Resumen

HA, Thi-Thanh et al. Unsupervised Sentence Embeddings for Answer Summarization in Non-factoid CQA. Comp. y Sist. [online]. 2018, vol.22, n.3, pp.835-843. ISSN 2007-9737.  https://doi.org/10.13053/cys-22-3-3027.

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.

Palabras llave : Summarizing answers; non-factoid questions; multi-documment summarization; community question-answering; auto encoder; LSTM.

        · texto en Inglés     · Inglés ( pdf )