Word Graph-Based Multi-sentence Compression: Re-ranking Candidates Using Frequent Words
| Autor: | Van-Giau Ung, An-Vinh Luong, Minh-Quoc Nghiem, Nhi-Thao Tran |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Sentence compression
business.industry Computer science Speech recognition Context (language use) computer.software_genre Word graph Task (project management) Medical services Compression (functional analysis) Re ranking Single sentence Artificial intelligence business computer Natural language processing |
| Zdroj: | KSE |
| DOI: | 10.1109/kse.2015.65 |
| Popis: | Multi-Sentence Compression is a task whose goal is to produce a short single sentence summary from a group of similar sentences. This paper presents a new re-ranking method based on frequent words extraction along with our modifications on a word graph-based MSC approach to reduce incorrect output. Compression candidates are re-ranked according to the number of frequent words they contain to select the most relevant output. Results of automatic evaluations performed in English and Vietnamese datasets show that the proposed method remarkably improves the generated compressions informativity. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|