Kurt Junshean Espinosa


pdf bib
A Search-based Neural Model for Biomedical Nested and Overlapping Event Detection
Kurt Junshean Espinosa | Makoto Miwa | Sophia Ananiadou
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

We tackle the nested and overlapping event detection task and propose a novel search-based neural network (SBNN) structured prediction model that treats the task as a search problem on a relation graph of trigger-argument structures. Unlike existing structured prediction tasks such as dependency parsing, the task targets to detect DAG structures, which constitute events, from the relation graph. We define actions to construct events and use all the beams in a beam search to detect all event structures that may be overlapping and nested. The search process constructs events in a bottom-up manner while modelling the global properties for nested and overlapping structures simultaneously using neural networks. We show that the model achieves performance comparable to the state-of-the-art model Turku Event Extraction System (TEES) on the BioNLP Cancer Genetics (CG) Shared Task 2013 without the use of any syntactic and hand-engineered features. Further analyses on the development set show that our model is more computationally efficient while yielding higher F1-score performance.


pdf bib
An Empirical Study on End-to-End Sentence Modelling
Kurt Junshean Espinosa
Proceedings of ACL 2017, Student Research Workshop


pdf bib
Learning to recognise named entities in tweets by exploiting weakly labelled data
Kurt Junshean Espinosa | Riza Theresa Batista-Navarro | Sophia Ananiadou
Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)

Named entity recognition (NER) in social media (e.g., Twitter) is a challenging task due to the noisy nature of text. As part of our participation in the W-NUT 2016 Named Entity Recognition Shared Task, we proposed an unsupervised learning approach using deep neural networks and leverage a knowledge base (i.e., DBpedia) to bootstrap sparse entity types with weakly labelled data. To further boost the performance, we employed a more sophisticated tagging scheme and applied dropout as a regularisation technique in order to reduce overfitting. Even without hand-crafting linguistic features nor leveraging any of the W-NUT-provided gazetteers, we obtained robust performance with our approach, which ranked third amongst all shared task participants according to the official evaluation on a gold standard named entity-annotated corpus of 3,856 tweets.