Acceptability Evaluation of Naturally Written Sentences

• Item type: Trans(1)
• 公開日: 2024-07-24
• タイトル: Acceptability Evaluation of Naturally Written Sentences
• タイトル / 言語: en
• タイトル: Acceptability Evaluation of Naturally Written Sentences
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [研究論文] acceptability, readability, grammaticality, generative text, text evaluation, syntactic knowledge, speakers judgement
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Tokyo Institute of Technology
• 著者所属: University of Pennsylvania
• 著者所属: Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): University of Pennsylvania
• 著者所属(英): en
• 著者所属(英): Tokyo Institute of Technology
• 著者名: Vijay, Daultani; Héctor, Javier Vázquez Martínez; Naoaki, Okazaki
• 著者名(英): Vijay, Daultani; Héctor, Javier Vázquez Martínez; Naoaki, Okazaki
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: The success of Language Models (LMs) on a variety of NLP tasks has prompted the design and analysis of natural language benchmarks to evaluate their fitness for particular applications. In this work, we focus on the NLP task of acceptability rating, whereby a given model must rate the ‘goodness’ of a series of tokens. We find the current commonly used datasets to benchmark for LM sentence acceptability fail to capture the distribution of naturally occurring written data. Moreover, we find that the bias toward shorter (5-8 word) sentences is a strong confounding factor that contributes positively to LMs' performance. We then introduce seven datasets collected from the NLP literature that closely follow the sentence length distribution of naturally occurring written text. In our experiments, when sentence length is controlled by adjusting the distribution to match naturally occurring data, we observe a performance drop for current commonly used datasets of up to 48 points in MCC. We conclude with a discussion on implications for current applications and recommendations to improve our current commonly used acceptability benchmarking datasets.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.32(2024) (online); ------------------------------
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: The success of Language Models (LMs) on a variety of NLP tasks has prompted the design and analysis of natural language benchmarks to evaluate their fitness for particular applications. In this work, we focus on the NLP task of acceptability rating, whereby a given model must rate the ‘goodness’ of a series of tokens. We find the current commonly used datasets to benchmark for LM sentence acceptability fail to capture the distribution of naturally occurring written data. Moreover, we find that the bias toward shorter (5-8 word) sentences is a strong confounding factor that contributes positively to LMs' performance. We then introduce seven datasets collected from the NLP literature that closely follow the sentence length distribution of naturally occurring written text. In our experiments, when sentence length is controlled by adjusting the distribution to match naturally occurring data, we observe a performance drop for current commonly used datasets of up to 48 points in MCC. We conclude with a discussion on implications for current applications and recommendations to improve our current commonly used acceptability benchmarking datasets.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.32(2024) (online); ------------------------------
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11464847
• 書誌情報: 情報処理学会論文誌データベース（TOD）; 巻 17, 号 3, 発行日 2024-07-24
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7799
• 出版者 / 言語: ja
• 出版者: 情報処理学会