GCN-Sem at SemEval-2019 Task 1: Semantic Parsing using Graph Convolutional and Recurrent Neural Networks

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 102–106 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 102 GCN-Sem at SemEval-2019 Task 1: Semantic Parsing using Graph Convolutional and Recurrent Neural Networks Shiva Taslimipoor Omid Rohanian Sara Moˇze Research Group in Computational Linguistics University of Wolverhampton, UK {shiva.taslimi, omid.rohanian, s.moze}@wlv.ac.uk Abstract This paper describes the system submitted to the SemEval 2019 shared task 1 ‘Cross-lingual Semantic Parsing with UCCA’. We rely on the semantic dependency parse trees provided in the shared task which are converted from the original UCCA files and model the task as tag- ging. The aim is to predict the graph structure of the output along with the types of relations among the nodes. Our proposed neural archi- tecture is composed of Graph Convolution and BiLSTM components. The layers of the sys- tem share their weights while predicting de- pendency links and semantic labels. The sys- tem is applied to the CONLLU format of the input data and is best suited for semantic de- pendency parsing. 1 Introduction Universal Conceptual Cognitive Annotation (UCCA) (Abend and Rappoport, 2013) is a semantically motivated approach to grammatical representation inspired by typological theories of grammar (Dixon, 2012) and Cognitive Linguistics literature (Croft and Cruse, 2004). In parsing, bi-lexical dependencies that are based on binary head-argument relations between lexical units are commonly employed in the representation of syntax (Nivre et al., 2007; Chen and Manning, 2014) and semantics (Hajiˇc et al., 2012; Oepen et al., 2014; Dozat and Manning, 2018). UCCA differs significantly from traditional de- pendency approaches in that it attempts to ab- stract away traditional syntactic structures and re- lations in favour of employing purely semantic distinctions to analyse sentence structure. The shared task, ‘cross-lingual semantic parsing with UCCA’ (Hershcovich et al., 2019) consists in pars- ing English, German, and French datasets using the UCCA semantic tagset. In order to enable multi-task learning, the UCCA-annotated data is automatically converted to other parsing formats, e.g. Abstract Meaning Representation (AMR) and Semantic Dependency Parsing (SDP), inter alia (Hershcovich et al., 2018). Although the schemes are formally different, they have shared semantic content. In order to perform our experiments, we target the converted CONLLU format, which corresponds to tradi- tional bi-lexical dependencies and rely on the con- version methodology which is provided in the shared task (Hershcovich et al., 2019) to attain UCCA graphs. UCCA graphs contain both explicit and implicit units 1 However, in bi-lexical dependencies, nodes are text tokens and semantic relations are direct bi-lexical relations between the tokens. The con- version between the two format results in partial loss of information. Nonetheless, we believe that it is worth trying to model the task using one of the available formats (i.e. semantic dependency parsing) which is very popular among NLP re- searchers. Typically, transition-based methods are used in syntactic (Chen and Manning, 2014) and seman- tic (Hershcovich et al., 2017) dependency parsing. By contrast, our proposed system shares several similarities with sequence-to-sequence neural ar- chitectures, …

Content truncated to 500 words