@inproceedings{cc260bb7f3bb463c92969d896561de5f,
title = "Spinning straw into gold: Using free text to train monolingual alignment models for non-factoid question answering",
abstract = "Monolingual alignment models have been shown to boost the performance of question answering systems by {"}bridging the lexical chasm{"} between questions and answers. The main limitation of these approaches is that they require semistructured training data in the form of question-answer pairs, which is difficult to obtain in specialized domains or lowresource languages. We propose two inexpensive methods for training alignment models solely using free text, by generating artificial question-answer pairs from discourse structures. Our approach is driven by two representations of discourse: a shallow sequential representation, and a deep one based on Rhetorical Structure Theory. We evaluate the proposed model on two corpora from different genres and domains: one from Yahoo! Answers and one from the biology domain, and two types of non-factoid questions: manner and reason. We show that these alignment models trained directly from discourse structures imposed on free text improve performance considerably over an information retrieval baseline and a neural network language model trained on the same data.",
author = "Rebecca Sharp and Peter Jansen and Mihai Surdeanu and Peter Clark",
note = "Publisher Copyright: {\textcopyright} 2015 Association for Computational Linguistics.; Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2015 ; Conference date: 31-05-2015 Through 05-06-2015",
year = "2015",
doi = "10.3115/v1/n15-1025",
language = "English (US)",
series = "NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "231--237",
booktitle = "NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics",
}