← Search

Tuan-Dung Cao

2 accepted papers

2023

A Self-enhancement Multitask Framework for Unsupervised Aspect Category Detection

EMNLP 2023long main

Our work addresses the problem of unsupervised Aspect Category Detection using a small set of seed words. Recent works have focused on learning embedding spaces for seed words and sentences to establish similarities between sentences and aspects. However, aspect representations are limited by the qu…

Cited by 0SourceScholar
2021

An Uncertainty-Aware Encoder for Aspect Detection

EMNLP 2021finding

Aspect detection is a fundamental task in opinion mining. Previous works use seed words either as priors of topic models, as anchors to guide the learning of aspects, or as features of aspect classifiers. This paper presents a novel weakly-supervised method to exploit seed words for aspect detection…