Papers by Parth Diwanji
Lin: Unsupervised Extraction of Tasks from Textual Communication (2020.coling-main)
Copied to clipboard
| Challenge: | Identifying tasks from emails and chats is a hallmark of collaborative communication . state-of-the-art approaches for task identification rely on large annotated datasets . |
| Approach: | They propose an unsupervised approach to identifying tasks that leverages dependency parsing and VerbNet. |
| Outcome: | The proposed approach yields comparable or more accurate results than supervised models on unseen domains. |