Identifying Opinion Holders for Question Answering in
Opinion Texts
S. Kim, and E. Hovy. Proceedings of AAAI-05 Workshop on Question Answering
in Restricted Domains, Pittsburgh, US, (2005)
Abstract
Question answering in opinion texts has so far mostly
concentrated on the identification of opinions and on
analyzing the sentiment expressed in opinions. In this
paper, we address another important part of Question
Answering (QA) in opinion texts: finding opinion
holders. Holder identification is a central part of
full opinion identification and can be used
independently to answer several opinion questions such
as �Is China supporting Bush�s war on
Iraq?� and �Do Iraqi people want U.S.
troops in their soil?�. Our system automatically
learns the syntactic features signaling opinion holders
using a Maximum Entropy ranking algorithm trained on
human annotated data. Using syntactic parsing features,
our system achieved 64% accuracy on identifying the
holder of opinions in the MPQA dataset.
%0 Conference Paper
%1 Kim05
%A Kim, Soo-Min
%A Hovy, Eduard
%B Proceedings of AAAI-05 Workshop on Question Answering
in Restricted Domains
%C Pittsburgh, US
%D 2005
%K imported
%T Identifying Opinion Holders for Question Answering in
Opinion Texts
%U http://www.isi.edu/~skim/Download/Papers/2005/WS1305SK.pdf
%X Question answering in opinion texts has so far mostly
concentrated on the identification of opinions and on
analyzing the sentiment expressed in opinions. In this
paper, we address another important part of Question
Answering (QA) in opinion texts: finding opinion
holders. Holder identification is a central part of
full opinion identification and can be used
independently to answer several opinion questions such
as �Is China supporting Bush�s war on
Iraq?� and �Do Iraqi people want U.S.
troops in their soil?�. Our system automatically
learns the syntactic features signaling opinion holders
using a Maximum Entropy ranking algorithm trained on
human annotated data. Using syntactic parsing features,
our system achieved 64% accuracy on identifying the
holder of opinions in the MPQA dataset.
@inproceedings{Kim05,
abstract = {Question answering in opinion texts has so far mostly
concentrated on the identification of opinions and on
analyzing the sentiment expressed in opinions. In this
paper, we address another important part of Question
Answering (QA) in opinion texts: finding opinion
holders. Holder identification is a central part of
full opinion identification and can be used
independently to answer several opinion questions such
as {\"i}¿½Is China supporting Bush{\"i}¿½s war on
Iraq?{\"i}¿½ and {\"i}¿½Do Iraqi people want U.S.
troops in their soil?{\"i}¿½. Our system automatically
learns the syntactic features signaling opinion holders
using a Maximum Entropy ranking algorithm trained on
human annotated data. Using syntactic parsing features,
our system achieved 64% accuracy on identifying the
holder of opinions in the MPQA dataset.},
added-at = {2009-01-22T05:56:16.000+0100},
address = {Pittsburgh, US},
author = {Kim, Soo-Min and Hovy, Eduard},
biburl = {https://www.bibsonomy.org/bibtex/29247aca8e67b1b5ad85ea11dbd66ee4a/kabloom},
booktitle = {Proceedings of AAAI-05 Workshop on Question Answering
in Restricted Domains},
interhash = {13dc95058a22992c24ee739f7784a491},
intrahash = {9247aca8e67b1b5ad85ea11dbd66ee4a},
keywords = {imported},
pdf = {Kim05.pdf},
timestamp = {2011-03-09T04:36:53.000+0100},
title = {Identifying Opinion Holders for Question Answering in
Opinion Texts},
url = {http://www.isi.edu/~skim/Download/Papers/2005/WS1305SK.pdf},
year = 2005
}