Papers by Andrey Bout
GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding (2023.acl-long)
Copied to clipboard
| Challenge: | grammatical error correction is an important NLP task that is usually solved with autoregressive sequence-to-sequence models. |
| Approach: | They propose a non-autoregressive approach to grammatical error correction that decouples a permutation network and a decoder network that fills in specific tokens. |
| Outcome: | The proposed approach improves over previously known non-autoregressive methods and reaches the level of autoregressive approaches that do not use language-specific synthetic data generation methods. |
Efficient Grammatical Error Correction Via Multi-Task Training and Optimized Training Schedule (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent research has focused on using synthetic data for grammatical error correction . lack of annotated training data hinders progress in the field . |
| Approach: | They propose auxiliary tasks that exploit alignment between original and corrected sentences . they propose a sequence-to-sequence problem and perform multi-task training . |
| Outcome: | The proposed auxiliary tasks outperform the best models with a BART-based model on 11B parameters. |
Toolken+: Improving LLM Tool Usage with Reranking and a Reject Option (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Using ToolkenGPT, tool learning paradigms lack flexibility and cannot generalize to unseen tools. |
| Approach: | They propose a tool learning paradigm that reranks top-k tools and generates a vocabulary token if REJECT is ranked first. |
| Outcome: | The proposed toolkenGPT model performs well on multistep numerical reasoning and tool selection tasks. |