-
- https://arxiv.org/abs/2104.05336
- 2021
ビームサーチは、自動回帰型機械翻訳モデルをデコードするための最も一般的な手法です。
ビームサーチはBLEUの点では一貫した改善をもたらしますが、モデルの尤度が高い出力を見つけることにしか関心がないため、実務者が気にする最終的なメトリックやスコアには不可知論的です。
我々の目的は、ビーム探索をより強力なメ…
e4exp updated
3 years ago
-
XNLI: Evaluating Cross-lingual Sentence Representations
Alexis Conneau, Guillaume Lample, Ruty Rinott, Adina Williams, Samuel R. Bowman, Holger Schwenk, Veselin Stoyanov
EMNLP 2018
https://arxi…
-
语义角色标注(SRL)是自然语言理解的重要组成部分,近年来学术界对其进行了大量的研究。当资源丰富的语言(如En english)使用大规模语料库时,监督方法取得了令人印象深刻的性能。而对于没有注释SRL数据集的低资源语言,获得具有竞争力的性能仍然是一个挑战。跨语言的SRL是解决这一问题的一种很有前途的方法,它借助于模型转换和注释投影技术取得了很大的进展。本文提出了一种新的基于语料库翻译的方法,即从…
-
I saw the great idea for combined models here:
https://stanfordnlp.github.io/stanza/combined_models.html
Is there a process to request more of these? Specifically I was thinking of Hebrew right …
-
https://github.com/tmbdev/teaching-dca
Thomas_Breuel 开授的课程
1.转换成pdf
2.pdf转换成html
3.翻译
-
## Keyword: super resolution
There is no result
## Keyword: gan
### Towards Discovery and Attribution of Open-world GAN Generated Images
- **Authors:** Sharath Girish, Saksham Suri, Saketh Rambhatla…
-
User workflow research, needs analysis and design of the NLP audio recording, transcription and translation feature
-
```bash
python s2s_pipeline.py --local_mac_optimal_settings
```
It seems this is done running setup and ready for me to start speaking? My mic is set to MacBook Pro Microphone. I say somethin…
-
The tokenization of strings like _14th_ with the ICU tokenizer is affected by the character that comes before preceeding whitespace.
For example, _x 14th_ is tokenized as x | 14th; _ァ 14th_ is tokeni…
-