AMORE-UPF at SemEval-2018 Task 4: BiLSTM with Entity Library
2018-05-14SEMEVAL 2018Code Available0· sign in to hype
Laura Aina, Carina Silberer, Ionut-Teodor Sorodoc, Matthijs Westera, Gemma Boleda
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/amore-upf/semeval2018-task4OfficialIn paperpytorch★ 0
Abstract
This paper describes our winning contribution to SemEval 2018 Task 4: Character Identification on Multiparty Dialogues. It is a simple, standard model with one key innovation, an entity library. Our results show that this innovation greatly facilitates the identification of infrequent characters. Because of the generic nature of our model, this finding is potentially relevant to any task that requires effective learning from sparse or unbalanced data.