Generative Sentiment Analysis via Latent Category Distribution and Constrained Decoding

TL;DR

This paper presents a generative model for fine-grained sentiment analysis that incorporates latent category distributions and constrained decoding to improve sequence generation and handle category overlap and structural patterns.

Contribution

It introduces a novel generative sentiment analysis approach using latent category variables and constrained decoding, addressing semantic overlap and structural pattern challenges.

Findings

Significant performance improvements on Restaurant-ACOS and Laptop-ACOS datasets.

Effective handling of category overlap and structural patterns.

Validation through ablation experiments confirms the model's components.

Abstract

Fine-grained sentiment analysis involves extracting and organizing sentiment elements from textual data. However, existing approaches often overlook issues of category semantic inclusion and overlap, as well as inherent structural patterns within the target sequence. This study introduces a generative sentiment analysis model. To address the challenges related to category semantic inclusion and overlap, a latent category distribution variable is introduced. By reconstructing the input of a variational autoencoder, the model learns the intensity of the relationship between categories and text, thereby improving sequence generation. Additionally, a trie data structure and constrained decoding strategy are utilized to exploit structural patterns, which in turn reduces the search space and regularizes the generation process. Experimental results on the Restaurant-ACOS and Laptop-ACOS datasets demonstrate a significant performance improvement compared to baseline models. Ablation experiments further confirm the effectiveness of latent category distribution and constrained decoding strategy.