AMORE-UPF at SemEval-2018 Task 4: BiLSTM with Entity Library

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 65–69 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics AMORE-UPF at SemEval-2018 Task 4: BiLSTM with Entity Library Laura Aina∗ Carina Silberer∗ Ionut-Teodor Sorodoc∗ Matthijs Westera∗ Gemma Boleda Universitat Pompeu Fabra Barcelona, Spain {firstname.lastname}@upf.edu Abstract This paper describes our winning contribution to SemEval 2018 Task 4: Character Identifi- cation on Multiparty Dialogues. It is a simple, standard model with one key innovation, an en- tity library. Our results show that this innova- tion greatly facilitates the identification of in- frequent characters. Because of the generic na- ture of our model, this finding is potentially rel- evant to any task that requires effective learn- ing from sparse or unbalanced data. 1 Introduction SemEval 2018 Task 4 is an entity linking task on multiparty dialogue.1 It consists in predicting the referents of nominals that refer to a person, such as she, mom, Judy – henceforth mentions. The set of possible referents is given beforehand, as well as the set of mentions to resolve. The dataset used in this task is based on Chen and Choi (2016) and Chen et al. (2017), and consists of dialogue from the TV show Friends in textual form. Our main interest is whether deep learning mod- els for tasks like entity linking can benefit from having an explicit entity library, i.e., a component of the neural network that stores entity represen- tations learned during training. To that end, we add such a component to an otherwise relatively basic model – a bidirectional LSTM (long short- term memory; Hochreiter and Schmidhuber 1997), the standard neural network model for sequential data like language. Training and evaluating this ∗denotes equal contribution. 1https://competitions.codalab.org/ competitions/17310 model on the task shows that the entity library is beneficial in the case of infrequent entities.2 2 Related Work Previous entity linking tasks concentrate on linking mentions to Wikipedia pages (Bunescu and Pas¸ca 2006; Mihalcea and Csomai 2007 and much sub- sequent work; for a recent approach see Francis- Landau et al. 2016). By contrast, in the present task (based on Chen and Choi 2016; Chen et al. 2017) only a list of entities is given, without any associated encyclopedic entries. This makes the task more similar to the way in which a human audience might watch the TV show, in that they are initially unfamiliar with the characters. What also sets the present task apart from most previous tasks is its focus on multiparty dialogue (as opposed to, typically, newswire articles). A task that is closely related to entity linking is coreference resolution, i.e., the task of clustering mentions that refer to the same entity (e.g., the CoNLL shared task of Pradhan et al. 2011). Since mention clusters essentially correspond to entities (an insight central to the approaches to coreference in Haghighi and Klein 2010; Clark and Manning 2016), the present task can be regarded as a type of coreference resolution, but one where the set of referents to choose from …

Content truncated to 500 words