Pivot Based Language Modeling for Improved Neural Domain Adaptation

Yftah Ziser, Roi Reichart


Abstract
Representation learning with pivot-based methods and with Neural Networks (NNs) have lead to significant progress in domain adaptation for Natural Language Processing. However, most previous work that follows these approaches does not explicitly exploit the structure of the input text, and its output is most often a single representation vector for the entire text. In this paper we present the Pivot Based Language Model (PBLM), a representation learning model that marries together pivot-based and NN modeling in a structure aware manner. Particularly, our model processes the information in the text with a sequential NN (LSTM) and its output consists of a representation vector for every input word. Unlike most previous representation learning models in domain adaptation, PBLM can naturally feed structure aware text classifiers such as LSTM and CNN. We experiment with the task of cross-domain sentiment classification on 20 domain pairs and show substantial improvements over strong baselines.
Anthology ID:
N18-1112
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1241–1251
Language:
URL:
https://www.aclweb.org/anthology/N18-1112
DOI:
10.18653/v1/N18-1112
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/N18-1112.pdf