Zero-Shot Entity Linking by Reading Entity Descriptions
Lajanugen Logeswarana b, Ming-Wei Changa c, Kenton Leea c, Kristina Toutanovaa c, Jacob Devlina c, Honglak Leea b
- aUniversity of Michigan , Google Research
- bUniversity of Michigan–Ann Arbor, Ann Arbor, United States
- cGoogle (United States), Mountain View, United States
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
We present the zero-shot entity linking task, where mentions must be linked to unseen entities without in-domain labeled data.The goal is to enable robust transfer to highly specialized domains, and so no metadata or alias tables are assumed.In this setting, entities are only identified by text descriptions, and models must rely strictly on language understanding to resolve the new entities.First, we show that strong reading comprehension models pre-trained on large unlabeled data can be used to generalize to unseen entities.Second, we propose a simple and effective adaptive pre-training strategy, which we term domainadaptive pre-training (DAP), to address the domain shift problem associated with linking unseen entities in a new domain.We present experiments on a new dataset that we construct for this task and show that DAP improves over strong pre-training baselines, including BERT.
TL;DRIt is shown that strong reading comprehension models pre-trained on large unlabeled data can be used to generalize to unseen entities and proposed domain-adaptive pre-training (DAP) is proposed to address the domain shift problem associated with linking unseen entities in a new domain. (Semantic Scholar)