Papers by Zhufeng Pan
Improving Open-Domain Dialogue Systems via Multi-Turn Incomplete Utterance Restoration (D19-1)
Copied to clipboard
| Challenge: | Experimental results show that restoring incomplete utterances from context improves the performance of open-domain dialogue systems. |
| Approach: | They propose to use a dataset to restore incomplete utterances from context . they propose to pick and combine the data to restore the incomplete . |
| Outcome: | The proposed model significantly boosts response quality of open-domain dialogue systems. |
Who Blames or Endorses Whom? Entity-to-Entity Directed Sentiment Extraction in News Text (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for sentiment analysis do not consider direction of sentiments between political entities. |
| Approach: | They propose a novel task of identifying directed sentiment relationship between political entities from a given news document. |
| Outcome: | The proposed method is useful for social science research questions in the 2016 election and COVID-19. |