Annual Meeting of the Association for Computational Linguistics最新文献_第8页

FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction FSUIE:一种新的通用信息抽取模糊跨度机制

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-19 DOI: 10.48550/arXiv.2306.14913

Tianshuo Peng, Z. Li, Lefei Zhang, Bo Du, Hai Zhao

引用次数: 0

Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction 基于前缀调谐的双门融合多模态关系提取

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-19 DOI: 10.48550/arXiv.2306.11020

Qian Li, Shu Guo, Cheng Ji, Xutan Peng, Shiyao Cui, Jianxin Li

{"title":"Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction","authors":"Qian Li, Shu Guo, Cheng Ji, Xutan Peng, Shiyao Cui, Jianxin Li","doi":"10.48550/arXiv.2306.11020","DOIUrl":"https://doi.org/10.48550/arXiv.2306.11020","url":null,"abstract":"Multi-Modal Relation Extraction (MMRE) aims at identifying the relation between two entities in texts that contain visual clues. Rich visual content is valuable for the MMRE task, but existing works cannot well model finer associations among different modalities, failing to capture the truly helpful visual information and thus limiting relation extraction performance. In this paper, we propose a novel MMRE framework to better capture the deeper correlations of text, entity pair, and image/objects, so as to mine more helpful information for the task, termed as DGF-PT. We first propose a prompt-based autoregressive encoder, which builds the associations of intra-modal and inter-modal features related to the task, respectively by entity-oriented and object-oriented prefixes. To better integrate helpful visual information, we design a dual-gated fusion module to distinguish the importance of image/objects and further enrich text representations. In addition, a generative decoder is introduced with entity type restriction on relations, better filtering out candidates. Extensive experiments conducted on the benchmark dataset show that our approach achieves excellent performance compared to strong competitors, even in the few-shot situation.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"26 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132835643","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: 3

"You might think about slightly revising the title”: Identifying Hedges in Peer-tutoring Interactions “你可能会考虑稍微修改一下标题”:在同伴辅导互动中识别对冲

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-18 DOI: 10.18653/v1/2022.acl-long.153

Yann Raphalen, C. Clavel, Justine Cassell

引用次数: 9

MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition MIR-GAN:使用对抗网络改进帧级模态不变表示用于视听语音识别

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-18 DOI: 10.48550/arXiv.2306.10567

Yuchen Hu, Chen Chen, Ruizhe Li, Heqing Zou, Chng Eng Siong

{"title":"MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition","authors":"Yuchen Hu, Chen Chen, Ruizhe Li, Heqing Zou, Chng Eng Siong","doi":"10.48550/arXiv.2306.10567","DOIUrl":"https://doi.org/10.48550/arXiv.2306.10567","url":null,"abstract":"Audio-visual speech recognition (AVSR) attracts a surge of research interest recently by leveraging multimodal signals to understand human speech. Mainstream approaches addressing this task have developed sophisticated architectures and techniques for multi-modality fusion and representation learning. However, the natural heterogeneity of different modalities causes distribution gap between their representations, making it challenging to fuse them. In this paper, we aim to learn the shared representations across modalities to bridge their gap. Different from existing similar methods on other multimodal tasks like sentiment analysis, we focus on the temporal contextual dependencies considering the sequence-to-sequence task setting of AVSR. In particular, we propose an adversarial network to refine frame-level modality-invariant representations (MIR-GAN), which captures the commonality across modalities to ease the subsequent multimodal fusion process. Extensive experiments on public benchmarks LRS3 and LRS2 show that our approach outperforms the state-of-the-arts.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124455413","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

Typo-Robust Representation Learning for Dense Retrieval 面向密集检索的打字鲁棒表示学习

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-17 DOI: 10.48550/arXiv.2306.10348

Panuthep Tasawong, Wuttikorn Ponwitayarat, Peerat Limkonchotiwat, Can Udomcharoenchaikit, E. Chuangsuwanich, Sarana Nutanong

引用次数: 0

Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation 从看见到看不见:探索多属性可控对话生成的组合泛化

