OSU_CHGCG at SemEval-2016 Task 9 : Chinese Semantic Dependency Parsing with Generalized Categorial Grammar

Abstract

This paper introduces our Chinese semantic dependency parsing system for Task 9 of Se-mEval 2016. Our system has two components: a parser trained using the Berkeley Grammar Trainer on the Penn Chinese Treebank reannotated in a Generalized Categorial Grammar, and a multinomial logistic regression classifier. We first parse the data with the automatic parser to obtain predicate-argument dependencies and then we use the classifier to predict the semantic dependency labels for the predicate-argument dependency relations extracted. Although our parser is not trained directly on the task training data, our system yields the best performance for the non-local dependency recovery for the news data and comparable overall results.

Probing the nature of an island constraint with a parsed corpus: A case study on the Coordinate Structure Constraint in Japanese

“…An obvious challenge for such a project is the fact that current parsers are not good at reliably identifying fine-grained linguistic information such as the position of the gap in a relative clause. However, research on improving the accuracy of machine annotation for fine-grained, linguistically relevant information is rapidly in progress (see, e.g., Duan et al (2016)), so, the future prospects for this type of work do not seem totally gloom.…”