Learning pairwise patterns in Community Question Answering

Simone Filice, Alessandro Moschitti

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In recent years, forums offering community Question Answering (cQA) services gained popularity on the web, as they offer a new opportunity for users to search and share knowledge. In fact, forums allow users to freely ask questions and expect answers from the community. Although the idea of receiving a direct, targeted response from other users is very attractive, it is not rare to see long threads of comments, where only a small portion of them are actually valid answers. In many cases users start conversations, ask for other information, and discuss about things, which are not central to the original topic. Therefore, finding the desired information in a long list of answers might be very time-consuming. Designing automatic systems to select good answers is not an easy task. In many cases the question and the answer do not share a large textual content, and approaches based on measuring the question-answer similarity will often fail. A more intriguing and promising approach would be trying to define valid question-answer templates and use a system to understand whether any of these templates is satisfied for a given question-answer pair. Unfortunately, the manual definition of these templates is extremely complex and requires a domain-expert. In this paper, we propose a supervised kernel-based framework that automatically learns from training question-answer pairs the syntactic/semantic patterns useful to recognize good answers. We carry out a detailed experimental evaluation, where we demonstrate that the proposed framework achieves state-of-the-art results on the Qatar Living datasets released in three different editions of the Community Question Answering Challenge of SemEval.

Original languageEnglish
Pages (from-to)49-65
Number of pages17
JournalIntelligenza Artificiale
Volume12
Issue number2
DOIs
Publication statusPublished - 1 Jan 2018

Fingerprint

Syntactics
Semantics

Keywords

  • Community Question Answering
  • Kernel methods
  • Structured Language Learning

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Learning pairwise patterns in Community Question Answering. / Filice, Simone; Moschitti, Alessandro.

In: Intelligenza Artificiale, Vol. 12, No. 2, 01.01.2018, p. 49-65.

Research output: Contribution to journalArticle

@article{12ed42b15145449b93794620b0786cf9,
title = "Learning pairwise patterns in Community Question Answering",
abstract = "In recent years, forums offering community Question Answering (cQA) services gained popularity on the web, as they offer a new opportunity for users to search and share knowledge. In fact, forums allow users to freely ask questions and expect answers from the community. Although the idea of receiving a direct, targeted response from other users is very attractive, it is not rare to see long threads of comments, where only a small portion of them are actually valid answers. In many cases users start conversations, ask for other information, and discuss about things, which are not central to the original topic. Therefore, finding the desired information in a long list of answers might be very time-consuming. Designing automatic systems to select good answers is not an easy task. In many cases the question and the answer do not share a large textual content, and approaches based on measuring the question-answer similarity will often fail. A more intriguing and promising approach would be trying to define valid question-answer templates and use a system to understand whether any of these templates is satisfied for a given question-answer pair. Unfortunately, the manual definition of these templates is extremely complex and requires a domain-expert. In this paper, we propose a supervised kernel-based framework that automatically learns from training question-answer pairs the syntactic/semantic patterns useful to recognize good answers. We carry out a detailed experimental evaluation, where we demonstrate that the proposed framework achieves state-of-the-art results on the Qatar Living datasets released in three different editions of the Community Question Answering Challenge of SemEval.",
keywords = "Community Question Answering, Kernel methods, Structured Language Learning",
author = "Simone Filice and Alessandro Moschitti",
year = "2018",
month = "1",
day = "1",
doi = "10.3233/IA-170034",
language = "English",
volume = "12",
pages = "49--65",
journal = "Intelligenza Artificiale",
issn = "1724-8035",
publisher = "IOS Press",
number = "2",

}

TY - JOUR

T1 - Learning pairwise patterns in Community Question Answering

AU - Filice, Simone

AU - Moschitti, Alessandro

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In recent years, forums offering community Question Answering (cQA) services gained popularity on the web, as they offer a new opportunity for users to search and share knowledge. In fact, forums allow users to freely ask questions and expect answers from the community. Although the idea of receiving a direct, targeted response from other users is very attractive, it is not rare to see long threads of comments, where only a small portion of them are actually valid answers. In many cases users start conversations, ask for other information, and discuss about things, which are not central to the original topic. Therefore, finding the desired information in a long list of answers might be very time-consuming. Designing automatic systems to select good answers is not an easy task. In many cases the question and the answer do not share a large textual content, and approaches based on measuring the question-answer similarity will often fail. A more intriguing and promising approach would be trying to define valid question-answer templates and use a system to understand whether any of these templates is satisfied for a given question-answer pair. Unfortunately, the manual definition of these templates is extremely complex and requires a domain-expert. In this paper, we propose a supervised kernel-based framework that automatically learns from training question-answer pairs the syntactic/semantic patterns useful to recognize good answers. We carry out a detailed experimental evaluation, where we demonstrate that the proposed framework achieves state-of-the-art results on the Qatar Living datasets released in three different editions of the Community Question Answering Challenge of SemEval.

AB - In recent years, forums offering community Question Answering (cQA) services gained popularity on the web, as they offer a new opportunity for users to search and share knowledge. In fact, forums allow users to freely ask questions and expect answers from the community. Although the idea of receiving a direct, targeted response from other users is very attractive, it is not rare to see long threads of comments, where only a small portion of them are actually valid answers. In many cases users start conversations, ask for other information, and discuss about things, which are not central to the original topic. Therefore, finding the desired information in a long list of answers might be very time-consuming. Designing automatic systems to select good answers is not an easy task. In many cases the question and the answer do not share a large textual content, and approaches based on measuring the question-answer similarity will often fail. A more intriguing and promising approach would be trying to define valid question-answer templates and use a system to understand whether any of these templates is satisfied for a given question-answer pair. Unfortunately, the manual definition of these templates is extremely complex and requires a domain-expert. In this paper, we propose a supervised kernel-based framework that automatically learns from training question-answer pairs the syntactic/semantic patterns useful to recognize good answers. We carry out a detailed experimental evaluation, where we demonstrate that the proposed framework achieves state-of-the-art results on the Qatar Living datasets released in three different editions of the Community Question Answering Challenge of SemEval.

KW - Community Question Answering

KW - Kernel methods

KW - Structured Language Learning

UR - http://www.scopus.com/inward/record.url?scp=85062396438&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062396438&partnerID=8YFLogxK

U2 - 10.3233/IA-170034

DO - 10.3233/IA-170034

M3 - Article

AN - SCOPUS:85062396438

VL - 12

SP - 49

EP - 65

JO - Intelligenza Artificiale

JF - Intelligenza Artificiale

SN - 1724-8035

IS - 2

ER -