Papers by Lisa Jin
Hooks in the Headline: Learning to Generate Headlines with Controlled Styles (2020.acl-main)
Copied to clipboard
| Challenge: | Current summarization systems only produce plain, factual headlines, far from the practical needs for exposure and memorableness of the articles. |
| Approach: | They propose a task to generate relevant headlines with three style options . they propose combining summarization and reconstruction tasks into a multitasking framework . |
| Outcome: | The proposed method outperforms the state-of-the-art summarization model by 9.68% . it can generate relevant, fluent headlines with humor, romance and clickbait . |
Rewarding Semantic Similarity under Optimized Alignments for AMR-to-Text Generation (2022.acl-short)
Copied to clipboard
| Challenge: | Automatic evaluation metrics score natural language generation systems based on how well they lexically align to humanannotated references. |
| Approach: | They propose to replace greedy alignments in BERTScore with optimized ones that replace the n-gram matching BERTAcore metrics with a token embedding to prevent domain mismatch. |
| Outcome: | The proposed metrics outperform cross-entropy and BLEU reward baselines on AMR-to-text generation. |
Generalized Shortest-Paths Encoders for AMR-to-Text Generation (2020.coling-main)
Copied to clipboard
| Challenge: | a recent effort to encode graphs with gated convolutions provides local context, but distance messages travel is limited by number of encoder propagation steps. |
| Approach: | They propose to use generalized shortest-paths to train a graph encoder to learn shortest paths . they show that path diversity affects performance across levels of AMR connectivity . |
| Outcome: | The proposed model achieves a 1.4 BLEU and 1.8 chrF++ margin over a baseline model that encodes only pairwise-unique shortest paths. |