Improving Aspect-Level Sentiment Analysis with Aspect Extraction

by   Navonil Majumder, et al.
Edinburgh Napier University
Instituto Politécnico Nacional
Singapore University of Technology and Design
Carnegie Mellon University

Aspect-based sentiment analysis (ABSA), a popular research area in NLP has two distinct parts – aspect extraction (AE) and labeling the aspects with sentiment polarity (ALSA). Although distinct, these two tasks are highly correlated. The work primarily hypothesize that transferring knowledge from a pre-trained AE model can benefit the performance of ALSA models. Based on this hypothesis, word embeddings are obtained during AE and subsequently, feed that to the ALSA model. Empirically, this work show that the added information significantly improves the performance of three different baseline ALSA models on two distinct domains. This improvement also translates well across domains between AE and ALSA tasks.


INSIGHT-1 at SemEval-2016 Task 5: Deep Learning for Multilingual Aspect-based Sentiment Analysis

This paper describes our deep learning-based approach to multilingual as...

Simple Unsupervised Similarity-Based Aspect Extraction

In the context of sentiment analysis, there has been growing interest in...

Interventional Aspect-Based Sentiment Analysis

Recent neural-based aspect-based sentiment analysis approaches, though a...

GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis

In this paper, we focus on the imbalance issue, which is rarely studied ...

Towards Robust Aspect-based Sentiment Analysis through Non-counterfactual Augmentations

While state-of-the-art NLP models have demonstrated excellent performanc...

Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation

Recently, aspect sentiment quad prediction (ASQP) has become a popular t...

Please sign up or login with your details

Forgot password? Click here to reset