| Revue: | Computación y sistemas |
| Base de datos: | |
| Número de sistema: | 000560361 |
| ISSN: | 1405-5546 |
| Autores: | Ha, Thi-Thanh2 Nguyen, Thanh-Chinh1 Nguyen, Kiem-Hieu1 Vu, Van-Chung1 Nguyen, Kim-Anh1 |
| Instituciones: | 1Hanoi University of Science and Technology, Hanoi. Vietnam 2Thai Nguyen University of Information and Communication Technology, Thai Nguyen. Vietnam |
| Año: | 2018 |
| Periodo: | Jul-Sep |
| Volumen: | 22 |
| Número: | 3 |
| Paginación: | 835-843 |
| País: | México |
| Idioma: | Inglés |
| Tipo de documento: | Artículo |
| Resumen en inglés | This paper presents a method for summarizing answers in Community Question Answering. We explore deep Auto-encoder and Long-short-term-memory Auto-encoder for sentence representation. The sentence representations are used to measure similarity in Maximal Marginal Relevance algorithm for extractive summarization. Experimental results on a benchmark dataset show that our unsupervised method achieves state-of-the-art performance while requiring no annotated data. |
| Disciplinas: | Ciencias de la computación |
| Palabras clave: | Inteligencia artificial |
| Keyword: | Summarizing answers, Non-factoid questions, Multi-documment summarization, Community question-answering, Auto encoder, LSTM, Artificial intelligence |
| Texte intégral: | Texto completo (Ver HTML) Texto completo (Ver PDF) |
