Deep Multi-Task Learning for Aspect Term Extraction with Memory Interaction
Refereed conference paper presented and published in conference proceedings

Altmetrics Information

Other information
AbstractWe propose a novel LSTM-based deep multi-task learning framework for aspect term extraction from user review sentences. Two LSTMs equipped with extended memories and neural memory operations are designed for jointly handling the extraction tasks of aspects and opinions via memory interactions. Sentimental sentence constraint is also added for more accurate prediction via another LSTM. Experiment results over two benchmark datasets demonstrate the effectiveness of our framework.
All Author(s) ListXin LI, Wai LAM
Name of ConferenceConference on Empirical Methods in Natural Language Processing (EMNLP 2017)
Start Date of Conference07/09/2017
End Date of Conference11/09/2017
Place of ConferenceCopenhagen
Country/Region of ConferenceDenmark
Proceedings TitleProceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
PublisherAssociation for Computational Linguistics
Pages2886 - 2892
LanguagesEnglish-United States

Last updated on 2022-12-01 at 23:53