Generative Sentiment Analysis via Latent Category Distribution and Constrained Decoding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929444514430976 |
|---|---|
| author | Zhou, Jun Yu, Dongyang Aziz, Kamran Su, Fangfang Zhang, Qing Li, Fei Ji, Donghong |
| author_facet | Zhou, Jun Yu, Dongyang Aziz, Kamran Su, Fangfang Zhang, Qing Li, Fei Ji, Donghong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_21560 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generative Sentiment Analysis via Latent Category Distribution and Constrained Decoding Zhou, Jun Yu, Dongyang Aziz, Kamran Su, Fangfang Zhang, Qing Li, Fei Ji, Donghong Computation and Language Artificial Intelligence 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. |
| title | Generative Sentiment Analysis via Latent Category Distribution and Constrained Decoding |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2407.21560 |