Proceedings of COLING. International Conference on Computational Linguistics最新文献

筛选
英文 中文
CoLo: A Contrastive Learning Based Re-ranking Framework for One-Stage Summarization CoLo:一种基于对比学习的单阶段总结重新排序框架
Proceedings of COLING. International Conference on Computational Linguistics Pub Date : 2022-09-29 DOI: 10.48550/arXiv.2209.14569
Chen An, Ming Zhong, Zhiyong Wu, Qinen Zhu, Xuanjing Huang, Xipeng Qiu
{"title":"CoLo: A Contrastive Learning Based Re-ranking Framework for One-Stage Summarization","authors":"Chen An, Ming Zhong, Zhiyong Wu, Qinen Zhu, Xuanjing Huang, Xipeng Qiu","doi":"10.48550/arXiv.2209.14569","DOIUrl":"https://doi.org/10.48550/arXiv.2209.14569","url":null,"abstract":"Traditional training paradigms for extractive and abstractive summarization systems always only use token-level or sentence-level training objectives. However, the output summary is always evaluated from summary-level which leads to the inconsistency in training and evaluation. In this paper, we propose a Contrastive Learning based re-ranking framework for one-stage summarization called CoLo. By modeling a contrastive objective, we show that the summarization model is able to directly generate summaries according to the summary-level score without additional modules and parameters. Extensive experiments demonstrate that CoLo boosts the extractive and abstractive results of one-stage systems on CNN/DailyMail benchmark to 44.58 and 46.33 ROUGE-1 score while preserving the parameter efficiency and inference efficiency. Compared with state-of-the-art multi-stage systems, we save more than 100 GPU training hours and obtaining 3x 8x speed-up ratio during inference while maintaining comparable results.","PeriodicalId":91381,"journal":{"name":"Proceedings of COLING. International Conference on Computational Linguistics","volume":"22 1","pages":"5783-5793"},"PeriodicalIF":0.0,"publicationDate":"2022-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88046517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection 用于可解释假新闻检测的粗到细级联证据蒸馏神经网络
Proceedings of COLING. International Conference on Computational Linguistics Pub Date : 2022-09-29 DOI: 10.48550/arXiv.2209.14642
Zhiwei Yang, Jing Ma, Hechang Chen, Hongzhan Lin, Ziyang Luo, Yi Chang
{"title":"A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection","authors":"Zhiwei Yang, Jing Ma, Hechang Chen, Hongzhan Lin, Ziyang Luo, Yi Chang","doi":"10.48550/arXiv.2209.14642","DOIUrl":"https://doi.org/10.48550/arXiv.2209.14642","url":null,"abstract":"Existing fake news detection methods aim to classify a piece of news as true or false and provide veracity explanations, achieving remarkable performances. However, they often tailor automated solutions on manual fact-checked reports, suffering from limited news coverage and debunking delays. When a piece of news has not yet been fact-checked or debunked, certain amounts of relevant raw reports are usually disseminated on various media outlets, containing the wisdom of crowds to verify the news claim and explain its verdict. In this paper, we propose a novel Coarse-to-fine Cascaded Evidence-Distillation (CofCED) neural network for explainable fake news detection based on such raw reports, alleviating the dependency on fact-checked ones. Specifically, we first utilize a hierarchical encoder for web text representation, and then develop two cascaded selectors to select the most explainable sentences for verdicts on top of the selected top-K reports in a coarse-to-fine manner. Besides, we construct two explainable fake news datasets, which is publicly available. Experimental results demonstrate that our model significantly outperforms state-of-the-art detection baselines and generates high-quality explanations from diverse evaluation perspectives.","PeriodicalId":91381,"journal":{"name":"Proceedings of COLING. International Conference on Computational Linguistics","volume":"1 1","pages":"2608-2621"},"PeriodicalIF":0.0,"publicationDate":"2022-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74330774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing 生成和检索:使用您的预测来改进语义解析的检索
Proceedings of COLING. International Conference on Computational Linguistics Pub Date : 2022-09-29 DOI: 10.48550/arXiv.2209.14899
Yury Zemlyanskiy, Michiel de Jong, J. Ainslie, Panupong Pasupat, Peter Shaw, Linlu Qiu, Sumit K. Sanghai, Fei Sha
