Papers with incremental text processing
The Referential Reader: A Recurrent Entity Network for Anaphora Resolution (P19-1)
Copied to clipboard
| Challenge: | Existing methods for storing and accessing entity mentions are expensive and implausible for human readers. |
| Approach: | They propose a method for storing and accessing entity mentions during online text processing. |
| Outcome: | The proposed model performs well on a dataset of pronoun-name anaphora. |