In real-world data, e.g., from Web forums, text is often contaminated with redundant or irrelevant content, which leads to introducing noise in machine learning algorithms. In this paper, we apply Long Short-Lerm Memory networks with an attention mechanism, which can select important parts of text for the task of similar question retrieval from community Question Answering (cQA) forums. In particular, we use the attention weights for both selecting entire sentences and their subparts, i.e., word/chunk, from shallow syntactic trees. More interestingly, we apply tree kernels to the filtered text representations, thus exploiting the implicit features of the subtree space for learning question reranking. Our results show that the attention-based pruning allows for achieving the top position in the cQA challenge of SemEval 2016, with a relatively large gap from the other participants while greatly decreasing running time.

Neural attention for learning to rank questions in community question answering

Da San Martino G.;Barron-Cedeno A.;
2016

Abstract

In real-world data, e.g., from Web forums, text is often contaminated with redundant or irrelevant content, which leads to introducing noise in machine learning algorithms. In this paper, we apply Long Short-Lerm Memory networks with an attention mechanism, which can select important parts of text for the task of similar question retrieval from community Question Answering (cQA) forums. In particular, we use the attention weights for both selecting entire sentences and their subparts, i.e., word/chunk, from shallow syntactic trees. More interestingly, we apply tree kernels to the filtered text representations, thus exploiting the implicit features of the subtree space for learning question reranking. Our results show that the attention-based pruning allows for achieving the top position in the cQA challenge of SemEval 2016, with a relatively large gap from the other participants while greatly decreasing running time.
COLING 2016 - 26th International Conference on Computational Linguistics, Proceedings of COLING 2016: Technical Papers
1734
1745
Romeo S.; Da San Martino G.; Barron-Cedeno A.; Moschitti A.; Belinkov Y.; Hsu W.-N.; Zhang Y.; Mohtarami M.; Glass J.
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/709249
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 30
  • ???jsp.display-item.citation.isi??? ND
social impact