We consider detection of the span of antecedents and consequents in argumentative prose a structural, grammatical task. Our system comprises a set of stacked Bi-LSTMs trained on two complementary linguistic annotations. We explore the effectiveness of grammatical features (POS and clause type) through ablation. The reported experiments suggest that a multi-task learning approach using this external, grammatical knowledge is useful for detecting the extent of antecedents and consequents and performs nearly as well without the use of word embeddings.
CITATION STYLE
Sung, M. G., Bagherzadeh, P., & Bergler, S. (2020). CLaC at SemEval-2020 Task 5: Muli-task Stacked Bi-LSTMs. In 14th International Workshops on Semantic Evaluation, SemEval 2020 - co-located 28th International Conference on Computational Linguistics, COLING 2020, Proceedings (pp. 445–450). International Committee for Computational Linguistics. https://doi.org/10.18653/v1/2020.semeval-1.54
Mendeley helps you to discover research relevant for your work.