Abstract
A typical knowledge-based question answering (KB-QA) system faces two challenges: one is to transform natural language questions into their meaning representations (MRs); the other is to retrieve answers from knowledge bases (KBs) using generated MRs. Unlike previous methods which treat them in a cascaded manner, we present a translation-based approach to solve these two tasks in one unified framework. We translate questions to answers based on CYK parsing. Answers as translations of the span covered by each CYK cell are obtained by a question translation method, which first generates formal triple queries as MRs for the span based on question patterns and relation expressions, and then retrieves answers from a given KB based on triple queries generated. A linear model is defined over derivations, and minimum error rate training is used to tune feature weights based on a set of question-answer pairs. Compared to a KB-QA system using a state-of-the-art semantic parser, our method achieves better results.
Highlights
Knowledge-based question answering (KB-QA) computes answers to natural language (NL) questions based on existing knowledge bases (KBs)
Like machine translation (MT), CYK parsing is used to parse each input question, and answers of the span covered by each CYK cell are considered the translations of that cell; unlike MT, which uses offline-generated translation tables to translate source phrases into target translations, a semantic parsing-based question translation method is used to translate each span into its answers on-the-fly, based on question patterns and relation expressions
Our method has further advantages: (1) Question answering and semantic parsing are performed in an joint way under a unified framework; (2) A robust method is proposed to map NL questions to their formal triple queries, which trades off the mapping quality by using question patterns and relation expressions in a cascaded way; and (3) We use domain independent feature set which allowing us to use a relatively small number of question-answer pairs to tune model parameters
Summary
Knowledge-based question answering (KB-QA) computes answers to natural language (NL) questions based on existing knowledge bases (KBs). Unlike existing KB-QA systems which treat semantic parsing and answer retrieval as two cascaded tasks, this paper presents a unified framework that can integrate semantic parsing into the question answering procedure directly. The final answers can be obtained from the root cell Derivations generated during such a translation procedure are modeled by a linear model, and minimum error rate training (MERT) (Och, 2003) is used to tune feature weights based on a set of question-answer pairs. We define the task of transforming question spans into formal triples as question translation. According to the above description, our KBQA method can be decomposed into four tasks as: (1) search space generation for H(Q); (2) question translation for transforming question spans into their corresponding formal triples; (3) feature design for hi(·); and (4) feature weight tuning for {λi}. We present details of these four tasks in the following subsections one-by-one
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call