AMORE-UPF at SemEval-2018 Task 4: BiLSTM with entity library

Boleda, Gemma; Aina, Laura; Silberer, Carina; Sorodoc, Ionut-Teodor; Westera, Matthijs

AMORE-UPF at SemEval-2018 Task 4: BiLSTM with entity library

License

Citation

Aina L, Silberer C, Sorodoc IT, Westera M, Boleda G. AMORE-UPF at SemEval-2018 Task 4: BiLSTM with entity library. In: Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018); 2018 Jun 5-6; New Orleans, LA. Stroudsburg (PA): ACL; 2018. p. 65–9.

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.

Description

Comunicació presentada al 12th International Workshop on Semantic Evaluation (SemEval-2018), celebrat els dies 5 i 6 de juny de 2018 a Nova Orleans, EUA.