Discriminative Models Can Still Outperform Generative Models in Aspect Based Sentiment Analysis

06/06/2022
by   Dhruv Mullick, et al.
4

Aspect-based Sentiment Analysis (ABSA) helps to explain customers' opinions towards products and services. In the past, ABSA models were discriminative, but more recently generative models have been used to generate aspects and polarities directly from text. In contrast, discriminative models commonly first select aspects from the text, and then classify the aspect's polarity. Previous results showed that generative models outperform discriminative models on several English ABSA datasets. Here, we evaluate and contrast two state-of-the-art discriminative and generative models in several settings: cross-lingual, cross-domain, and cross-lingual and domain, to understand generalizability in settings other than English mono-lingual in-domain. Our more thorough evaluation shows that, contrary to previous studies, discriminative models can still outperform generative models in almost all settings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/15/2022

Linear Transformations for Cross-lingual Sentiment Analysis

This paper deals with cross-lingual sentiment analysis in Czech, English...
research
07/06/2017

Cross-Lingual Sentiment Analysis Without (Good) Translation

Current approaches to cross-lingual sentiment analysis try to leverage t...
research
05/28/2019

A Cross-Domain Transferable Neural Coherence Model

Coherence is an important aspect of text quality and is crucial for ensu...
research
06/13/2019

On the Effect of Word Order on Cross-lingual Sentiment Analysis

Current state-of-the-art models for sentiment analysis make use of word ...
research
04/02/2022

CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment Analysis

As an extensive research in the field of Natural language processing (NL...
research
03/06/2017

Generative and Discriminative Text Classification with Recurrent Neural Networks

We empirically characterize the performance of discriminative and genera...
research
09/19/2011

Learning Discriminative Metrics via Generative Models and Kernel Learning

Metrics specifying distances between data points can be learned in a dis...

Please sign up or login with your details

Forgot password? Click here to reset