Papers by Zhengxiang Shi
Rethinking Semi-supervised Learning with Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Semi-supervised learning (SSL) is a popular setting to make use of unlabelled data . Currently, there are two popular approaches to make effective use of the unlabelled datasets . |
| Approach: | They compare semi-supervised learning (SSL) and task-adaptive pre-training (TAPT) they find TAPT is a stronger and more robust SSL learner, even when using just a few hundred unlabelled samples . |
| Outcome: | The proposed methods improve model performance across different NLP tasks and data sizes. |
Learning to Execute Actions or Ask Clarification Questions (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing work on Minecraft Corpus Dataset only learns to execute instructions neglecting the importance of asking for clarifications. |
| Approach: | They propose to annotate all builder utterances into eight types, including clarification questions, and propose a builder agent model capable of determining when to ask or execute instructions. |
| Outcome: | The proposed model outperforms existing models on the collaborative building task with a substantial improvement. |
Lexical Entrainment for Conversational Systems (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Conversational agents are expected to possess human-like features such as lexical entrainment (LE). |
| Approach: | They propose a dataset and a measure for LE for conversational systems to explicitly integrate LE into conversational system. |
| Outcome: | The proposed dataset and a measure for LE for conversational systems address this human-like phenomenon. |