Transactions of the Association for Computational Linguistics最新文献

Beyond Boundaries: A Human-like Approach for Question Answering over Structured and Unstructured Information Sources 超越界限：结构化和非结构化信息源问题解答的类人方法

Transactions of the Association for Computational Linguistics Pub Date : 2024-06-01 DOI: 10.1162/tacl_a_00671

Jens Lehmann, Dhananjay Bhandiwad, Preetam Gattogi, S. Vahdati

引用次数: 1

An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation 基于能量的计算机辅助翻译单词级自动补全模型

Transactions of the Association for Computational Linguistics Pub Date : 2024-02-01 DOI: 10.1162/tacl_a_00637

Cheng Yang, Guoping Huang, Mo Yu, Zhirui Zhang, Siheng Li, Mingming Yang, Shuming Shi, Yujiu Yang, Lemao Liu

{"title":"An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation","authors":"Cheng Yang, Guoping Huang, Mo Yu, Zhirui Zhang, Siheng Li, Mingming Yang, Shuming Shi, Yujiu Yang, Lemao Liu","doi":"10.1162/tacl_a_00637","DOIUrl":"https://doi.org/10.1162/tacl_a_00637","url":null,"abstract":"Abstract Word-level AutoCompletion (WLAC) is a rewarding yet challenging task in Computer-aided Translation. Existing work addresses this task through a classification model based on a neural network that maps the hidden vector of the input context into its corresponding label (i.e., the candidate target word is treated as a label). Since the context hidden vector itself does not take the label into account and it is projected to the label through a linear classifier, the model cannot sufficiently leverage valuable information from the source sentence as verified in our experiments, which eventually hinders its overall performance. To alleviate this issue, this work proposes an energy-based model for WLAC, which enables the context hidden vector to capture crucial information from the source sentence. Unfortunately, training and inference suffer from efficiency and effectiveness challenges, therefore we employ three simple yet effective strategies to put our model into practice. Experiments on four standard benchmarks demonstrate that our reranking-based approach achieves substantial improvements (about 6.07%) over the previous state-of-the-art model. Further analyses show that each strategy of our approach contributes to the final performance.1","PeriodicalId":506323,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"24 1","pages":"137-156"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139891085","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

An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation 基于能量的计算机辅助翻译单词级自动补全模型

Transactions of the Association for Computational Linguistics Pub Date : 2024-02-01 DOI: 10.1162/tacl_a_00637

Cheng Yang, Guoping Huang, Mo Yu, Zhirui Zhang, Siheng Li, Mingming Yang, Shuming Shi, Yujiu Yang, Lemao Liu

{"title":"An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation","authors":"Cheng Yang, Guoping Huang, Mo Yu, Zhirui Zhang, Siheng Li, Mingming Yang, Shuming Shi, Yujiu Yang, Lemao Liu","doi":"10.1162/tacl_a_00637","DOIUrl":"https://doi.org/10.1162/tacl_a_00637","url":null,"abstract":"Abstract Word-level AutoCompletion (WLAC) is a rewarding yet challenging task in Computer-aided Translation. Existing work addresses this task through a classification model based on a neural network that maps the hidden vector of the input context into its corresponding label (i.e., the candidate target word is treated as a label). Since the context hidden vector itself does not take the label into account and it is projected to the label through a linear classifier, the model cannot sufficiently leverage valuable information from the source sentence as verified in our experiments, which eventually hinders its overall performance. To alleviate this issue, this work proposes an energy-based model for WLAC, which enables the context hidden vector to capture crucial information from the source sentence. Unfortunately, training and inference suffer from efficiency and effectiveness challenges, therefore we employ three simple yet effective strategies to put our model into practice. Experiments on four standard benchmarks demonstrate that our reranking-based approach achieves substantial improvements (about 6.07%) over the previous state-of-the-art model. Further analyses show that each strategy of our approach contributes to the final performance.1","PeriodicalId":506323,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"1447 ","pages":"137-156"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139831090","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

Addressing the Binning Problem in Calibration Assessment through Scalar Annotations 通过标量注释解决校准评估中的分选问题

Transactions of the Association for Computational Linguistics Pub Date : 2024-02-01 DOI: 10.1162/tacl_a_00636

Zhengping Jiang, Anqi Liu, Benjamnin Van Durme

引用次数: 0

Addressing the Binning Problem in Calibration Assessment through Scalar Annotations 通过标量注释解决校准评估中的分选问题

Transactions of the Association for Computational Linguistics Pub Date : 2024-02-01 DOI: 10.1162/tacl_a_00636

Zhengping Jiang, Anqi Liu, Benjamnin Van Durme

引用次数: 0