Papers by Lesheng Jin
Neural Graph Matching Networks for Chinese Short Text Matching (2020.acl-main)
Copied to clipboard
| Challenge: | Chinese word segmentation can be erroneous, ambiguous or inconsistent, causing performance problems. |
| Approach: | They propose a sentence matching framework that uses paired word lattices as input instead of a character sequence. |
| Outcome: | The proposed framework outperforms the state-of-the-art short text matching models on two Chinese datasets. |
VeriLocc: End-to-End Cross-Architecture Register Allocation via LLM (2025.emnlp-main)
Copied to clipboard
| Challenge: | Modern GPUs evolve rapidly, yet production compilers still rely on hand-crafted register allocation heuristics that require substantial re-tuning for each hardware generation. |
| Approach: | They propose a framework that combines large language models with compiler techniques to enable generalizable and verifiable register allocation across GPU architectures. |
| Outcome: | The framework outperforms expert-tuned libraries on matrix multiplication and multi-head attention and a verifier-guided regeneration loop to ensure correctness. |
WeDef: Weakly Supervised Backdoor Defense for Text Classification (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing backdoor defense methods are only effective for limited trigger types . Existing methods only work against certain types of triggers . |
| Approach: | They propose a weakly supervised backdoor defense framework WeDef to defend different trigger types at once . they define reliability of samples based on whether predictions agree with their labels . |
| Outcome: | The proposed framework outperforms existing backdoor defense methods against popular trigger-based attacks. |