TEncDM: Understanding the Properties of the Diffusion Model in the Space of Language Model Encodings
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909507041361920 |
|---|---|
| author | Shabalin, Alexander Meshchaninov, Viacheslav Chimbulatov, Egor Lapikov, Vladislav Kim, Roman Bartosh, Grigory Molchanov, Dmitry Markov, Sergey Vetrov, Dmitry |
| author_facet | Shabalin, Alexander Meshchaninov, Viacheslav Chimbulatov, Egor Lapikov, Vladislav Kim, Roman Bartosh, Grigory Molchanov, Dmitry Markov, Sergey Vetrov, Dmitry |
| contents | This paper presents the Text Encoding Diffusion Model (TEncDM), a novel approach to diffusion modeling that operates in the space of pre-trained language model encodings. In contrast to traditionally used embeddings, encodings integrate contextual information. In our approach, we also employ a transformer-based decoder, specifically designed to incorporate context in the token prediction process. We conduct a comprehensive examination of the influence of the encoder, decoder, noise scheduler, and self-conditioning on zero-shot generation. Furthermore, we compare TEncDM with previous approaches on three conditional text generation tasks: QQP, XSum, and Wiki-Auto. The results show that TEncDM exhibits superior performance compared to existing non-autoregressive diffusion models. Our code is available at https://github.com/M0RJIQUE/tencdm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_19097 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TEncDM: Understanding the Properties of the Diffusion Model in the Space of Language Model Encodings Shabalin, Alexander Meshchaninov, Viacheslav Chimbulatov, Egor Lapikov, Vladislav Kim, Roman Bartosh, Grigory Molchanov, Dmitry Markov, Sergey Vetrov, Dmitry Computation and Language I.2; I.7 This paper presents the Text Encoding Diffusion Model (TEncDM), a novel approach to diffusion modeling that operates in the space of pre-trained language model encodings. In contrast to traditionally used embeddings, encodings integrate contextual information. In our approach, we also employ a transformer-based decoder, specifically designed to incorporate context in the token prediction process. We conduct a comprehensive examination of the influence of the encoder, decoder, noise scheduler, and self-conditioning on zero-shot generation. Furthermore, we compare TEncDM with previous approaches on three conditional text generation tasks: QQP, XSum, and Wiki-Auto. The results show that TEncDM exhibits superior performance compared to existing non-autoregressive diffusion models. Our code is available at https://github.com/M0RJIQUE/tencdm. |
| title | TEncDM: Understanding the Properties of the Diffusion Model in the Space of Language Model Encodings |
| topic | Computation and Language I.2; I.7 |
| url | https://arxiv.org/abs/2402.19097 |