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-17 DOI: 10.48550/arXiv.2306.10317

Weihao Zeng, Lulu Zhao, Keqing He, Ruotong Geng, Jingang Wang, Wei Wu, Weiran Xu

引用次数: 0

FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue FutureTOD:将未来知识传授给任务导向对话的预训练语言模型

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-17 DOI: 10.48550/arXiv.2306.10315

Weihao Zeng, Keqing He, Yejie Wang, Chen Zeng, Jingang Wang, Yunsen Xian, Weiran Xu

引用次数: 1

REDFM: a Filtered and Multilingual Relation Extraction Dataset REDFM:一个过滤的多语言关系提取数据集

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-16 DOI: 10.48550/arXiv.2306.09802

Pere-Llu'is Huguet Cabot, Simone Tedeschi, A. N. Ngomo, Roberto Navigli

{"title":"REDFM: a Filtered and Multilingual Relation Extraction Dataset","authors":"Pere-Llu'is Huguet Cabot, Simone Tedeschi, A. N. Ngomo, Roberto Navigli","doi":"10.48550/arXiv.2306.09802","DOIUrl":"https://doi.org/10.48550/arXiv.2306.09802","url":null,"abstract":"Relation Extraction (RE) is a task that identifies relationships between entities in a text, enabling the acquisition of relational facts and bridging the gap between natural language and structured knowledge. However, current RE models often rely on small datasets with low coverage of relation types, particularly when working with languages other than English.In this paper, we address the above issue and provide two new resources that enable the training and evaluation of multilingual RE systems.First, we present SREDFM, an automatically annotated dataset covering 18 languages, 400 relation types, 13 entity types, totaling more than 40 million triplet instances. Second, we propose REDFM, a smaller, human-revised dataset for seven languages that allows for the evaluation of multilingual RE systems. To demonstrate the utility of these novel datasets, we experiment with the first end-to-end multilingual RE model, mREBEL, that extracts triplets, including entity types, in multiple languages. We release our resources and model checkpoints at [https://www.github.com/babelscape/rebel](https://www.github.com/babelscape/rebel).","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"172 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116004136","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

Reproducibility in NLP: What Have We Learned from the Checklist? NLP中的再现性:我们从清单中学到了什么?

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-16 DOI: 10.48550/arXiv.2306.09562

Ian H. Magnusson, Noah A. Smith, Jesse Dodge

{"title":"Reproducibility in NLP: What Have We Learned from the Checklist?","authors":"Ian H. Magnusson, Noah A. Smith, Jesse Dodge","doi":"10.48550/arXiv.2306.09562","DOIUrl":"https://doi.org/10.48550/arXiv.2306.09562","url":null,"abstract":"Scientific progress in NLP rests on the reproducibility of researchers' claims. The *CL conferences created the NLP Reproducibility Checklist in 2020 to be completed by authors at submission to remind them of key information to include. We provide the first analysis of the Checklist by examining 10,405 anonymous responses to it. First, we find evidence of an increase in reporting of information on efficiency, validation performance, summary statistics, and hyperparameters after the Checklist's introduction. Further, we show acceptance rate grows for submissions with more Yes responses. We find that the 44% of submissions that gather new data are 5% less likely to be accepted than those that did not; the average reviewer-rated reproducibility of these submissions is also 2% lower relative to the rest. We find that only 46% of submissions claim to open-source their code, though submissions that do have 8% higher reproducibility score relative to those that do not, the most for any item. We discuss what can be inferred about the state of reproducibility in NLP, and provide a set of recommendations for future conferences, including: a) allowing submitting code and appendices one week after the deadline, and b) measuring dataset reproducibility by a checklist of data collection practices.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129184332","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

How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese 在连续脚本语言中，不同的标记器如何执行下游任务?:日语案例研究

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-16 DOI: 10.48550/arXiv.2306.09572

T. Fujii, Koki Shibata, Atsuki Yamaguchi, Terufumi Morishita, Yasuhiro Sogawa

引用次数: 0