose a shared task on detecting propaganda techniques for Arabic textual content. We have done a pilot annotation of 200 Arabic tweets, which we plan to extend to 2,000 tweets, covering diverse topics. We hope that the shared task will help in building a community for Arabic propaganda detection. The dataset will be made publicly available, which can help in future studies. - 2022.wanlp-1.11 + 2022.wanlp-1.11 alam-etal-2022-overview + + Corrected one paper title. <fixed-case>A</fixed-case>rz<fixed-case>E</fixed-case>n-<fixed-case>ST</fixed-case>: A Three-way Speech Translation Corpus for Code-Switched <fixed-case>E</fixed-case>gyptian <fixed-case>A</fixed-case>rabic-<fixed-case>E</fixed-case>nglish @@ -669,8 +671,10 @@ AntonioTannouryData Scientist 520-523 Nowadays, the rapid dissemination of data on digital platforms has resulted in the emergence of information pollution and data contamination, specifically mis-information, mal-information, dis-information, fake news, and various types of propaganda. These topics are now posing a serious threat to the online digital realm, posing numerous challenges to social media platforms and governments around the world. In this article, we propose a propaganda detection model based on the transformer-based model AraBERT, with the objective of using this framework to detect propagandistic content in the Arabic social media text scene, well with purpose of making online Arabic news and media consumption healthier and safer. Given the dataset, our results are relatively encouraging, indicating a huge potential for this line of approaches in Arabic online news text NLP. - 2022.wanlp-1.61 + 2022.wanlp-1.61 sharara-etal-2022-arabert + + Corrected author name. <fixed-case>A</fixed-case>ra<fixed-case>BEM</fixed-case> at <fixed-case>WANLP</fixed-case> 2022 Shared Task: Propaganda Detection in <fixed-case>A</fixed-case>rabic Tweets diff --git a/data/xml/2022.wmt.xml b/data/xml/2022.wmt.xml index 81dfeb756c..7ac7de0a4d 100644 --- a/data/xml/2022.wmt.xml +++ b/data/xml/2022.wmt.xml @@ -91,7 +91,7 @@ FrédéricBlainUniversity of Wolverhampton RicardoReiUnbabel/INESC-ID PiyawatLertvittayakumjornGoogle - José G.C. De SouzaUnbabel + José G.C. de SouzaUnbabel SteffenEgerNLLG Lab, Bielefeld University DipteshKanojiaUniversity of Surrey DuarteAlvesInstituto Superior Técnico / Unbabel @@ -561,7 +561,7 @@ DuarteAlvesInstituto Superior Técnico / Unbabel RicardoReiUnbabel/INESC-ID Ana CFarinhaUnbabel - José G.C. De SouzaUnbabel + José G.C. de SouzaUnbabel André F. T.MartinsUnbabel, Instituto de Telecomunicacoes 469-478 Automatic translations with critical errors may lead to misinterpretations and pose several risks for the user. As such, it is important that Machine Translation (MT) Evaluation systems are robust to these errors in order to increase the reliability and safety of Machine Translation systems. Here we introduce SMAUG a novel Sentence-level Multilingual AUGmentation approach for generating translations with critical errors and apply this approach to create a test set to evaluate the robustness of MT metrics to these errors. We show that current State-of-the-Art metrics are improving their capability to distinguish translations with and without critical errors and to penalize the first accordingly. We also show that metrics tend to struggle with errors related to named entities and numbers and that there is a high variance in the robustness of current methods to translations with critical errors. @@ -576,8 +576,10 @@ LianeGuillouThe University of Edinburgh 479-513 As machine translation (MT) metrics improve their correlation with human judgement every year, it is crucial to understand the limitations of these metrics at the segment level. Specifically, it is important to investigate metric behaviour when facing accuracy errors in MT because these can have dangerous consequences in certain contexts (e.g., legal, medical). We curate ACES, a translation accuracy challenge set, consisting of 68 phenomena ranging from simple perturbations at the word/character level to more complex errors based on discourse and real-world knowledge. We use ACES to evaluate a wide range of MT metrics including the submissions to the WMT 2022 metrics shared task and perform several analyses leading to general recommendations for metric developers. We recommend: a) combining metrics with different strengths, b) developing metrics that give more weight to the source and less to surface-level overlap with the reference and c) explicitly modelling additional language-specific information beyond what is available via multilingual embeddings. - 2022.wmt-1.44 + 