TY - GEN
T1 - Investigating LSTMs for joint extraction of opinion entities and relations
AU - Katiyar, Arzoo
AU - Cardie, Claire
N1 - Publisher Copyright:
© 2016 Association for Computational Linguistics.
PY - 2016
Y1 - 2016
N2 - We investigate the use of deep bidirectional LSTMs for joint extraction of opinion entities and the IS-FROM and IS-ABOUT relations that connect them - the first such attempt using a deep learning approach. Perhaps surprisingly, we find that standard LSTMs are not competitive with a state-of-the-art CRF+ILP joint inference approach (Yang and Cardie, 2013) to opinion entities extraction, performing below even the standalone sequencetagging CRF. Incorporating sentence-level and a novel relation-level optimization, however, allows the LSTM to identify opinion relations and to perform within 1-3% of the state-of-the-art joint model for opinion entities and the IS-FROM relation; and to perform as well as the state-of-theart for the IS-ABOUT relation - all without access to opinion lexicons, parsers and other preprocessing components required for the feature-rich CRF+ILP approach.
AB - We investigate the use of deep bidirectional LSTMs for joint extraction of opinion entities and the IS-FROM and IS-ABOUT relations that connect them - the first such attempt using a deep learning approach. Perhaps surprisingly, we find that standard LSTMs are not competitive with a state-of-the-art CRF+ILP joint inference approach (Yang and Cardie, 2013) to opinion entities extraction, performing below even the standalone sequencetagging CRF. Incorporating sentence-level and a novel relation-level optimization, however, allows the LSTM to identify opinion relations and to perform within 1-3% of the state-of-the-art joint model for opinion entities and the IS-FROM relation; and to perform as well as the state-of-theart for the IS-ABOUT relation - all without access to opinion lexicons, parsers and other preprocessing components required for the feature-rich CRF+ILP approach.
UR - http://www.scopus.com/inward/record.url?scp=85011878882&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85011878882&partnerID=8YFLogxK
U2 - 10.18653/v1/p16-1087
DO - 10.18653/v1/p16-1087
M3 - Conference contribution
AN - SCOPUS:85011878882
T3 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
SP - 919
EP - 929
BT - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
PB - Association for Computational Linguistics (ACL)
T2 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
Y2 - 7 August 2016 through 12 August 2016
ER -