Korean-Specific Emotion Annotation Procedure Using N-Gram-Based Distant Supervision and Korean-Specific-Feature-Based Distant Supervision

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 1–10 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 1 Neural Mention Detection Juntao Yu,1 Bernd Bohnet,2 Massimo Poesio1 1Queen Mary University of London, 2Google Research juntao.yu@qmul.ac.uk, bohnetbd@google.com, m.poesio@qmul.ac.uk Abstract Mention detection is an important preprocessing step for annotation and interpretation in applications such as NER and coreference resolution, but few stand-alone neural models have been proposed able to handle the full range of mentions. In this work, we propose and compare three neural network-based approaches to mention detection. The first approach is based on the mention detection part of a state of the art coreference resolution system; the second uses ELMO embeddings together with a bidirectional LSTM and a biaffine classifier; the third approach uses the recently introduced BERT model. Our best model (using a biaffine classifier) achieves gains of up to 1.8 percentage points on mention recall when compared with a strong baseline in a HIGH RECALL coreference annotation setting. The same model achieves improvements of up to 5.3 and 6.2 p.p. when compared with the best-reported mention detection F1 on the CONLL and CRAC coreference data sets respectively in a HIGH F1 annotation setting. We then evaluate our models for coreference resolution by using mentions predicted by our best model in start-of-the-art coreference systems. The enhanced model achieved absolute improvements of up to 1.7 and 0.7 p.p. when compared with our strong baseline systems (pipeline system and end-to-end system) respectively. For nested NER, the evaluation of our model on the GENIA corpora shows that our model matches or outperforms state-of-the-art models despite not being specifically designed for this task. Keywords: Mention Detection, Coreference Resolution, Nested Named Entity Recognition, Deep Neural Networks 1. Introduction Mention detection (MD) is the task of identifying mentions of entities in text. It is an important preprocessing step for downstream applications such as nested named entity recognition (Zheng et al., 2019) or coreference resolution (Poesio et al., 2016); thus, the quality of mention detection affects both the performance of models for such applica- tions and the quality of annotated data used to train them (Chamberlain et al., 2016; Poesio et al., 2019). Much mention detection research for NER has concentrated on a simplified version of MD that focuses on proper names only (i.e., it doesn’t consider as mentions nominals such as the protein or pronouns such as it), and ignores the fact that mentions may nest (e.g., noun phrases such as [[CCITA] mRNA] in the GENIA corpus are mentions of two separate entities, CCITA and CCITA and mRNA (Alex et al., 2007)). However such simplified view of mentions is not sufficient for NER in domains such as biomedical, or for coreference, that requires full mention detection. Another limitation of typical mention detection systems is that they only predict mentions in a HIGH F1 fashion, whereas in coreference, for instance, mentions are usually predicted in a HIGH RE- CALL setting, since further pruning will be carried …

Content truncated to 500 words