{"title":"Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing","authors":"Yury Zemlyanskiy, Michiel de Jong, J. Ainslie, Panupong Pasupat, Peter Shaw, Linlu Qiu, Sumit K. Sanghai, Fei Sha","doi":"10.48550/arXiv.2209.14899","DOIUrl":"https://doi.org/10.48550/arXiv.2209.14899","url":null,"abstract":"A common recent approach to semantic parsing augments sequence-to-sequence models by retrieving and appending a set of training samples, called exemplars. The effectiveness of this recipe is limited by the ability to retrieve informative exemplars that help produce the correct parse, which is especially challenging in low-resource settings. Existing retrieval is commonly based on similarity of query and exemplar inputs. We propose GandR, a retrieval procedure that retrieves exemplars for which outputs are also similar. GandR first generates a preliminary prediction with input-based retrieval. Then, it retrieves exemplars with outputs similar to the preliminary prediction which are used to generate a final prediction. GandR sets the state of the art on multiple low-resource semantic parsing tasks.","PeriodicalId":91381,"journal":{"name":"Proceedings of COLING. International Conference on Computational Linguistics","volume":"1 1","pages":"4946-4951"},"PeriodicalIF":0.0,"publicationDate":"2022-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89679063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 7
Human-in-the-loop Robotic Grasping Using BERT Scene Representation 基于BERT场景表示的人在环机器人抓取
Proceedings of COLING. International Conference on Computational Linguistics Pub Date : 2022-09-28 DOI: 10.48550/arXiv.2209.14026
Yaoxian Song, Penglei Sun, Pengfei Fang, Linyi Yang, Yanghua Xiao, Yue Zhang
{"title":"Human-in-the-loop Robotic Grasping Using BERT Scene Representation","authors":"Yaoxian Song, Penglei Sun, Pengfei Fang, Linyi Yang, Yanghua Xiao, Yue Zhang","doi":"10.48550/arXiv.2209.14026","DOIUrl":"https://doi.org/10.48550/arXiv.2209.14026","url":null,"abstract":"Current NLP techniques have been greatly applied in different domains. In this paper, we propose a human-in-the-loop framework for robotic grasping in cluttered scenes, investigating a language interface to the grasping process, which allows the user to intervene by natural language commands. This framework is constructed on a state-of-the-art grasping baseline, where we substitute a scene-graph representation with a text representation of the scene using BERT. Experiments on both simulation and physical robot show that the proposed method outperforms conventional object-agnostic and scene-graph based methods in the literature. In addition, we find that with human intervention, performance can be significantly improved. Our dataset and code are available on our project website https://sites.google.com/view/hitl-grasping-bert.","PeriodicalId":91381,"journal":{"name":"Proceedings of COLING. International Conference on Computational Linguistics","volume":"44 1","pages":"2992-3006"},"PeriodicalIF":0.0,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89923721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Assessing Digital Language Support on a Global Scale 评估全球范围内的数字语言支持
Proceedings of COLING. International Conference on Computational Linguistics Pub Date : 2022-09-27 DOI: 10.48550/arXiv.2209.13515
Gary F. Simons, Abbey L. Thomas, Chad White
{"title":"Assessing Digital Language Support on a Global Scale","authors":"Gary F. Simons, Abbey L. Thomas, Chad White","doi":"10.48550/arXiv.2209.13515","DOIUrl":"https://doi.org/10.48550/arXiv.2209.13515","url":null,"abstract":"The users of endangered languages struggle to thrive in a digitally-mediated world. We have developed an automated method for assessing how well every language recognized by ISO 639 is faring in terms of digital language support. The assessment is based on scraping the names of supported languages from the websites of 143 digital tools selected to represent a full range of ways that digital technology can support languages. The method uses Mokken scale analysis to produce an explainable model for quantifying digital language support and monitoring it on a global scale.","PeriodicalId":91381,"journal":{"name":"Proceedings of COLING. International Conference on Computational Linguistics","volume":"13 1","pages":"4299-4305"},"PeriodicalIF":0.0,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87056214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 6
