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

When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants 什么时候使用有效的自我关注?剖析文本，语音和图像转换器变体

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-14 DOI: 10.48550/arXiv.2306.08667

Anuj Diwan, Eunsol Choi, David F. Harwath

引用次数: 0

ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer ChatGPT与人类撰写的文本:对可控文本摘要和句子风格转换的见解

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-13 DOI: 10.48550/arXiv.2306.07799

Dongqi Pu, Vera Demberg

引用次数: 16

Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph Reasoning 思辨知识图推理的带自训练的噪声正无标签学习

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-13 DOI: 10.48550/arXiv.2306.07512

Ruijie Wang, Baoyu Li, Yichen Lu, Dachun Sun, Jinning Li, Yuchen Yan, Shengzhong Liu, H. Tong, T. Abdelzaher

{"title":"Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph Reasoning","authors":"Ruijie Wang, Baoyu Li, Yichen Lu, Dachun Sun, Jinning Li, Yuchen Yan, Shengzhong Liu, H. Tong, T. Abdelzaher","doi":"10.48550/arXiv.2306.07512","DOIUrl":"https://doi.org/10.48550/arXiv.2306.07512","url":null,"abstract":"This paper studies speculative reasoning task on real-world knowledge graphs (KG) that contain both textit{false negative issue} (i.e., potential true facts being excluded) and textit{false positive issue} (i.e., unreliable or outdated facts being included). State-of-the-art methods fall short in the speculative reasoning ability, as they assume the correctness of a fact is solely determined by its presence in KG, making them vulnerable to false negative/positive issues. The new reasoning task is formulated as a noisy Positive-Unlabeled learning problem. We propose a variational framework, namely nPUGraph, that jointly estimates the correctness of both collected and uncollected facts (which we call textit{label posterior}) and updates model parameters during training. The label posterior estimation facilitates speculative reasoning from two perspectives. First, it improves the robustness of a label posterior-aware graph encoder against false positive links. Second, it identifies missing facts to provide high-quality grounds of reasoning. They are unified in a simple yet effective self-training procedure. Empirically, extensive experiments on three benchmark KG and one Twitter dataset with various degrees of false negative/positive cases demonstrate the effectiveness of nPUGraph.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131587709","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

Linear Classifier: An Often-Forgotten Baseline for Text Classification 线性分类器:一个经常被遗忘的文本分类基线

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-12 DOI: 10.48550/arXiv.2306.07111

Yu-Chen Lin, Si-An Chen, Jie-Jyun Liu, Chih-Jen Lin

引用次数: 1

Recurrent Attention Networks for Long-text Modeling 用于长文本建模的循环注意网络

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-12 DOI: 10.48550/arXiv.2306.06843

Xianming Li, Zongxi Li, Xiaotian Luo, Haoran Xie, Xing Lee, Yingbin Zhao, Fu Lee Wang, Qing Li

{"title":"Recurrent Attention Networks for Long-text Modeling","authors":"Xianming Li, Zongxi Li, Xiaotian Luo, Haoran Xie, Xing Lee, Yingbin Zhao, Fu Lee Wang, Qing Li","doi":"10.48550/arXiv.2306.06843","DOIUrl":"https://doi.org/10.48550/arXiv.2306.06843","url":null,"abstract":"Self-attention-based models have achieved remarkable progress in short-text mining. However, the quadratic computational complexities restrict their application in long text processing. Prior works have adopted the chunking strategy to divide long documents into chunks and stack a self-attention backbone with the recurrent structure to extract semantic representation. Such an approach disables parallelization of the attention mechanism, significantly increasing the training cost and raising hardware requirements. Revisiting the self-attention mechanism and the recurrent structure, this paper proposes a novel long-document encoding model, Recurrent Attention Network (RAN), to enable the recurrent operation of self-attention. Combining the advantages from both sides, the well-designed RAN is capable of extracting global semantics in both token-level and document-level representations, making it inherently compatible with both sequential and classification tasks, respectively. Furthermore, RAN is computationally scalable as it supports parallelization on long document processing. Extensive experiments demonstrate the long-text encoding ability of the proposed RAN model on both classification and sequential tasks, showing its potential for a wide range of applications.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127372018","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: 4

History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling 基于时态信息建模的历史语义图增强会话KBQA

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-12 DOI: 10.48550/arXiv.2306.06872

Hao-Lun Sun, Y. Li, Li Deng, Bowen Li, Binyuan Hui, Binhua Li, Yunshi Lan, Yan Zhang, Yongbin Li

引用次数: 0

Gradient Ascent Post-training Enhances Language Model Generalization 梯度上升训练后增强语言模型泛化

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-12 DOI: 10.48550/arXiv.2306.07052

Dongkeun Yoon, Joel Jang, Sungdong Kim, Minjoon Seo

引用次数: 1

The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation 细节决定成败:论事件抽取评估的陷阱

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-12 DOI: 10.48550/arXiv.2306.06918

Hao Peng, Xiaozhi Wang, Feng Yao, Kaisheng Zeng, Lei Hou, Juanzi Li, Zhiyuan Liu, Weixing Shen

{"title":"The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation","authors":"Hao Peng, Xiaozhi Wang, Feng Yao, Kaisheng Zeng, Lei Hou, Juanzi Li, Zhiyuan Liu, Weixing Shen","doi":"10.48550/arXiv.2306.06918","DOIUrl":"https://doi.org/10.48550/arXiv.2306.06918","url":null,"abstract":"Event extraction (EE) is a crucial task aiming at extracting events from texts, which includes two subtasks: event detection (ED) and event argument extraction (EAE). In this paper, we check the reliability of EE evaluations and identify three major pitfalls: (1) The data preprocessing discrepancy makes the evaluation results on the same dataset not directly comparable, but the data preprocessing details are not widely noted and specified in papers. (2) The output space discrepancy of different model paradigms makes different-paradigm EE models lack grounds for comparison and also leads to unclear mapping issues between predictions and annotations. (3) The absence of pipeline evaluation of many EAE-only works makes them hard to be directly compared with EE works and may not well reflect the model performance in real-world pipeline scenarios. We demonstrate the significant influence of these pitfalls through comprehensive meta-analyses of recent papers and empirical experiments. To avoid these pitfalls, we suggest a series of remedies, including specifying data preprocessing, standardizing outputs, and providing pipeline evaluation results. To help implement these remedies, we develop a consistent evaluation framework OMNIEVENT, which can be obtained from https://github.com/THU-KEG/OmniEvent.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125640424","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

Language of Bargaining 议价语言

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-12 DOI: 10.2139/ssrn.4436666

Mourad Heddaya, Solomon Dworkin, Chenhao Tan, Rob Voigt, Alexander Zentefis

引用次数: 0

Estimating the Uncertainty in Emotion Attributes using Deep Evidential Regression 用深度证据回归估计情绪属性的不确定性

Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-11 DOI: 10.48550/arXiv.2306.06760

Wen Wu, C. Zhang, P. Woodland

引用次数: 1