North American Chapter of the Association for Computational Linguistics最新文献_第9页

Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer 面向无监督文本风格转移的鲁棒和语义组织潜在表示

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-04 DOI: 10.48550/arXiv.2205.02309

Sharan Narasimhan, Suvodip Dey, M. Desarkar

{"title":"Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer","authors":"Sharan Narasimhan, Suvodip Dey, M. Desarkar","doi":"10.48550/arXiv.2205.02309","DOIUrl":"https://doi.org/10.48550/arXiv.2205.02309","url":null,"abstract":"Recent studies show that auto-encoder based approaches successfully perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner. The latent space geometry of such models is organised well enough to perform on datasets where the style is “coarse-grained” i.e. a small fraction of words alone in a sentence are enough to determine the overall style label. A recent study uses a discrete token-based perturbation approach to map “similar” sentences (“similar” defined by low Levenshtein distance/ high word overlap) close by in latent space. This definition of “similarity” does not look into the underlying nuances of the constituent words while mapping latent space neighbourhoods and therefore fails to recognise sentences with different style-based semantics while mapping latent neighbourhoods. We introduce EPAAEs (Embedding Perturbed Adversarial AutoEncoders) which completes this perturbation model, by adding a finely adjustable noise component on the continuous embeddings space. We empirically show that this (a) produces a better organised latent space that clusters stylistically similar sentences together, (b) performs best on a diverse set of text style transfer tasks than its counterparts, and (c) is capable of fine-grained control of Style Transfer strength. We also extend the text style transfer tasks to NLI datasets and show that these more complex definitions of style are learned best by EPAAE. To the best of our knowledge, extending style transfer to NLI tasks has not been explored before.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125430320","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

Aligning to Social Norms and Values in Interactive Narratives 与互动叙事中的社会规范和价值观保持一致

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-04 DOI: 10.48550/arXiv.2205.01975

Prithviraj Ammanabrolu, Liwei Jiang, Maarten Sap, Hannaneh Hajishirzi, Yejin Choi

{"title":"Aligning to Social Norms and Values in Interactive Narratives","authors":"Prithviraj Ammanabrolu, Liwei Jiang, Maarten Sap, Hannaneh Hajishirzi, Yejin Choi","doi":"10.48550/arXiv.2205.01975","DOIUrl":"https://doi.org/10.48550/arXiv.2205.01975","url":null,"abstract":"We focus on creating agents that act in alignment with socially beneficial norms and values in interactive narratives or text-based games—environments wherein an agent perceives and interacts with a world through natural language. Such interactive agents are often trained via reinforcement learning to optimize task performance, even when such rewards may lead to agent behaviors that violate societal norms—causing harm either to the agent itself or other entities in the environment. Social value alignment refers to creating agents whose behaviors conform to expected moral and social norms for a given context and group of people—in our case, it means agents that behave in a manner that is less harmful and more beneficial for themselves and others.We build on the Jiminy Cricket benchmark (Hendrycks et al. 2021), a set of 25 annotated interactive narratives containing thousands of morally salient scenarios covering everything from theft and bodily harm to altruism. We introduce the GALAD (Game-value ALignment through Action Distillation) agent that uses the social commonsense knowledge present in specially trained language models to contextually restrict its action space to only those actions that are aligned with socially beneficial values. An experimental study shows that the GALAD agent makes decisions efficiently enough to improve state-of-the-art task performance by 4% while reducing the frequency of socially harmful behaviors by 25% compared to strong contemporary value alignment approaches.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128291128","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: 22

Explaining Why: How Instructions and User Interfaces Impact Annotator Rationales When Labeling Text Data 解释原因:当标记文本数据时，说明和用户界面如何影响注释器的基本原理

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-04 DOI: 10.48550/arXiv.2205.02005

Ankan Mullick, Sukannya Purkayastha, Pawan Goyal, Niloy Ganguly

引用次数: 2

ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models ElitePLM:预训练语言模型通用语言能力评价的实证研究