LOViS: Learning Orientation and Visual Signals for Vision and Language Navigation 视觉和语言导航的学习方向和视觉信号
Proceedings of COLING. International Conference on Computational Linguistics Pub Date : 2022-09-26 DOI: 10.48550/arXiv.2209.12723
Yue Zhang, Parisa Kordjamshidi
{"title":"LOViS: Learning Orientation and Visual Signals for Vision and Language Navigation","authors":"Yue Zhang, Parisa Kordjamshidi","doi":"10.48550/arXiv.2209.12723","DOIUrl":"https://doi.org/10.48550/arXiv.2209.12723","url":null,"abstract":"Understanding spatial and visual information is essential for a navigation agent who follows natural language instructions. The current Transformer-based VLN agents entangle the orientation and vision information, which limits the gain from the learning of each information source. In this paper, we design a neural agent with explicit Orientation and Vision modules. Those modules learn to ground spatial information and landmark mentions in the instructions to the visual environment more effectively. To strengthen the spatial reasoning and visual perception of the agent, we design specific pre-training tasks to feed and better utilize the corresponding modules in our final navigation model. We evaluate our approach on both Room2room (R2R) and Room4room (R4R) datasets and achieve the state of the art results on both benchmarks.","PeriodicalId":91381,"journal":{"name":"Proceedings of COLING. International Conference on Computational Linguistics","volume":"39 1","pages":"5745-5754"},"PeriodicalIF":0.0,"publicationDate":"2022-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73908153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Conversational QA Dataset Generation with Answer Revision 会话QA数据集生成与答案修订
Proceedings of COLING. International Conference on Computational Linguistics Pub Date : 2022-09-23 DOI: 10.48550/arXiv.2209.11396
Seonjeong Hwang, G. G. Lee
{"title":"Conversational QA Dataset Generation with Answer Revision","authors":"Seonjeong Hwang, G. G. Lee","doi":"10.48550/arXiv.2209.11396","DOIUrl":"https://doi.org/10.48550/arXiv.2209.11396","url":null,"abstract":"Conversational question-answer generation is a task that automatically generates a large-scale conversational question answering dataset based on input passages. In this paper, we introduce a novel framework that extracts question-worthy phrases from a passage and then generates corresponding questions considering previous conversations. In particular, our framework revises the extracted answers after generating questions so that answers exactly match paired questions. Experimental results show that our simple answer revision approach leads to significant improvement in the quality of synthetic data. Moreover, we prove that our framework can be effectively utilized for domain adaptation of conversational question answering.","PeriodicalId":91381,"journal":{"name":"Proceedings of COLING. International Conference on Computational Linguistics","volume":"16 1","pages":"1636-1644"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87358456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension 会话式机器阅读理解的一种新颖的端到端框架
Proceedings of COLING. International Conference on Computational Linguistics Pub Date : 2022-09-23 DOI: 10.48550/arXiv.2209.11484
Xiao Zhang, Heyan Huang, Zewen Chi, Xian-Ling Mao
{"title":"ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension","authors":"Xiao Zhang, Heyan Huang, Zewen Chi, Xian-Ling Mao","doi":"10.48550/arXiv.2209.11484","DOIUrl":"https://doi.org/10.48550/arXiv.2209.11484","url":null,"abstract":"Conversational machine reading comprehension (CMRC) aims to assist computers to understand an natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text. Existing methods typically require three steps: (1) decision making based on entailment reasoning; (2) span extraction if required by the above decision; (3) question rephrasing based on the extracted span. However, for nearly all these methods, the span extraction and question rephrasing steps cannot fully exploit the fine-grained entailment reasoning information in decision making step because of their relative independence, which will further enlarge the information gap between decision making and question phrasing. Thus, to tackle this problem, we propose a novel end-to-end framework for conversational machine reading comprehension based on shared parameter mechanism, called entailment reasoning T5 (ET5). Despite the lightweight of our proposed framework, experimental results show that the proposed ET5 achieves new state-of-the-art results on the ShARC leaderboard with the BLEU-4 score of 55.2. Our model and code are publicly available.","PeriodicalId":91381,"journal":{"name":"Proceedings of COLING. International Conference on Computational Linguistics","volume":"95 1","pages":"570-579"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83703302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
