Papers by Helen Chen
LexSubCon: Integrating Knowledge from Lexical Resources into Contextual Embeddings for Lexical Substitution (2022.acl-long)
Copied to clipboard
| Challenge: | Lexical substitution is the task of generating meaningful substitutes for a word in a given textual context. |
| Approach: | They propose an end-to-end lexical substitution framework based on contextual embedding models that can identify highly-accurate substitute candidates. |
| Outcome: | The proposed framework outperforms state-of-the-art embedding models on LS07 and CoInCo benchmark datasets by at least 2% over existing embeddable models. |
UmlsBERT: Clinical Domain Knowledge Augmentation of Contextual Embeddings Using the Unified Medical Language System Metathesaurus (2021.naacl-main)
Copied to clipboard
| Challenge: | Contextual word embedding models do not take into account structured expert domain knowledge from a knowledge base. |
| Approach: | They propose a contextual embedding model that integrates domain knowledge during the pre-training process via a novel knowledge augmentation strategy. |
| Outcome: | The proposed model outperforms existing domain-specific models on common named-entity recognition (NER) and clinical natural language inference tasks. |
Unsupervised Multi-scale Expressive Speaking Style Modeling with Hierarchical Context Information for Audiobook Speech Synthesis (2022.coling-1)
Copied to clipboard
| Challenge: | a recent study has shown that expressiveness of audiobooks is limited by the averaged global-scale speaking style representation. |
| Approach: | They propose an unsupervised multi-scale context-sensitive text-to-speech model for audiobooks . they use hierarchical context encoder to predict global-scale contextual style embeddings . |
| Outcome: | The proposed model outperforms existing models on a real-world Mandarin audio dataset. |
Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates (2025.emnlp-main)
Copied to clipboard
Hy Dang, Tianyi Liu, Zhuofeng Wu, Jingfeng Yang, Haoming Jiang, Tao Yang, Pei Chen, Zhengyang Wang, Helen Wang, Huasheng Li, Bing Yin, Meng Jiang
| Challenge: | Large language models (LLMs) have strong reasoning and tool-use capabilities, yet fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent. |
| Approach: | They propose a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function calls. |
| Outcome: | The proposed framework reduces tool-use errors and improves interpretability and transparency of tool-using agents. |