MaskParse@Deskin at SemEval-2019 Task 1: Cross-lingual UCCA Semantic Parsing using Recursive Masked Sequence Tagging

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 107–112 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 107 MaskParse@Deski˜n at SemEval-2019 Task 1: Cross-lingual UCCA Semantic Parsing using Recursive Masked Sequence Tagging Gabriel Marzinotto1,2 Johannes Heinecke1 G´eraldine Damnati1 (1) Orange Labs / Lannion France (2) Aix Marseille Univ, CNRS, LIS / Marseille France {gabriel.marzinotto,johannes.heinecke,geraldine.damnati}@orange.com Abstract This paper describes our recursive system for SemEval-2019 Task 1: Cross-lingual Seman- tic Parsing with UCCA. Each recursive step consists of two parts. We first perform seman- tic parsing using a sequence tagger to estimate the probabilities of the UCCA categories in the sentence. Then, we apply a decoding policy which interprets these probabilities and builds the graph nodes. Parsing is done recursively, we perform a first inference on the sentence to extract the main scenes and links and then we recursively apply our model on the sentence using a masking feature that reflects the deci- sions made in previous steps. Process contin- ues until the terminal nodes are reached. We choose a standard neural tagger and we fo- cused on our recursive parsing strategy and on the cross lingual transfer problem to develop a robust model for the French language, using only few training samples. 1 Introduction Semantic representation is an essential part of NLP. For this reason, several semantic represen- tation paradigms have been proposed. Among them we find PropBank (Palmer et al., 2005) and FrameNet Semantics (Baker et al., 1998), Ab- stract Meaning Representation (AMR) (Banarescu et al., 2013), Universal Decompositional Seman- tics (White et al., 2016) and Universal Conceptual Cognitive Annotation (UCCA) (Abend and Rap- poport, 2013). These constantly improving rep- resentations, along with the advances in semantic parsing, have proven to be beneficial in many NLU tasks such as Question Answering (Shen and La- pata, 2007), text summarization (Genest and La- palme, 2011), dialog systems (Tur et al., 2005), in- formation extraction (Bastianelli et al., 2013) and machine translation (Liu and Gildea, 2010). UCCA is a cross-lingual semantic representa- tion scheme, has demonstrated applicability in En- glish, French and German (with pilot annotation projects on Czech, Russian and Hebrew). De- spite the newness of UCCA, it has proven useful for defining semantic evaluation measures in text- to-text generation and machine translation (Birch et al., 2016). UCCA represents the semantics of a sentence using directed acyclic graphs (DAGs), where terminal nodes correspond to text tokens, and non-terminal nodes to higher level semantic units. Edges are labelled, indicating the role of a child in the relation to its parent. UCCA pars- ing is a recent task and since UCCA has several unique properties, adapting syntactic parsers or parsers from other semantic representations is not straight-forward. Current state of the art parser TUPA (Hershcovich et al., 2017) uses a transition based parsing to build UCCA representations. Building over previous work on FrameNet Se- mantic Parsing (Marzinotto et al., 2018a,b) we chose to perform UCCA parsing using sequence tagging methods along with a graph decoding pol- icy. To …

Content truncated to 500 words