Papers by Maxime De Bruyn

2 papers
Domain- and Task-Adaptation for VaccinChatNL, a Dutch COVID-19 FAQ Answering Corpus and Classification Model (2022.coling-1)

Copied to clipboard

Challenge: VaccinChatNL is the first FAQ chatbot with over 12k user queries . it can be used to find the representative question that matches a user's request .
Approach: They build a FAQ chatbot from 50 question-answer pairs and annotate user questions with appropriate or new answer classes.
Outcome: The VaccinChatNL is the first publicly available Dutch FAQ answering corpus with large groups of human-paraphrased questions.
Open-Domain Dialog Evaluation Using Follow-Ups Likelihood (2022.coling-1)

Copied to clipboard

Challenge: Existing methods do not correlate strongly with human annotations.
Approach: They propose a method that measures the probability that a language model will continue the conversation with a fixed set of follow-ups.
Outcome: The proposed method achieves the highest correlation with human evaluations when compared against twelve existing methods.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations