North American Chapter of the Association for Computational Linguistics最新文献_第7页

A Data Cartography based MixUp for Pre-trained Language Models 基于数据制图的预训练语言模型混合

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-06 DOI: 10.48550/arXiv.2205.03403

Seohong Park, Cornelia Caragea

引用次数: 4

Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection 解释文本分类器的必要性与充分性:以仇恨言语检测为例

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-06 DOI: 10.48550/arXiv.2205.03302

Esma Balkir, I. Nejadgholi, Kathleen C. Fraser, S. Kiritchenko

引用次数: 14

Combining Humor and Sarcasm for Improving Political Parody Detection 幽默与讽刺相结合提高政治戏仿检测

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-06 DOI: 10.48550/arXiv.2205.03313

Xiao Ao, Danae Sánchez Villegas, Daniel Preoctiuc-Pietro, Nikolaos Aletras

引用次数: 2

Federated Learning with Noisy User Feedback 基于噪声用户反馈的联邦学习

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-06 DOI: 10.48550/arXiv.2205.03092

Rahul Sharma, Anil Ramakrishna, Ansel MacLaughlin, Anna Rumshisky, Jimit Majmudar, Clement Chung, S. Avestimehr, Rahul Gupta

{"title":"Federated Learning with Noisy User Feedback","authors":"Rahul Sharma, Anil Ramakrishna, Ansel MacLaughlin, Anna Rumshisky, Jimit Majmudar, Clement Chung, S. Avestimehr, Rahul Gupta","doi":"10.48550/arXiv.2205.03092","DOIUrl":"https://doi.org/10.48550/arXiv.2205.03092","url":null,"abstract":"Machine Learning (ML) systems are getting increasingly popular, and drive more and more applications and services in our daily life. Thishas led to growing concerns over user privacy, since human interaction data typically needs to be transmitted to the cloud in order to trainand improve such systems. Federated learning (FL) has recently emerged as a method for training ML models on edge devices using sensitive user data and is seen as a way to mitigate concerns over data privacy. However, since ML models are most commonly trained with label supervision, we need a way to extract labels on edge to make FL viable. In this work, we propose a strategy for training FL models using positive and negative user feedback. We also design a novel framework to study different noise patterns in user feedback, and explore how well standard noise-robust objectives can help mitigate this noise when training models in a federated setting. We evaluate our proposed training setup through detailed experiments on two text classification datasets and analyze the effects of varying levels of user reliability and feedback noise on model performance. We show that our method improves substantially over a self-training baseline, achieving performance closer to models trained with full supervision.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124351652","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

Collective Relevance Labeling for Passage Retrieval 文章检索的集体关联标注

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-06 DOI: 10.48550/arXiv.2205.03273

Jihyuk Kim, Minsoo Kim, Seung-won Hwang

引用次数: 6

Robust Conversational Agents against Imperceptible Toxicity Triggers 针对难以察觉的毒性触发的健壮会话代理

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-05 DOI: 10.48550/arXiv.2205.02392

Ninareh Mehrabi, Ahmad Beirami, Fred Morstatter, A. Galstyan

{"title":"Robust Conversational Agents against Imperceptible Toxicity Triggers","authors":"Ninareh Mehrabi, Ahmad Beirami, Fred Morstatter, A. Galstyan","doi":"10.48550/arXiv.2205.02392","DOIUrl":"https://doi.org/10.48550/arXiv.2205.02392","url":null,"abstract":"Warning: this paper contains content that maybe offensive or upsetting.Recent research in Natural Language Processing (NLP) has advanced the development of various toxicity detection models with the intention of identifying and mitigating toxic language from existing systems. Despite the abundance of research in this area, less attention has been given to adversarial attacks that force the system to generate toxic language and the defense against them. Existing work to generate such attacks is either based on human-generated attacks which is costly and not scalable or, in case of automatic attacks, the attack vector does not conform to human-like language, which can be detected using a language model loss. In this work, we propose attacks against conversational agents that are imperceptible, i.e., they fit the conversation in terms of coherency, relevancy, and fluency, while they are effective and scalable, i.e., they can automatically trigger the system into generating toxic language. We then propose a defense mechanism against such attacks which not only mitigates the attack but also attempts to maintain the conversational flow. Through automatic and human evaluations, we show that our defense is effective at avoiding toxic language generation even against imperceptible toxicity triggers while the generated language fits the conversation in terms of coherency and relevancy. Lastly, we establish the generalizability of such a defense mechanism on language generation models beyond conversational agents.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124339958","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: 12

CompactIE: Compact Facts in Open Information Extraction CompactIE:开放信息提取中的紧凑事实

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-05 DOI: 10.48550/arXiv.2205.02880

Farimah Bayat, Nikita Bhutani, H. Jagadish

引用次数: 7

Optimising Equal Opportunity Fairness in Model Training 优化模型训练中的机会均等公平性

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-05 DOI: 10.48550/arXiv.2205.02393

Aili Shen, Xudong Han, Trevor Cohn, Timothy Baldwin, Lea Frermann

引用次数: 18

Natural Language Inference with Self-Attention for Veracity Assessment of Pandemic Claims 基于自关注的自然语言推断用于流行病索赔的真实性评估

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-05 DOI: 10.48550/arXiv.2205.02596

M. Arana-Catania, E. Kochkina, A. Zubiaga, M. Liakata, R. Procter, Yulan He

引用次数: 5

Implicit n-grams Induced by Recurrence 由递归引起的隐式n图

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-05 DOI: 10.48550/arXiv.2205.02724

Xiaobing Sun, Wei Lu

{"title":"Implicit n-grams Induced by Recurrence","authors":"Xiaobing Sun, Wei Lu","doi":"10.48550/arXiv.2205.02724","DOIUrl":"https://doi.org/10.48550/arXiv.2205.02724","url":null,"abstract":"Although self-attention based models such as Transformers have achieved remarkable successes on natural language processing (NLP)tasks, recent studies reveal that they have limitations on modeling sequential transformations (Hahn, 2020), which may promptre-examinations of recurrent neural networks (RNNs) that demonstrated impressive results on handling sequential data. Despite manyprior attempts to interpret RNNs, their internal mechanisms have not been fully understood, and the question on how exactly they capturesequential features remains largely unclear. In this work, we present a study that shows there actually exist some explainable componentsthat reside within the hidden states, which are reminiscent of the classical n-grams features. We evaluated such extracted explainable features from trained RNNs on downstream sentiment analysis tasks and found they could be used to model interesting linguistic phenomena such as negation and intensification. Furthermore, we examined the efficacy of using such n-gram components alone as encoders on tasks such as sentiment analysis and language modeling, revealing they could be playing important roles in contributing to the overall performance of RNNs. We hope our findings could add interpretability to RNN architectures, and also provide inspirations for proposing new architectures for sequential data.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131365176","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