2022.wmt-1.44 amrhein-etal-2022-aces + + Corrected tables. Linguistically Motivated Evaluation of Machine Translation Metrics Based on a Challenge Set @@ -673,7 +675,7 @@ <fixed-case>COMET</fixed-case>-22: Unbabel-<fixed-case>IST</fixed-case> 2022 Submission for the Metrics Shared Task RicardoReiUnbabel/INESC-ID - José G.C. De SouzaUnbabel + José G.C. de SouzaUnbabel DuarteAlvesInstituto Superior Técnico / Unbabel ChrysoulaZervaInstituto de Telecomunicações, Instituto Superior Técnico, University of Lisbon Ana CFarinhaUnbabel @@ -709,8 +711,10 @@ MarineCarpuatUniversity of Maryland 593-596 This paper describes submission to the WMT 2022 Quality Estimation shared task (Task 1: sentence-level quality prediction). We follow a simple and intuitive approach, which consists of estimating MT quality by automatically back-translating hypotheses into the source language using a multilingual MT system. We then compare the resulting backtranslation with the original source using standard MT evaluation metrics. We find that even the best-performing backtranslation-based scores perform substantially worse than supervised QE systems, including the organizers’ baseline. However, combining backtranslation-based metrics with off-the-shelf QE scorers improves correlation with human judgments, suggesting that they can indeed complement a supervised QE system. - 2022.wmt-1.54 + 2022.wmt-1.54 agrawal-etal-2022-quality + + Corrected Acknowledgement. <fixed-case>A</fixed-case>libaba-Translate <fixed-case>C</fixed-case>hina’s Submission for <fixed-case>WMT</fixed-case> 2022 Quality Estimation Shared Task @@ -784,7 +788,7 @@ ChrysoulaZervaInstituto de Telecomunicações, Instituto Superior Técnico, University of Lisbon Ana CFarinhaUnbabel ChristineMarotiUnbabel - José G.C. De SouzaUnbabel + José G.C. de SouzaUnbabel TaisiyaGlushkovaInstituto de Telecomunicações, Instituto Superior Técnico, University of Lisbon DuarteAlvesInstituto Superior Técnico / Unbabel LuisaCoheurINESC-ID/Instituto Superior Técnico @@ -929,7 +933,7 @@ M. AminFarajianUnbabel MariannaBuchicchioUnbabel PatrickFernandesCarnegie Mellon University, Instituto de Telecomunicações - José G.C. De SouzaUnbabel + José G.C. de SouzaUnbabel HelenaMonizINESC-ID, University of Lisbon André F. T.MartinsUnbabel, Instituto de Telecomunicacoes 724-743 @@ -1181,7 +1185,7 @@ Unbabel-<fixed-case>IST</fixed-case> at the <fixed-case>WMT</fixed-case> Chat Translation Shared Task JoãoAlvesUnbabel Pedro HenriqueMartinsInstituto de Telecomunicações, Instituto Superior Técnico - José G.C. De SouzaUnbabel + José G.C. de SouzaUnbabel M. AminFarajianUnbabel André F. T.MartinsUnbabel, Instituto de Telecomunicacoes 943-948 diff --git a/data/xml/W19.xml b/data/xml/W19.xml index 279af035be..c1591922cf 100644 --- a/data/xml/W19.xml +++ b/data/xml/W19.xml @@ -13288,7 +13288,7 @@ One of the references was wrong therefore it is corrected to cite the appropriat Can <fixed-case>M</fixed-case>odern <fixed-case>S</fixed-case>tandard <fixed-case>A</fixed-case>rabic Approaches be used for <fixed-case>A</fixed-case>rabic Dialects? Sentiment Analysis as a Case Study - ChatrineQwaider + KathreinAbu Kwaik StergiosChatzikyriakidis SimonDobnik 40–50 @@ -15962,7 +15962,7 @@ One of the references was wrong therefore it is corrected to cite the appropriat FrancisTyers JonathanWashington 24–31 - W19-6805 + W19-6805 gokirmak-etal-2019-machine diff --git a/data/yaml/name_variants.yaml b/data/yaml/name_variants.yaml index 6048edbe63..714de5b3c7 100644 --- a/data/yaml/name_variants.yaml +++ b/data/yaml/name_variants.yaml @@ -2943,6 +2943,10 @@ - canonical: {first: Kok Wee, last: Gan} variants: - {first: Kok-Wee, last: Gan} +- canonical: {first: Mattia A., last: Di Gangi} + variants: + - {first: Mattia Antonino, last: Di Gangi} + - {first: Mattia, last: Di Gangi} - canonical: {first: Surya, last: Ganesh} variants: - {first: Surya Ganesh, last: V} diff --git a/data/yaml/sigs/sigdial.yaml b/data/yaml/sigs/sigdial.yaml index 48d0230f65..d6017006c2 100644 --- a/data/yaml/sigs/sigdial.yaml +++ b/data/yaml/sigs/sigdial.yaml @@ -2,6 +2,8 @@ Name: ACL/ISCA Special Interest Group on Discourse and Dialogue ShortName: SIGDIAL URL: http://www.aclweb.org/sigdial Meetings: + - 2022: + - 2022.sigdial-1 - 2021: - 2021.sigdial-1 # Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue - 2020: diff --git a/data/yaml/sigs/siggen.yaml b/data/yaml/sigs/siggen.yaml index ce21be058c..0424ca6e7e 100644 --- a/data/yaml/sigs/siggen.yaml +++ b/data/yaml/sigs/siggen.yaml @@ -6,6 +6,7 @@ Meetings: - 2022.inlg-main - 2022.inlg-demos - 2022.nlg4health-1 + - 2022.gem-1 - 2022.inlg-genchal - 2021: - 2021.inlg-1