POS Tagging using Dependency Information

• Item type: SIG Technical Reports(1)
• 公開日: 2011-07-08
• タイトル: POS Tagging using Dependency Information
• タイトル / 言語: en
• タイトル: POS Tagging using Dependency Information
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 字句解析
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Nara Institute of Science and Technology
• 著者所属: Nara Institute of Science and Technology
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology
• 著者名: Erlyn, Manguilimotan; Yuji, Matsumoto
• 著者名(英): Erlyn, Manguilimotan; Yuji, Matsumoto
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: This paper presents a POS tagging approach that makes use of dependency information of a word as feature to condition a model. A part-of-speech tagger for Tagalog makes use of morphological information such as affixes and reduplication as features. However, state-of-the art sequential labeling technique cannot achieve high accuracy for Tagalog. In this work, we investigate the use of dependency head information of the words to help predict the POS tag of the word. Most existing dependency parsing assumes POS tagging as a preprocess. In this paper, we did the reverse. We apply dependency parsing without POS information, and the POS tagger tested using the output of the dependency parser. Experiments show that this approach improves the baseline scores of the POS taggers of about 1.5% for POS unigram model and 2% for POS bigram model.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: This paper presents a POS tagging approach that makes use of dependency information of a word as feature to condition a model. A part-of-speech tagger for Tagalog makes use of morphological information such as affixes and reduplication as features. However, state-of-the art sequential labeling technique cannot achieve high accuracy for Tagalog. In this work, we investigate the use of dependency head information of the words to help predict the POS tag of the word. Most existing dependency parsing assumes POS tagging as a preprocess. In this paper, we did the reverse. We apply dependency parsing without POS information, and the POS tagger tested using the output of the dependency parser. Experiments show that this approach improves the baseline scores of the POS taggers of about 1.5% for POS unigram model and 2% for POS bigram model.
• 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: AN10115061
• 書誌情報: 研究報告自然言語処理（NL）; 巻 2011-NL-202, 号 2, p. 1-8, 発行日 2011-07-08
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会