Generative Sentiment Analysis via Latent Category Distribution and Constrained Decoding
This work solves the problem of improving accuracy in fine-grained sentiment analysis for applications like review analysis, though it is incremental as it builds on existing generative and constrained decoding methods.
The paper tackled fine-grained sentiment analysis by addressing category semantic inclusion/overlap and structural patterns, introducing a generative model with latent category distribution and constrained decoding that achieved significant performance improvements on Restaurant-ACOS and Laptop-ACOS datasets.
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.