A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation
Uloženo v:
| Název: | A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation |
|---|---|
| Autoři: | Liqiang Xiao, Wenqing Chen, Hao He, Yaohui Jin, Jidong Tian |
| Zdroj: | Proceedings of the 28th International Conference on Computational Linguistics. :1186-1198 |
| Informace o vydavateli: | International Committee on Computational Linguistics, 2020. |
| Rok vydání: | 2020 |
| Popis: | Paraphrase generation aims to generate semantically consistent sentences with different syntactic realizations. Most of the recent studies rely on the typical encoder-decoder framework where the generation process is deterministic. However, in practice, the ability to generate multiple syntactically different paraphrases is important. Recent work proposed to cooperate variational inference on a target-related latent variable to introduce the diversity. But the latent variable may be contaminated by the semantic information of other unrelated sentences, and in turn, change the conveyed meaning of generated paraphrases. In this paper, we propose a semantically consistent and syntactically variational encoder-decoder framework, which uses adversarial learning to ensure the syntactic latent variable be semantic-free. Moreover, we adopt another discriminator to improve the word-level and sentence-level semantic consistency. So the proposed framework can generate multiple semantically consistent and syntactically different paraphrases. The experiments show that our model outperforms the baseline models on the metrics based on both n-gram matching and semantic similarity, and our model can generate multiple different paraphrases by assembling different syntactic variables. |
| Druh dokumentu: | Article |
| DOI: | 10.18653/v1/2020.coling-main.102 |
| Přístupová URL adresa: | https://www.aclweb.org/anthology/2020.coling-main.102.pdf https://aclanthology.org/2020.coling-main.102/ https://dblp.uni-trier.de/db/conf/coling/coling2020.html#ChenTXHJ20 https://www.aclweb.org/anthology/2020.coling-main.102/ |
| Rights: | CC BY |
| Přístupové číslo: | edsair.doi.dedup.....adf9cec641a3f1bb5cc4c6749a3e3d8c |
| Databáze: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | Paraphrase generation aims to generate semantically consistent sentences with different syntactic realizations. Most of the recent studies rely on the typical encoder-decoder framework where the generation process is deterministic. However, in practice, the ability to generate multiple syntactically different paraphrases is important. Recent work proposed to cooperate variational inference on a target-related latent variable to introduce the diversity. But the latent variable may be contaminated by the semantic information of other unrelated sentences, and in turn, change the conveyed meaning of generated paraphrases. In this paper, we propose a semantically consistent and syntactically variational encoder-decoder framework, which uses adversarial learning to ensure the syntactic latent variable be semantic-free. Moreover, we adopt another discriminator to improve the word-level and sentence-level semantic consistency. So the proposed framework can generate multiple semantically consistent and syntactically different paraphrases. The experiments show that our model outperforms the baseline models on the metrics based on both n-gram matching and semantic similarity, and our model can generate multiple different paraphrases by assembling different syntactic variables. |
|---|---|
| DOI: | 10.18653/v1/2020.coling-main.102 |