mbrs: A Library for Minimum Bayes Risk 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_ | 1866929551304556544 |
|---|---|
| author | Deguchi, Hiroyuki Sakai, Yusuke Kamigaito, Hidetaka Watanabe, Taro |
| author_facet | Deguchi, Hiroyuki Sakai, Yusuke Kamigaito, Hidetaka Watanabe, Taro |
| contents | Minimum Bayes risk (MBR) decoding is a decision rule of text generation tasks that outperforms conventional maximum a posterior (MAP) decoding using beam search by selecting high-quality outputs based on a utility function rather than those with high-probability. Typically, it finds the most suitable hypothesis from the set of hypotheses under the sampled pseudo-references. mbrs is a library of MBR decoding, which can flexibly combine various metrics, alternative expectation estimations, and algorithmic variants. It is designed with a focus on speed measurement and calling count of code blocks, transparency, reproducibility, and extensibility, which are essential for researchers and developers. We published our mbrs as an MIT-licensed open-source project, and the code is available on GitHub.
GitHub: https://github.com/naist-nlp/mbrs |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04167 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | mbrs: A Library for Minimum Bayes Risk Decoding Deguchi, Hiroyuki Sakai, Yusuke Kamigaito, Hidetaka Watanabe, Taro Computation and Language Minimum Bayes risk (MBR) decoding is a decision rule of text generation tasks that outperforms conventional maximum a posterior (MAP) decoding using beam search by selecting high-quality outputs based on a utility function rather than those with high-probability. Typically, it finds the most suitable hypothesis from the set of hypotheses under the sampled pseudo-references. mbrs is a library of MBR decoding, which can flexibly combine various metrics, alternative expectation estimations, and algorithmic variants. It is designed with a focus on speed measurement and calling count of code blocks, transparency, reproducibility, and extensibility, which are essential for researchers and developers. We published our mbrs as an MIT-licensed open-source project, and the code is available on GitHub. GitHub: https://github.com/naist-nlp/mbrs |
| title | mbrs: A Library for Minimum Bayes Risk Decoding |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.04167 |