Discourse Complements Lexical Semantics for Non-factoid Answer Reranking
Discourse Complements Lexical Semantics for Non-factoid Answer Reranking
复制标题
DOI：
10.3115/v1/p14-1092
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Peter Alexander Jansen;M. Surdeanu;Peter Clark
中科院分区：
文献类型：
--
作者：
Peter Alexander Jansen;M. Surdeanu;Peter Clark
我们提出了一个强大的答案重排序模型的非事实性问题，整合词汇语义与话语信息，驱动两个表示的话语：一个浅层的话语标记为中心，和一个深层的修辞结构理论的基础上。我们从不同的流派和领域的两个语料库评估所提出的模型：一个从雅虎！答案和一个来自生物领域，和两种类型的非事实性问题：方式和原因。我们的实验表明，非事实答案的话语结构提供的信息是补充问题和答案之间的词汇语义相似性，提高性能高达24%（相对）的国家的最先进的模型，利用词汇语义相似性单独。我们进一步证明了话语信息的出色域转移，表明这些话语特征对非事实性问答具有普遍效用。
We propose a robust answer reranking model for non-factoid questions that integrates lexical semantics with discourse information, driven by two representations of discourse: a shallow representation centered around discourse markers, 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 experimentally demonstrate that the discourse structure of nonfactoid answers provides information that is complementary to lexical semantic similarity between question and answer, improving performance up to 24% (relative) over a state-of-the-art model that exploits lexical semantic similarity alone. We further demonstrate excellent domain transfer of discourse information, suggesting these discourse features have general utility to non-factoid question answering.