Papers by Ting-Wei Wu
A Label-Aware BERT Attention Network for Zero-Shot Multi-Intent Detection in Spoken Language Understanding (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing systems for speech-based dialogs have found the inadequacy of relying on simple classification techniques to accomplish the automation task. |
| Approach: | They propose a Label-Aware BERT Attention Network (LABAN) for zero-shot multi-intent detection by encoding input utterances with BERT and building a label embedded space by considering embedded semantics in intent labels. |
| Outcome: | The proposed approach can detect many unseen intent labels correctly on a few/zero-shot setting, and achieves state-of-the-art performance on five multi-intent datasets in normal cases. |
Towards Zero-Shot Multilingual Transfer for Code-Switched Responses (2023.acl-long)
Copied to clipboard
| Challenge: | Recent task-oriented dialog systems have had great success building English-based personal assistants, but extending these systems to a global audience may take tremendous efforts. |
| Approach: | They propose a framework that allows for efficient transfer by learning task-specific representations and encapsulating source and target language representations. |
| Outcome: | The proposed framework is able to successfully transfer language knowledge even when the target language corpus is limited. |
Infusing Context and Knowledge Awareness in Multi-turn Dialog Understanding (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing work on multi-turn dialog understanding does not model multi-turned dynamics, instead leaving them for updating dialog states only. |
| Approach: | They propose to equip a BERT-based framework with knowledge and context awareness to model multi-turn dialog dynamics by detecting intents and slots within each user utterance. |
| Outcome: | The proposed framework can detect intents and slots within a dialog and extract key slot information as 'semantic frames' however, humans usually associate relevant background knowledge with the current dialog contexts to better illustrate slot semantics revealed from word connotations . |