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-03 DOI: 10.48550/arXiv.2205.01523

Junyi Li, Tianyi Tang, Zheng Gong, Lixin Yang, Zhuohao Yu, Z. Chen, Jingyuan Wang, Wayne Xin Zhao, Ji-rong Wen

{"title":"ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models","authors":"Junyi Li, Tianyi Tang, Zheng Gong, Lixin Yang, Zhuohao Yu, Z. Chen, Jingyuan Wang, Wayne Xin Zhao, Ji-rong Wen","doi":"10.48550/arXiv.2205.01523","DOIUrl":"https://doi.org/10.48550/arXiv.2205.01523","url":null,"abstract":"Nowadays, pretrained language models (PLMs) have dominated the majority of NLP tasks. While, little research has been conducted on systematically evaluating the language abilities of PLMs. In this paper, we present a large-scale empirical study on general language ability evaluation of PLMs (ElitePLM). In our study, we design four evaluation dimensions, memory, comprehension, reasoning, and composition, to measure ten widely-used PLMs within five categories. Our empirical results demonstrate that: (1) PLMs with varying training objectives and strategies are good at different ability tests; (2) fine-tuning PLMs in downstream tasks is usually sensitive to the data size and distribution; (3) PLMs have excellent transferability between similar tasks. Moreover, the prediction results of PLMs in our experiments are released as an open resource for more deep and detailed analysis on the language abilities of PLMs. This paper can guide the future work to select, apply, and design PLMs for specific tasks. We have made all the details of experiments publicly available at https://github.com/RUCAIBox/ElitePLM.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"2020 18","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120971281","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

Neural Language Taskonomy: Which NLP Tasks are the most Predictive of fMRI Brain Activity? 神经语言任务:哪些NLP任务最能预测fMRI脑活动?

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-03 DOI: 10.18653/v1/2022.naacl-main.235

S. Oota, Jashn Arora, Veeral Agarwal, Mounika Marreddy, Manish Gupta, Raju Surampudi Bapi

{"title":"Neural Language Taskonomy: Which NLP Tasks are the most Predictive of fMRI Brain Activity?","authors":"S. Oota, Jashn Arora, Veeral Agarwal, Mounika Marreddy, Manish Gupta, Raju Surampudi Bapi","doi":"10.18653/v1/2022.naacl-main.235","DOIUrl":"https://doi.org/10.18653/v1/2022.naacl-main.235","url":null,"abstract":"Several popular Transformer based language models have been found to be successful for text-driven brain encoding. However, existing literature leverages only pretrained text Transformer models and has not explored the efficacy of task-specific learned Transformer representations. In this work, we explore transfer learning from representations learned for ten popular natural language processing tasks (two syntactic and eight semantic) for predicting brain responses from two diverse datasets: Pereira (subjects reading sentences from paragraphs) and Narratives (subjects listening to the spoken stories). Encoding models based on task features are used to predict activity in different regions across the whole brain. Features from coreference resolution, NER, and shallow syntax parsing explain greater variance for the reading activity. On the other hand, for the listening activity, tasks such as paraphrase generation, summarization, and natural language inference show better encoding performance. Experiments across all 10 task representations provide the following cognitive insights: (i) language left hemisphere has higher predictive brain activity versus language right hemisphere, (ii) posterior medial cortex, temporo-parieto-occipital junction, dorsal frontal lobe have higher correlation versus early auditory and auditory association cortex, (iii) syntactic and semantic tasks display a good predictive performance across brain regions for reading and listening stimuli resp.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123464253","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: 21

Learning to Transfer Prompts for Text Generation 学习转移文本生成提示

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-03 DOI: 10.48550/arXiv.2205.01543

