发布求助
文献互助 智能选刊 最新文献

Annual Meeting of the Association for Computational Linguistics最新文献

筛选
英文 中文
Chain of Thought Prompting Elicits Knowledge Augmentation 思维链提示引出知识扩充
Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-04 DOI: 10.48550/arXiv.2307.01640
Di Wu, Jing Zhang, Xinmei Huang
{"title":"Chain of Thought Prompting Elicits Knowledge Augmentation","authors":"Di Wu, Jing Zhang, Xinmei Huang","doi":"10.48550/arXiv.2307.01640","DOIUrl":"https://doi.org/10.48550/arXiv.2307.01640","url":null,"abstract":"The knowledge-augmented deep learning paradigm refers to a paradigm in which domain knowledge is identified and integrated into deep models. Conventional methods typically employ task-specific approaches to gather external knowledge from various sources. In contrast, large language models are extensively pre-trained and can serve as a comprehensive source of external knowledge. In this paper, we propose CoT-KA, a Chain-of-Thought-based method that augments knowledge for deep learning. CoT-KA avoids the need for additional knowledge retrieval or knowledge reasoning models, as required in conventional augmentation methods. Our results demonstrate that CoT-KA outperforms both pure CoT-based methods and the non-augmented method across the majority of eleven publicly available benchmarks for various reasoning tasks.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115888061","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
Mitigating the Learning Bias towards Repetition by Self-Contrastive Training for Open-Ended Generation 通过自我对比训练减轻开放式世代的重复学习偏见
Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-04 DOI: 10.48550/arXiv.2307.01542
Jian Guan, Minlie Huang
{"title":"Mitigating the Learning Bias towards Repetition by Self-Contrastive Training for Open-Ended Generation","authors":"Jian Guan, Minlie Huang","doi":"10.48550/arXiv.2307.01542","DOIUrl":"https://doi.org/10.48550/arXiv.2307.01542","url":null,"abstract":"Despite the huge progress in myriad generation tasks, pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts with maximization-based decoding algorithms for open-ended generation. We attribute their overestimation of token-level repetition probabilities to the learning bias: LMs capture simple repetitive patterns faster with the MLE loss. We propose self-contrastive training to penalize the output of a premature checkpoint of the same model when it incorrectly predicts repetition, which is shown to mitigate repetition effectively while maintaining fluency on two datasets. Furthermore, we find that LMs use longer-range dependencies to predict repetitive tokens than non-repetitive ones, which may be the cause of sentence-level repetition loops.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131669118","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: 0
Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking 对话状态跟踪的多元检索增强语境学习
Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-04 DOI: 10.48550/arXiv.2307.01453
Brendan King, Jeffrey Flanigan
{"title":"Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking","authors":"Brendan King, Jeffrey Flanigan","doi":"10.48550/arXiv.2307.01453","DOIUrl":"https://doi.org/10.48550/arXiv.2307.01453","url":null,"abstract":"There has been significant interest in zero and few-shot learning for dialogue state tracking (DST) due to the high cost of collecting and annotating task-oriented dialogues. Recent work has demonstrated that in-context learning requires very little data and zero parameter updates, and even outperforms trained methods in the few-shot setting (Hu et al. 2022). We propose RefPyDST, which advances the state of the art with three advancements to in-context learning for DST. First, we formulate DST as a Python programming task, explicitly modeling language coreference as variable reference in Python. Second, since in-context learning depends highly on the context examples, we propose a method to retrieve a diverse set of relevant examples to improve performance. Finally, we introduce a novel re-weighting method during decoding that takes into account probabilities of competing surface forms, and produces a more accurate dialogue state prediction. We evaluate our approach using MultiWOZ and achieve state-of-the-art multi-domain joint-goal accuracy in zero and few-shot settings.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127528015","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: 0
Transformed Protoform Reconstruction 变形原形重建
Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-04 DOI: 10.48550/arXiv.2307.01896
Young Min Kim, Kalvin Chang, Chenxuan Cui, David R. Mortensen
{"title":"Transformed Protoform Reconstruction","authors":"Young Min Kim, Kalvin Chang, Chenxuan Cui, David R. Mortensen","doi":"10.48550/arXiv.2307.01896","DOIUrl":"https://doi.org/10.48550/arXiv.2307.01896","url":null,"abstract":"Protoform reconstruction is the task of inferring what morphemes or words appeared like in the ancestral languages of a set of daughter languages. Meloni et al (2021) achieved the state-of-the-art on Latin protoform reconstruction with an RNN-based encoder-decoder with attention model. We update their model with the state-of-the-art seq2seq model: the Transformer. Our model outperforms their model on a suite of different metrics on two different datasets: their Romance data of 8,000 cognates spanning 5 languages and a Chinese dataset (Hou 2004) of 800+ cognates spanning 39 varieties. We also probe our model for potential phylogenetic signal contained in the model. Our code is publicly available at https://github.com/cmu-llab/acl-2023.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130941961","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
UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding UniFine:零镜头视觉语言理解的统一和细粒度方法
Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-03 DOI: 10.48550/arXiv.2307.00862
Rui Sun, Zhecan Wang, Haoxuan You, N. Codella, Kai-Wei Chang, Shih-Fu Chang
{"title":"UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding","authors":"Rui Sun, Zhecan Wang, Haoxuan You, N. Codella, Kai-Wei Chang, Shih-Fu Chang","doi":"10.48550/arXiv.2307.00862","DOIUrl":"https://doi.org/10.48550/arXiv.2307.00862","url":null,"abstract":"Vision-language tasks, such as VQA, SNLI-VE, and VCR are challenging because they require the model's reasoning ability to understand the semantics of the visual world and natural language. Supervised methods working for vision-language tasks have been well-studied. However, solving these tasks in a zero-shot setting is less explored. Since Contrastive Language-Image Pre-training (CLIP) has shown remarkable zero-shot performance on image-text matching, previous works utilized its strong zero-shot ability by converting vision-language tasks into an image-text matching problem, and they mainly consider global-level matching (e.g., the whole image or sentence). However, we find visual and textual fine-grained information, e.g., keywords in the sentence and objects in the image, can be fairly informative for semantics understanding. Inspired by this, we propose a unified framework to take advantage of the fine-grained information for zero-shot vision-language learning, covering multiple tasks such as VQA, SNLI-VE, and VCR. Our experiments show that our framework outperforms former zero-shot methods on VQA and achieves substantial improvement on SNLI-VE and VCR. Furthermore, our ablation studies confirm the effectiveness and generalizability of our proposed method. Code will be available at https://github.com/ThreeSR/UniFine","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115962291","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: 0
SSP: Self-Supervised Post-training for Conversational Search SSP:会话搜索的自我监督后训练
Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-02 DOI: 10.48550/arXiv.2307.00569
Quan Tu, Shen Gao, Xiaolong Wu, Zhao Cao, Jiaxin Wen, Rui Yan
{"title":"SSP: Self-Supervised Post-training for Conversational Search","authors":"Quan Tu, Shen Gao, Xiaolong Wu, Zhao Cao, Jiaxin Wen, Rui Yan","doi":"10.48550/arXiv.2307.00569","DOIUrl":"https://doi.org/10.48550/arXiv.2307.00569","url":null,"abstract":"Conversational search has been regarded as the next-generation search paradigm. Constrained by data scarcity, most existing methods distill the well-trained ad-hoc retriever to the conversational retriever. However, these methods, which usually initialize parameters by query reformulation to discover contextualized dependency, have trouble in understanding the dialogue structure information and struggle with contextual semantic vanishing. In this paper, we propose fullmodel (model) which is a new post-training paradigm with three self-supervised tasks to efficiently initialize the conversational search model to enhance the dialogue structure and contextual semantic understanding. Furthermore, the model can be plugged into most of the existing conversational models to boost their performance. To verify the effectiveness of our proposed method, we apply the conversational encoder post-trained by model on the conversational search task using two benchmark datasets: CAsT-19 and CAsT-20. Extensive experiments that our model can boost the performance of several existing conversational search methods. Our source code is available at url{https://github.com/morecry/SSP}.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"62 44","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120971702","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: 0
Revisiting Sample Size Determination in Natural Language Understanding 自然语言理解中样本大小的确定
Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-07-01 DOI: 10.48550/arXiv.2307.00374
Ernie Chang, Muhammad Hassan Rashid, Pin-Jie Lin, Changsheng Zhao, Vera Demberg, Yangyang Shi, Vikas Chandra
{"title":"Revisiting Sample Size Determination in Natural Language Understanding","authors":"Ernie Chang, Muhammad Hassan Rashid, Pin-Jie Lin, Changsheng Zhao, Vera Demberg, Yangyang Shi, Vikas Chandra","doi":"10.48550/arXiv.2307.00374","DOIUrl":"https://doi.org/10.48550/arXiv.2307.00374","url":null,"abstract":"Knowing exactly how many data points need to be labeled to achieve a certain model performance is a hugely beneficial step towards reducing the overall budgets for annotation. It pertains to both active learning and traditional data annotation, and is particularly beneficial for low resource scenarios. Nevertheless, it remains a largely under-explored area of research in NLP. We therefore explored various techniques for estimating the training sample size necessary to achieve a targeted performance value. We derived a simple yet effective approach to predict the maximum achievable model performance based on small amount of training samples - which serves as an early indicator during data annotation for data quality and sample size determination. We performed ablation studies on four language understanding tasks, and showed that the proposed approach allows us to forecast model performance within a small margin of mean absolute error (~ 0.9%) with only 10% data.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132589052","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: 0