MetaPrompting: Learning to Learn Better Prompts metaprompts:学习更好的提示
Proceedings of COLING. International Conference on Computational Linguistics Pub Date : 2022-09-23 DOI: 10.48550/arXiv.2209.11486
Yutai Hou, Hongyuan Dong, Xinghao Wang, Bohan Li, Wanxiang Che
{"title":"MetaPrompting: Learning to Learn Better Prompts","authors":"Yutai Hou, Hongyuan Dong, Xinghao Wang, Bohan Li, Wanxiang Che","doi":"10.48550/arXiv.2209.11486","DOIUrl":"https://doi.org/10.48550/arXiv.2209.11486","url":null,"abstract":"Prompting method is regarded as one of the crucial progress for few-shot nature language processing. Recent research on prompting moves from discrete tokens based “hard prompts” to continuous “soft prompts”, which employ learnable vectors as pseudo prompt tokens and achieve better performance. Though showing promising prospects, these soft-prompting methods are observed to rely heavily on good initialization to take effect. Unfortunately, obtaining a perfect initialization for soft prompts requires understanding of inner language models working and elaborate design, which is no easy task and has to restart from scratch for each new task. To remedy this, we propose a generalized soft prompting method called MetaPrompting, which adopts the well-recognized model-agnostic meta-learning algorithm to automatically find better prompt initialization that facilitates fast adaptation to new prompting tasks. Extensive experiments show MetaPrompting tackles soft prompt initialization problem and brings significant improvement on three different datasets (over 6 points improvement in accuracy for 1-shot setting), achieving new state-of-the-art performance.","PeriodicalId":91381,"journal":{"name":"Proceedings of COLING. International Conference on Computational Linguistics","volume":"25 1","pages":"3251-3262"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81873666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 8
Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model 基于条件屏蔽语言模型的神经机器翻译语义一致性数据增强
Proceedings of COLING. International Conference on Computational Linguistics Pub Date : 2022-09-22 DOI: 10.48550/arXiv.2209.10875
Qiao Cheng, Jin Huang, Yitao Duan
{"title":"Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model","authors":"Qiao Cheng, Jin Huang, Yitao Duan","doi":"10.48550/arXiv.2209.10875","DOIUrl":"https://doi.org/10.48550/arXiv.2209.10875","url":null,"abstract":"This paper introduces a new data augmentation method for neural machine translation that can enforce stronger semantic consistency both within and across languages. Our method is based on Conditional Masked Language Model (CMLM) which is bi-directional and can be conditional on both left and right context, as well as the label. We demonstrate that CMLM is a good technique for generating context-dependent word distributions. In particular, we show that CMLM is capable of enforcing semantic consistency by conditioning on both source and target during substitution. In addition, to enhance diversity, we incorporate the idea of soft word substitution for data augmentation which replaces a word with a probabilistic distribution over the vocabulary. Experiments on four translation datasets of different scales show that the overall solution results in more realistic data augmentation and better translation quality. Our approach consistently achieves the best performance in comparison with strong and recent works and yields improvements of up to 1.90 BLEU points over the baseline.","PeriodicalId":91381,"journal":{"name":"Proceedings of COLING. International Conference on Computational Linguistics","volume":"56 1","pages":"5148-5157"},"PeriodicalIF":0.0,"publicationDate":"2022-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83582002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信