About me
I am a Research Assistant working with professor Bryan Hooi at National University of Singapore, where I recently graduated with a bachelor's degree in Computer Science and Mathematics. I am also currently working with professor Hannaneh Hajishirzi and her student Zeqiu Wu at University of Washington.
My research is concentrated on Natural Language Processing (NLP). A more specific area that I am keen to explore is
extending the usage of language models to more general settings.
Previously, I was advised by professor Tat Seng Chua
and professor Lizi Liao at NExT++ Research Center.
I worked on Conversation Disentanglement and Multi-party Response Generation to enable chit-chat agents
to converse properly in multi-party dialogues that involve more than 2 speakers. Solving these tasks is crucial for the
eventual application of chatbots in group chat and forums, where different topics may be discussed in a simultaneous and
interleaved manner.
My current research directions include
• Applying LMs to multi-party settings: In multi-party settings, potentially with preset goals,
different agents can assume different personas and roles, and the relations between the agents can be
collaborative, adversarial, or competitive. There have been exciting works released recently that make use of multiple dialogue
agents for settings such as problem-solving
and text adventures. Exploration is needed for more complicated scenarios.
• Reasoning: I am exploring various ways to enhance the reasoning ability of LMs, including
(1) collaboration between agents to make the reasoning path more logical and (2) augmentation of external knowledge to increase truthfulness and provide attribution.
Aside from these, I am excited to explore other NLP topics too.
Previous Research Topics
-
Conversation Disentanglement
Conversation Disentanglement is the task of separating the utterances in a multi-party dialogue into detached threads, where each thread corresponds to a single topic being discussed.
-
Response Generation
Response Generation, or Dialogue Generation, is the task of generating a text reply to a given message in a dialogue. While there are many works that aim at enhancing the diversity and smoothness of the generated text in a 1-1 setting, research on multi-party response generation is still at the starting stage.