Sentence extraction using similar words

• Autorzy: Suzuki Y. , Fukumoto F.
• Konferencja: Human Language Technologies as a challenge for Computer Science and Linguistics (2; 21-23.04.2005; Poznań, Poland)
• Języki publikacji: EN

Abstrakty

EN

In both written and spoken languages, we sometimes use different words in order to describe the same thing. For Instance, we use "candidacy and "running in an election" as the same meaning. This makes text classification, event tracking and text summarization difficult. In this paper, we propose a method to extract words which are semantically similar to each other accurately. Using this method, we extracted similar word pairs from newspaper articles. Furthermore, we performed sentence extraction from the newspaper articles using the extracted similar word pairs. We hypothesized that the headline is salient information of the newspaper article and presence of headline terms in the article can be used to detect salient sentences of news text. By using similar words in the headline, we obtained better results than that without using it. The results suggest that our method is useful for text summarization.

Słowa kluczowe

EN

sentence extraction; newspaper articles; headline; similar words; respective nearest neighbors (RNNs); text summarization

• Wydawca: Polish Academy of Sciences, Committee of Automatic Control and Robotics
• Czasopismo: Archives of Control Sciences
• Rocznik: 2005
• Tom: Vol. 15, no. 4
• Strony: 665--672
• Opis fizyczny: Bibliogr. 8 poz., rys., tab.

Twórcy

autor

Suzuki Y.

• University of Yamanashi 4-3-11 Takeda, Kofu, Japan

autor

Fukumoto F.

• University of Yamanashi 4-3-11 Takeda, Kofu, Japan

Bibliografia

• [1] R. Brandow, K. Mitze and L. Rau: Automatic condensation of electronic publications by sentence selection. MIT Press, (1999) 293-303.
• [2] T. Fukusima and M. Okumura: Text summarization challenge: Text Summarization Evaluation at NTCIR Workshop2. In NTCIR Workshop 2 Proc. 2nd NTCIR Workshop on Research in Chinese & Japanese Text Retrieval and Text Summarization, (2001).
• [3] D. Hindle: Noun classification from predicate-argument structures. In Proc. 28th Annual Meeting of the Association for Computational Linguistics, (1990), 268-275.
• [4] K. Kanzaki, Q. Ma, M. Murata and H. Isahara: Similarities and differences among semantic behaviors of Japanese adnominal constituents. In Proc. ANLP/NAACL'2000 Workshop: Syntactic and Semantic Complexity in Natural Language Processing Systems, (2000), 59-68.
• [5] T. Kudo and Y. Matsumoto: Japanese dependency analysis using cascaded chunking. In CoNLL'2002: Proc. 6th Conf. on Natural Language Learning. (2002), 63-69.
• [6] D. Lin: Using syntactic dependency as local context to resolve word sense ambiguity. In Proc. ACL/EACL-97, (1997), 64-71.
• [7] D. Lin: Automatic retrieval and clustering of similar words. In Proc. 36th Annual Meeting of the Association for Computational Linguistics and 17th Int. Conf. On Computational Linguistics, (1998), 768-774.
• [8] Y. Seki: Sentence extraction by tf/idf and position weighting from newspaper articles. In Proc. Third NTCIR Workshop, (2003).