A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis

04/11/2022
by   Ehsan Hosseini-Asl, et al.
0

Sentiment analysis is an important task in natural language processing. In recent works, pre-trained language models are often used to achieve state-of-the-art results, especially when training data is scarce. It is common to fine-tune on the downstream task, usually by adding task-specific layers on top of the model. In this paper, we focus on aspect-based sentiment analysis, which involves extracting aspect term, category, and predicting their corresponding polarities. In particular, we are interested in few-shot settings. We propose to reformulate the extraction and prediction tasks into the sequence generation task, using a generative language model with unidirectional attention (GPT2 is used unless stated otherwise). This way, the model learns to accomplish the tasks via language generation without the need of training task-specific layers. Our evaluation results on the single-task polarity prediction show that our approach outperforms the previous state-of-the-art (based on BERT) on average performance by a large margins in few-shot and full-shot settings. More importantly, our generative approach significantly reduces the model variance caused by low-resource data. We further demonstrate that the proposed generative language model can handle joint and multi-task settings, unlike previous work. We observe that the proposed sequence generation method achieves further improved performances on polarity prediction when the model is trained via joint and multi-task settings. Further evaluation on similar sentiment analysis datasets, SST-2, SST- and OOS intent detection validates the superiority and noise robustness of generative language model in few-shot settings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/14/2021

Solving Aspect Category Sentiment Analysis as a Text Generation Task

Aspect category sentiment analysis has attracted increasing research att...
research
10/19/2022

Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation

Recently, aspect sentiment quad prediction (ASQP) has become a popular t...
research
06/13/2020

Transferring Monolingual Model to Low-Resource Language: The Case of Tigrinya

In recent years, transformer models have achieved great success in natur...
research
05/19/2023

A Weak Supervision Approach for Few-Shot Aspect Based Sentiment

We explore how weak supervision on abundant unlabeled data can be levera...
research
12/17/2019

A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction

Aspect-based sentiment analysis (ABSA) task is a multi-grained task of n...
research
06/01/2023

Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction

Recently, aspect sentiment quad prediction has received widespread atten...
research
05/15/2022

Adaptive Prompt Learning-based Few-Shot Sentiment Analysis

In the field of natural language processing, sentiment analysis via deep...

Please sign up or login with your details

Forgot password? Click here to reset