Phrase-Level Topic Modeling Based on Joint Embedding Space of Words, Phrases and Documents

• Item type: Trans(1)
• 公開日: 2024-01-25
• タイトル: Phrase-Level Topic Modeling Based on Joint Embedding Space of Words, Phrases and Documents
• タイトル / 言語: en
• タイトル: Phrase-Level Topic Modeling Based on Joint Embedding Space of Words, Phrases and Documents
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [研究論文] topic modeling, embeddings, Phrase-BERT
• 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: Presently with University of Tsukuba
• 著者所属: University of Tsukuba
• 著者所属: University of Tsukuba
• 著者所属(英): en
• 著者所属(英): Presently with University of Tsukuba
• 著者所属(英): en
• 著者所属(英): University of Tsukuba
• 著者所属(英): en
• 著者所属(英): University of Tsukuba
• 著者名: Zikai, Zhou; Kei, Wakabayashi; Hiroyoshi, Ito
• 著者名(英): Zikai, Zhou; Kei, Wakabayashi; Hiroyoshi, Ito
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: In topic modeling, phrases act as important grammatical units that help users interpret the semantics of extracted topics. Embedding-based topic modeling, which has been proposed recently, is a promising approach to extracting phrase-level topics because it does not suffer from scalability issues due to the increased vocabulary size by adding phrases. However, the quality of the phrase-level topics extracted by this approach has not been evaluated, and the effect of the choice of the embedding models used for this method has not been investigated. In this paper, we validate the performance of the phrase-level embedding-based topic modeling and evaluate the effect of the embedding models on the quality of the phrase-level topics. From the result of the evaluation, we realized that the existing pre-trained BERT models have limitations in either sentence or phrase representation; therefore, we further propose a joint fine-tuning of BERT for phrase and sentence embeddings to improve the quality of phrase-level topic modeling. The experimental results quantitatively and qualitatively demonstrate that the jointly fine-tuned BERT yields more coherent phrase-level topics compared with other methods, including popular LDA-based phrase topic modeling.; ------------------------------; 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: In topic modeling, phrases act as important grammatical units that help users interpret the semantics of extracted topics. Embedding-based topic modeling, which has been proposed recently, is a promising approach to extracting phrase-level topics because it does not suffer from scalability issues due to the increased vocabulary size by adding phrases. However, the quality of the phrase-level topics extracted by this approach has not been evaluated, and the effect of the choice of the embedding models used for this method has not been investigated. In this paper, we validate the performance of the phrase-level embedding-based topic modeling and evaluate the effect of the embedding models on the quality of the phrase-level topics. From the result of the evaluation, we realized that the existing pre-trained BERT models have limitations in either sentence or phrase representation; therefore, we further propose a joint fine-tuning of BERT for phrase and sentence embeddings to improve the quality of phrase-level topic modeling. The experimental results quantitatively and qualitatively demonstrate that the jointly fine-tuned BERT yields more coherent phrase-level topics compared with other methods, including popular LDA-based phrase topic modeling.; ------------------------------; 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 1, 発行日 2024-01-25
• 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