A New Task and Dataset on Detecting Attacks on Human Rights Defenders 探测对人权维护者的攻击的新任务和数据集
Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-30 DOI: 10.48550/arXiv.2306.17695
Shihao Ran, Di Lu, Joel Tetreault, A. Cahill, A. Jaimes
{"title":"A New Task and Dataset on Detecting Attacks on Human Rights Defenders","authors":"Shihao Ran, Di Lu, Joel Tetreault, A. Cahill, A. Jaimes","doi":"10.48550/arXiv.2306.17695","DOIUrl":"https://doi.org/10.48550/arXiv.2306.17695","url":null,"abstract":"The ability to conduct retrospective analyses of attacks on human rights defenders over time and by location is important for humanitarian organizations to better understand historical or ongoing human rights violations and thus better manage the global impact of such events. We hypothesize that NLP can support such efforts by quickly processing large collections of news articles to detect and summarize the characteristics of attacks on human rights defenders. To that end, we propose a new dataset for detecting Attacks on Human Rights Defenders (HRDsAttack) consisting of crowdsourced annotations on 500 online news articles. The annotations include fine-grained information about the type and location of the attacks, as well as information about the victim(s). We demonstrate the usefulness of the dataset by using it to train and evaluate baseline models on several sub-tasks to predict the annotated characteristics.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122435110","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: 0
Should you marginalize over possible tokenizations? 你应该忽略可能的标记化吗?
Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-30 DOI: 10.48550/arXiv.2306.17757
N. Chirkova, Germán Kruszewski, Jos Rozen, Marc Dymetman
{"title":"Should you marginalize over possible tokenizations?","authors":"N. Chirkova, Germán Kruszewski, Jos Rozen, Marc Dymetman","doi":"10.48550/arXiv.2306.17757","DOIUrl":"https://doi.org/10.48550/arXiv.2306.17757","url":null,"abstract":"Autoregressive language models (LMs) map token sequences to probabilities. The usual practice for computing the probability of any character string (e.g. English sentences) is to first transform it into a sequence of tokens that is scored by the model. However, there are exponentially many token sequences that represent any given string. To truly compute the probability of a string one should marginalize over all tokenizations, which is typically intractable. Here, we analyze whether the practice of ignoring the marginalization is justified. To this end, we devise an importance-sampling-based algorithm that allows us to compute estimates of the marginal probabilities and compare them to the default procedure in a range of state-of-the-art models and datasets. Our results show that the gap in log-likelihood is no larger than 0.5% in most cases, but that it becomes more pronounced for data with long complex words.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129045727","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
Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation 基于多源语义图的多模态讽刺解释生成
Annual Meeting of the Association for Computational Linguistics Pub Date : 2023-06-29 DOI: 10.48550/arXiv.2306.16650
Liqiang Jing, Xuemeng Song, Kun Ouyang, Mengzhao Jia, Liqiang Nie
{"title":"Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation","authors":"Liqiang Jing, Xuemeng Song, Kun Ouyang, Mengzhao Jia, Liqiang Nie","doi":"10.48550/arXiv.2306.16650","DOIUrl":"https://doi.org/10.48550/arXiv.2306.16650","url":null,"abstract":"Multimodal Sarcasm Explanation (MuSE) is a new yet challenging task, which aims to generate a natural language sentence for a multimodal social post (an image as well as its caption) to explain why it contains sarcasm. Although the existing pioneer study has achieved great success with the BART backbone, it overlooks the gap between the visual feature space and the decoder semantic space, the object-level metadata of the image, as well as the potential external knowledge. To solve these limitations, in this work, we propose a novel mulTi-source sEmantic grAph-based Multimodal sarcasm explanation scheme, named TEAM. In particular, TEAM extracts the object-level semantic meta-data instead of the traditional global visual features from the input image. Meanwhile, TEAM resorts to ConceptNet to obtain the external related knowledge concepts for the input text and the extracted object meta-data. Thereafter, TEAM introduces a multi-source semantic graph that comprehensively characterize the multi-source (i.e., caption, object meta-data, external knowledge) semantic relations to facilitate the sarcasm reasoning. Extensive experiments on a public released dataset MORE verify the superiority of our model over cutting-edge methods.","PeriodicalId":352845,"journal":{"name":"Annual Meeting of the Association for Computational Linguistics","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133290028","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: 0
首页 上一页 下一页 尾页
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
现在去查看 取消
×
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