Papers with WMT19
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (P19-1)
Copied to clipboard
| Challenge: | ACL 2019 received a record number of papers, close to three thousand, a sharp increase . aaron safina: organizers have to adapt quickly to numbers that surpass previous estimates . but he says conference needs to be large but should be enjoyable for all, retain original spirit . |
| Approach: | a record number of papers were submitted for the 2019 ACL conference . aaron ramirez: organizers worked hard to ensure a program that suits most participants . the conference will feature 9 tutorials, 18 one-day workshops and a varied program, he says . |
| Outcome: | a record number of papers received at the 2019 ACL, says cnn's nigel tsang . ttsong: organizers worked hard and professionally to make conference enjoyable for all . the conference will feature 9 tutorials, 18 one-day workshops, and the fourth conference on machine translation . |
Relational Memory-Augmented Language Models (2022.tacl-1)
Copied to clipboard
| Challenge: | Existing language models rely on word correlation and are difficult to interpret . existing models often lack explicit representations for such information . |
| Approach: | They propose a memory-augmented approach to condition autoregressive language models on knowledge graphs. |
| Outcome: | The proposed model improves perplexity and bits per character in an autoregressive language model . it is complementary to token-based memory and enables causal interventions . |
Fixing Rogue Memorization in Many-to-One Multilingual Translators of Extremely-Low-Resource Languages by Rephrasing Training Samples (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing fine-tuning of large high-resource language models into multilingual machine translators is difficult for extremely lowresource languages. |
| Approach: | They propose to fine-tune large high-resource language models into multilingual machine translators for extremely-lowresource languages such as endangered Indigenous languages. |
| Outcome: | The proposed model halls are reformulated to improve translation accuracy and improve translation quality. |
Are we Estimating or Guesstimating Translation Quality? (2020.acl-main)
Copied to clipboard
| Challenge: | A carefully engineered ensemble of pre-trained multilingual language models won the QE shared task at WMT19. |
| Approach: | They propose to use pre-trained multilingual language models to train quality estimation for machine translation. |
| Outcome: | A carefully engineered ensemble of pre-trained language models wins the QE shared task at WMT19. |