Transactions of the Association for Computational Linguistics最新文献_第10页

How to Dissect a Muppet: The Structure of Transformer Embedding Spaces 如何解剖布偶:变压器嵌入空间的结构

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-06-07 DOI: 10.1162/tacl_a_00501

Timothee Mickus, Denis Paperno, Mathieu Constant

引用次数: 10

Heterogeneous Supervised Topic Models 异构监督主题模型

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-06-01 DOI: 10.1162/tacl_a_00487

Dhanya Sridhar, Hal Daumé, D. Blei

引用次数: 4

Uncertainty Estimation and Reduction of Pre-trained Models for Text Regression 文本回归预训练模型的不确定性估计与减少

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-06-01 DOI: 10.1162/tacl_a_00483

Yuxia Wang, Daniel Beck, Timothy Baldwin, K. Verspoor

引用次数: 13

Naturalistic Causal Probing for Morpho-Syntax 形态句法的自然因果探究

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-05-14 DOI: 10.1162/tacl_a_00554

Afra Amini, Tiago Pimentel, Clara Meister, Ryan Cotterell

引用次数: 7

Document Summarization with Latent Queries 具有潜在查询的文档摘要

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-05-01 DOI: 10.1162/tacl_a_00480

Yumo Xu, Mirella Lapata

引用次数: 15

A Neighborhood Framework for Resource-Lean Content Flagging 资源精益内容标记的邻域框架

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-05-01 DOI: 10.1162/tacl_a_00472

Sheikh Muhammad Sarwar, Dimitrina Zlatkova, Momchil Hardalov, Yoan Dinkov, Isabelle Augenstein, Preslav Nakov

{"title":"A Neighborhood Framework for Resource-Lean Content Flagging","authors":"Sheikh Muhammad Sarwar, Dimitrina Zlatkova, Momchil Hardalov, Yoan Dinkov, Isabelle Augenstein, Preslav Nakov","doi":"10.1162/tacl_a_00472","DOIUrl":"https://doi.org/10.1162/tacl_a_00472","url":null,"abstract":"We propose a novel framework for cross- lingual content flagging with limited target- language data, which significantly outperforms prior work in terms of predictive performance. The framework is based on a nearest-neighbor architecture. It is a modern instantiation of the vanilla k-nearest neighbor model, as we use Transformer representations in all its components. Our framework can adapt to new source- language instances, without the need to be retrained from scratch. Unlike prior work on neighborhood-based approaches, we encode the neighborhood information based on query– neighbor interactions. We propose two encoding schemes and we show their effectiveness using both qualitative and quantitative analysis. Our evaluation results on eight languages from two different datasets for abusive language detection show sizable improvements of up to 9.5 F1 points absolute (for Italian) over strong baselines. On average, we achieve 3.6 absolute F1 points of improvement for the three languages in the Jigsaw Multilingual dataset and 2.14 points for the WUL dataset.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"10 1","pages":"484-502"},"PeriodicalIF":10.9,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48734165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

End-to-end Argument Mining with Cross-corpora Multi-task Learning 跨语料库多任务学习的端到端论证挖掘

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-05-01 DOI: 10.1162/tacl_a_00481

Gaku Morio, Hiroaki Ozaki, Terufumi Morishita, Kohsuke Yanai

引用次数: 5

Visual Spatial Reasoning 视觉空间推理

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-04-30 DOI: 10.1162/tacl_a_00566

Fangyu Liu, Guy Edward Toh Emerson, Nigel Collier

引用次数: 35

FaithDial: A Faithful Benchmark for Information-Seeking Dialogue 忠实拨号:信息寻求对话的忠实基准

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-04-22 DOI: 10.1162/tacl_a_00529

Nouha Dziri, Ehsan Kamalloo, Sivan Milton, Osmar Zaiane, Mo Yu, E. Ponti, Siva Reddy

{"title":"FaithDial: A Faithful Benchmark for Information-Seeking Dialogue","authors":"Nouha Dziri, Ehsan Kamalloo, Sivan Milton, Osmar Zaiane, Mo Yu, E. Ponti, Siva Reddy","doi":"10.1162/tacl_a_00529","DOIUrl":"https://doi.org/10.1162/tacl_a_00529","url":null,"abstract":"Abstract The goal of information-seeking dialogue is to respond to seeker queries with natural language utterances that are grounded on knowledge sources. However, dialogue systems often produce unsupported utterances, a phenomenon known as hallucination. To mitigate this behavior, we adopt a data-centric solution and create FaithDial, a new benchmark for hallucination-free dialogues, by editing hallucinated responses in the Wizard of Wikipedia (WoW) benchmark. We observe that FaithDial is more faithful than WoW while also maintaining engaging conversations. We show that FaithDial can serve as training signal for: i) a hallucination critic, which discriminates whether an utterance is faithful or not, and boosts the performance by 12.8 F1 score on the BEGIN benchmark compared to existing datasets for dialogue coherence; ii) high-quality dialogue generation. We benchmark a series of state-of-the-art models and propose an auxiliary contrastive objective that achieves the highest level of faithfulness and abstractiveness based on several automated metrics. Further, we find that the benefits of FaithDial generalize to zero-shot transfer on other datasets, such as CMU-Dog and TopicalChat. Finally, human evaluation reveals that responses generated by models trained on FaithDial are perceived as more interpretable, cooperative, and engaging.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"10 1","pages":"1473-1490"},"PeriodicalIF":10.9,"publicationDate":"2022-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47575589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 39

Chinese Idiom Paraphrasing 汉语习语释义

IF 10.9 1区计算机科学

Transactions of the Association for Computational Linguistics Pub Date : 2022-04-15 DOI: 10.1162/tacl_a_00572

Jipeng Qiang, Yang Li, Chaowei Zhang, Yun Li, Yunhao Yuan, Yi Zhu, Xin Wu

{"title":"Chinese Idiom Paraphrasing","authors":"Jipeng Qiang, Yang Li, Chaowei Zhang, Yun Li, Yunhao Yuan, Yi Zhu, Xin Wu","doi":"10.1162/tacl_a_00572","DOIUrl":"https://doi.org/10.1162/tacl_a_00572","url":null,"abstract":"Abstract Idioms are a kind of idiomatic expression in Chinese, most of which consist of four Chinese characters. Due to the properties of non-compositionality and metaphorical meaning, Chinese idioms are hard to be understood by children and non-native speakers. This study proposes a novel task, denoted as Chinese Idiom Paraphrasing (CIP). CIP aims to rephrase idiom-containing sentences to non-idiomatic ones under the premise of preserving the original sentence’s meaning. Since the sentences without idioms are more easily handled by Chinese NLP systems, CIP can be used to pre-process Chinese datasets, thereby facilitating and improving the performance of Chinese NLP tasks, e.g., machine translation systems, Chinese idiom cloze, and Chinese idiom embeddings. In this study, we can treat the CIP task as a special paraphrase generation task. To circumvent difficulties in acquiring annotations, we first establish a large-scale CIP dataset based on human and machine collaboration, which consists of 115,529 sentence pairs. In addition to three sequence-to-sequence methods as the baselines, we further propose a novel infill-based approach based on text infilling. The results show that the proposed method has better performance than the baselines based on the established CIP dataset.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"11 1","pages":"740-754"},"PeriodicalIF":10.9,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42968525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2