I am a third-year PhD student in Computer Science in the Natural Language Processing Lab working with Jinho Choi at Emory University. My research interests are in natural language processing, especially in the context of conversational systems. I have explored many facets of conversational systems, including the development and deployment of a personal-experience-oriented dialogue system for large-scale usage, the current evaluation protocols being used to evaluate such dialogue systems, and the ability to detect user engagement during the course of a conversation. My current works focus on an approach to dialogue using semantic graphs and common sense reasoning as well as pursuing comprehensive and reproducible dialogue system evaluation.
Before coming to Emory University, my undergraduate research background also was in automated dialogue systems. I worked as an undergraduate research assistant in the Language and Interaction Lab at Michigan State University, where we focused on developing a robotic system that is able to learn how to perform a task from a human teacher, using both language instruction and visual demonstration. I also spent a summer in the Natural Language Dialogue Group at the Institute for Creative Technologies of the University of Southern California investigating the sharing of personal information between humans in chat-oriented dialogues and applying our findings to the development of an automated system for extracting personal information of a human interlocutor.
Sarah E. Finch and Jinho Choi. 2020. Towards Unified Dialogue System Evaluation: A Comprehensive Analysis of Current Evaluation Protocols. In Proceedings of the 21st Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL).
Sarah E. Finch, James D. Finch, Ali Ahmadvand, Ingyu (Jason) Choi, Xiangjue Dong, Ruixiang Qi, Harshita Sahijwani, Sergey Volokhin, Zihan Wang, Zihao Wang, and Jinho D. Choi. 2020. Emora: An Inquisitive Social Chatbot Who Cares For You. In 3rd Proceedings of the Alexa Prize.
Sarah Fillwock and David Traum. 2018. Identification of Personal Information Shared in Chat-Oriented Dialogue in Proceedings of the 11th International Conference on Language Resources and Evaluation, Miyazaki, Japan.
Sarah Fillwock, Changsong Liu, and Joyce Chai. July 2016. Dialogue Management for Task-Learning Human-Robot Dialogue. Poster presented at the Mid-Michigan Symposium for Undergraduate Research Experiences.
I was the co-team-lead for Emory University's 14-person student team participating in the 3rd Amazon Alexa Prize. The goal of this challenge is to develop the most engaging and capable dialogue agent. We were one of 10 teams invited to participate based on our proposal, out of approximately 400 applicants. By July 2020, we won this year's competition, based on advancing through two elimination rounds based on user ratings and then receiving the highest overall rating from the panel of final judges.
There currently exist a wide variety of evaluation strategies for dialogue systems, which presents challenges for comparing approaches across works. In an effort to explore these diversities, I analyzed the evaluation protocols of twenty recent dialogue system works, focusing on human evaluations. This analysis and the resulting synthesized human evaluation dimensions for dialogue will be presented at SIGDIAL 2020.
As a step towards being able to predict future events based on real events extracted from current news, I collaborated with two other graduate students in the NLP Lab to explore unsupervised clustering aproaches for cross-document entity linking.
Accurate emotional understanding of a conversational partner allows for more sophisticated dialogue strategies. I investigated a language-based approach to predicting current user engagement in an online fashion during a conversation, with the ultimate goal of using such engagement as a feature for initiative transfer.
I worked in the Natural Language Dialogue Group with Dr. David Traum during this 10-week NSF REU program. Inspired by previous work showing that human-human conversations tend to contain a significant portion of personal experience and personal information sharing, I explored in detail the types of personal information that people tend to share in conversations and developed a preliminary word-embedding-based approach to extracting such information from user utterances.
I was involved as a undergraduate research assistant in the development of an end-to-end multi-modal task-learning robot. My focus was on the information-state-driven dialogue strategy for understanding the human teacher's instructions for a given task.