Papers by Chia-Jung Lee
Long Document Ranking with Query-Directed Sparse Transformer (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to document ranking require long documents to be broken to fit in pretrained models. |
| Approach: | They propose a Query-Directed Sparse attention model that induces IR-axiomatic structures in transformer self-attention. |
| Outcome: | The proposed model enforces the principle properties desired in ranking while also enjoying efficiency from sparsity. |
Incorporating Behavioral Hypotheses for Query Generation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Prior work has focused on extending standard Seq2Seq models but literature often leaves out the influence of clickthrough actions. |
| Approach: | They propose a generic encoder-decoder Transformer framework to generate query suggestions from user inputs. |
| Outcome: | The proposed approach improves top-k word error rate and Bert F1 score compared to a recent BART model. |