Papers by Weixian Waylon Li
BERT Is Not The Count: Learning to Match Mathematical Statements with Proofs (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing work on mathematical article analysis uses natural language processing to solve complex mathematical articles. |
| Approach: | They propose a bilinear similarity model and two decoding methods to match statements to proofs effectively. |
| Outcome: | The proposed model matches proofs to statements without being aware of proofs, but it follows a relatively shallow symbolic analysis and matching to achieve that performance. |