Improving Citation Text Generation: Overcoming Limitations in Length Control
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911963667234816 |
|---|---|
| author | Mandal, Biswadip Li, Xiangci Ouyang, Jessica |
| author_facet | Mandal, Biswadip Li, Xiangci Ouyang, Jessica |
| contents | A key challenge in citation text generation is that the length of generated text often differs from the length of the target, lowering the quality of the generation. While prior works have investigated length-controlled generation, their effectiveness depends on knowing the appropriate generation length. In this work, we present an in-depth study of the limitations of predicting scientific citation text length and explore the use of heuristic estimates of desired length. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14997 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Citation Text Generation: Overcoming Limitations in Length Control Mandal, Biswadip Li, Xiangci Ouyang, Jessica Digital Libraries Computation and Language A key challenge in citation text generation is that the length of generated text often differs from the length of the target, lowering the quality of the generation. While prior works have investigated length-controlled generation, their effectiveness depends on knowing the appropriate generation length. In this work, we present an in-depth study of the limitations of predicting scientific citation text length and explore the use of heuristic estimates of desired length. |
| title | Improving Citation Text Generation: Overcoming Limitations in Length Control |
| topic | Digital Libraries Computation and Language |
| url | https://arxiv.org/abs/2407.14997 |