During the multi-turn response selection, BERT focuses on training the relationship between the context with multiple utterances and the response.
Ranked #1 on Conversational Response Selection on Douban
As research on utilizing human knowledge in natural language processing has attracted considerable attention in recent years, knowledge graph (KG) completion has come into the spotlight.
This paper describes our approach to the task of identifying offensive languages in a multilingual setting.
This paper describes our system, Joint Encoders for Stable Suggestion Inference (JESSI), for the SemEval 2019 Task 9: Suggestion Mining from Online Reviews and Forums.
To generate a large amount of machine-labeled data, firstly we generate an initial machine-labeled data by using a chunker and MetaMap.