DeepAI AI Chat
Log In Sign Up

A Weak Supervision Approach for Few-Shot Aspect Based Sentiment

by   Robert Vacareanu, et al.
The University of Arizona

We explore how weak supervision on abundant unlabeled data can be leveraged to improve few-shot performance in aspect-based sentiment analysis (ABSA) tasks. We propose a pipeline approach to construct a noisy ABSA dataset, and we use it to adapt a pre-trained sequence-to-sequence model to the ABSA tasks. We test the resulting model on three widely used ABSA datasets, before and after fine-tuning. Our proposed method preserves the full fine-tuning performance while showing significant improvements (15.84 learning scenario for the harder tasks. In zero-shot (i.e., without fine-tuning), our method outperforms the previous state of the art on the aspect extraction sentiment classification (AESC) task and is, additionally, capable of performing the harder aspect sentiment triplet extraction (ASTE) task.


Zero-Shot Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) typically requires in-domain anno...

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

Sentiment analysis is an important task in natural language processing. ...

Emotions are Subtle: Learning Sentiment Based Text Representations Using Contrastive Learning

Contrastive learning techniques have been widely used in the field of co...

Ensemble Making Few-Shot Learning Stronger

Few-shot learning has been proposed and rapidly emerging as a viable mea...

Better Handling Coreference Resolution in Aspect Level Sentiment Classification by Fine-Tuning Language Models

Customer feedback is invaluable to companies as they refine their produc...

Learning Matching Models with Weak Supervision for Response Selection in Retrieval-based Chatbots

We propose a method that can leverage unlabeled data to learn a matching...