Junyi Li, Tianyi Tang, J. Nie, Ji-rong Wen, Wayne Xin Zhao

{"title":"Learning to Transfer Prompts for Text Generation","authors":"Junyi Li, Tianyi Tang, J. Nie, Ji-rong Wen, Wayne Xin Zhao","doi":"10.48550/arXiv.2205.01543","DOIUrl":"https://doi.org/10.48550/arXiv.2205.01543","url":null,"abstract":"Pretrained language models (PLMs) have made remarkable progress in text generation tasks via fine-tuning. While, it is challenging to fine-tune PLMs in a data-scarce situation. Therefore, it is non-trivial to develop a general and lightweight model that can adapt to various text generation tasks based on PLMs. To fulfill this purpose, the recent prompt-based learning offers a potential solution. In this paper, we improve this technique and propose a novel prompt-based method (PTG) for text generation in a transferable setting. First, PTG learns a set of source prompts for various source generation tasks and then transfers these prompts as target prompts to perform target generation tasks. To consider both task- and instance-level information, we design an adaptive attention mechanism to derive the target prompts. For each data instance, PTG learns a specific target prompt by attending to highly relevant source prompts. In extensive experiments, PTG yields competitive or better results than fine-tuning methods. We release our source prompts as an open resource, where users can add or reuse them to improve new text generation tasks for future research. Code and data can be available at https://github.com/RUCAIBox/Transfer-Prompts-for-Text-Generation.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115621197","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: 18

Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Features 具有话语层面规划与美学特征的零射十四行诗生成

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-03 DOI: 10.48550/arXiv.2205.01821

Yufei Tian, Nanyun Peng

引用次数: 14

Exact Paired-Permutation Testing for Structured Test Statistics 结构化检验统计的精确配对置换检验

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-03 DOI: 10.48550/arXiv.2205.01416

Ran Zmigrod, Tim Vieira, Ryan Cotterell

引用次数: 1

Meta Learning for Natural Language Processing: A Survey 自然语言处理中的元学习:综述

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-03 DOI: 10.48550/arXiv.2205.01500

Hung-yi Lee, Shang-Wen Li, Ngoc Thang Vu

引用次数: 25

Don’t sweat the small stuff, classify the rest: Sample Shielding to protect text classifiers against adversarial attacks 不要为小事而烦恼，对其余部分进行分类:样本屏蔽，以保护文本分类器免受对抗性攻击

North American Chapter of the Association for Computational Linguistics Pub Date : 2022-05-03 DOI: 10.48550/arXiv.2205.01714

Jonathan Rusert, P. Srinivasan

{"title":"Don’t sweat the small stuff, classify the rest: Sample Shielding to protect text classifiers against adversarial attacks","authors":"Jonathan Rusert, P. Srinivasan","doi":"10.48550/arXiv.2205.01714","DOIUrl":"https://doi.org/10.48550/arXiv.2205.01714","url":null,"abstract":"Deep learning (DL) is being used extensively for text classification. However, researchers have demonstrated the vulnerability of such classifiers to adversarial attacks. Attackers modify the text in a way which misleads the classifier while keeping the original meaning close to intact. State-of-the-art (SOTA) attack algorithms follow the general principle of making minimal changes to the text so as to not jeopardize semantics. Taking advantage of this we propose a novel and intuitive defense strategy called Sample Shielding.It is attacker and classifier agnostic, does not require any reconfiguration of the classifier or external resources and is simple to implement. Essentially, we sample subsets of the input text, classify them and summarize these into a final decision. We shield three popular DL text classifiers with Sample Shielding, test their resilience against four SOTA attackers across three datasets in a realistic threat setting. Even when given the advantage of knowing about our shielding strategy the adversary’s attack success rate is <=10% with only one exception and often < 5%. Additionally, Sample Shielding maintains near original accuracy when applied to original texts. Crucially, we show that the ‘make minimal changes’ approach of SOTA attackers leads to critical vulnerabilities that can be defended against with an intuitive sampling strategy.","PeriodicalId":382084,"journal":{"name":"North American Chapter of the Association for Computational Linguistics","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127786923","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