Papers by Duong Le
Improved Instruction Ordering in Recipe-Grounded Conversation (2023.acl-long)
Copied to clipboard
| Challenge: | In this paper, we explore the task of instructional dialogue and focus on the cooking domain. |
| Approach: | They propose to explore two auxiliary subtasks to support response generation with improved instruction grounding by incorporating user intent and instruction state information into the model. |
| Outcome: | The proposed model lacks understanding of user intent and inability to track instruction state (i.e., which step was last instructed) incorporating user intent information helps the response generation model mitigate the incorrect order issue. |
Fine-Grained Event Trigger Detection (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for Event Detection (ED) focus on a limited set of event types . existing datasets for ED focus on only 33 event types while the number of events in the TAC KBP dataset is 38. |
| Approach: | They propose to transform Word Sense Disambiguation's Semcor dataset into a large and high-quality dataset for ED. |
| Outcome: | The proposed method transforms the Semcor dataset for Word Sense Disambiguation into a large and high-quality dataset for FED. |
ChatHF: Collecting Rich Human Feedback from Real-time Conversations (2024.emnlp-demo)
Copied to clipboard
| Challenge: | We present an interactive framework for chatbot evaluation that integrates configurable annotation within a chat interface. |
| Approach: | They propose an interactive framework for chatbot evaluation that integrates configurable annotation within a chat interface. |
| Outcome: | The proposed framework supports fine-grained error detection and human evaluation at the same time. |