Knowledge-based question answering using the semantic embedding space

Min Chul Yang, Do Gil Lee, So Young Park, Hae-Chang Rim

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Semantic transformation of a natural language question into its corresponding logical form is crucial for knowledge-based question answering systems. Most previous methods have tried to achieve this goal by using syntax-based grammar formalisms and rule-based logical inference. However, these approaches are usually limited in terms of the coverage of the lexical trigger, which performs a mapping task from words to the logical properties of the knowledge base, and thus it is easy to ignore implicit and broken relations between properties by not interpreting the full knowledge base. In this study, our goal is to answer questions in any domains by using the semantic embedding space in which the embeddings encode the semantics of words and logical properties. In the latent space, the semantic associations between existing features can be exploited based on their embeddings without using a manually produced lexicon and rules. This embedding-based inference approach for question answering allows the mapping of factoid questions posed in a natural language onto logical representations of the correct answers guided by the knowledge base. In terms of the overall question answering performance, our experimental results and examples demonstrate that the proposed method outperforms previous knowledge-based question answering baseline methods with a publicly released question answering evaluation dataset: WebQuestions.

Original languageEnglish
Article number10144
Pages (from-to)9086-9104
Number of pages19
JournalExpert Systems with Applications
Volume42
Issue number23
DOIs
Publication statusPublished - 2015 Dec 15

Fingerprint

Semantics

Keywords

  • Distributional semantics
  • Embedding model
  • Knowledge base
  • Labeled-LDA
  • Neural networks
  • Question answering

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Engineering(all)

Cite this

Knowledge-based question answering using the semantic embedding space. / Yang, Min Chul; Lee, Do Gil; Park, So Young; Rim, Hae-Chang.

In: Expert Systems with Applications, Vol. 42, No. 23, 10144, 15.12.2015, p. 9086-9104.

Research output: Contribution to journalArticle

Yang, Min Chul ; Lee, Do Gil ; Park, So Young ; Rim, Hae-Chang. / Knowledge-based question answering using the semantic embedding space. In: Expert Systems with Applications. 2015 ; Vol. 42, No. 23. pp. 9086-9104.
@article{313ab655e2394d52ad2ea8fb07250acc,
title = "Knowledge-based question answering using the semantic embedding space",
abstract = "Semantic transformation of a natural language question into its corresponding logical form is crucial for knowledge-based question answering systems. Most previous methods have tried to achieve this goal by using syntax-based grammar formalisms and rule-based logical inference. However, these approaches are usually limited in terms of the coverage of the lexical trigger, which performs a mapping task from words to the logical properties of the knowledge base, and thus it is easy to ignore implicit and broken relations between properties by not interpreting the full knowledge base. In this study, our goal is to answer questions in any domains by using the semantic embedding space in which the embeddings encode the semantics of words and logical properties. In the latent space, the semantic associations between existing features can be exploited based on their embeddings without using a manually produced lexicon and rules. This embedding-based inference approach for question answering allows the mapping of factoid questions posed in a natural language onto logical representations of the correct answers guided by the knowledge base. In terms of the overall question answering performance, our experimental results and examples demonstrate that the proposed method outperforms previous knowledge-based question answering baseline methods with a publicly released question answering evaluation dataset: WebQuestions.",
keywords = "Distributional semantics, Embedding model, Knowledge base, Labeled-LDA, Neural networks, Question answering",
author = "Yang, {Min Chul} and Lee, {Do Gil} and Park, {So Young} and Hae-Chang Rim",
year = "2015",
month = "12",
day = "15",
doi = "10.1016/j.eswa.2015.07.009",
language = "English",
volume = "42",
pages = "9086--9104",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "23",

}

TY - JOUR

T1 - Knowledge-based question answering using the semantic embedding space

AU - Yang, Min Chul

AU - Lee, Do Gil

AU - Park, So Young

AU - Rim, Hae-Chang

PY - 2015/12/15

Y1 - 2015/12/15

N2 - Semantic transformation of a natural language question into its corresponding logical form is crucial for knowledge-based question answering systems. Most previous methods have tried to achieve this goal by using syntax-based grammar formalisms and rule-based logical inference. However, these approaches are usually limited in terms of the coverage of the lexical trigger, which performs a mapping task from words to the logical properties of the knowledge base, and thus it is easy to ignore implicit and broken relations between properties by not interpreting the full knowledge base. In this study, our goal is to answer questions in any domains by using the semantic embedding space in which the embeddings encode the semantics of words and logical properties. In the latent space, the semantic associations between existing features can be exploited based on their embeddings without using a manually produced lexicon and rules. This embedding-based inference approach for question answering allows the mapping of factoid questions posed in a natural language onto logical representations of the correct answers guided by the knowledge base. In terms of the overall question answering performance, our experimental results and examples demonstrate that the proposed method outperforms previous knowledge-based question answering baseline methods with a publicly released question answering evaluation dataset: WebQuestions.

AB - Semantic transformation of a natural language question into its corresponding logical form is crucial for knowledge-based question answering systems. Most previous methods have tried to achieve this goal by using syntax-based grammar formalisms and rule-based logical inference. However, these approaches are usually limited in terms of the coverage of the lexical trigger, which performs a mapping task from words to the logical properties of the knowledge base, and thus it is easy to ignore implicit and broken relations between properties by not interpreting the full knowledge base. In this study, our goal is to answer questions in any domains by using the semantic embedding space in which the embeddings encode the semantics of words and logical properties. In the latent space, the semantic associations between existing features can be exploited based on their embeddings without using a manually produced lexicon and rules. This embedding-based inference approach for question answering allows the mapping of factoid questions posed in a natural language onto logical representations of the correct answers guided by the knowledge base. In terms of the overall question answering performance, our experimental results and examples demonstrate that the proposed method outperforms previous knowledge-based question answering baseline methods with a publicly released question answering evaluation dataset: WebQuestions.

KW - Distributional semantics

KW - Embedding model

KW - Knowledge base

KW - Labeled-LDA

KW - Neural networks

KW - Question answering

UR - http://www.scopus.com/inward/record.url?scp=84940641418&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940641418&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2015.07.009

DO - 10.1016/j.eswa.2015.07.009

M3 - Article

AN - SCOPUS:84940641418

VL - 42

SP - 9086

EP - 9104

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 23

M1 - 10144

ER -