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

This paper describes our recursive system for SemEval-2019 \textit{ Task 1: Cross-lingual Semantic Parsing with UCCA}. Each recursive step consists of two parts. We first perform semantic 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 decisions made in previous steps. Process continues until the terminal nodes are reached. We choose a standard neural tagger and we focused 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]  Milan Straka,et al.  Tokenizing, POS Tagging, Lemmatizing and Parsing UD 2.0 with UDPipe , 2017, CoNLL.

[2]  Frédéric Béchet,et al.  Semantic Frame Parsing for Information Extraction : the CALOR corpus , 2018, LREC.

[3]  Ondrej Bojar,et al.  HUME: Human UCCA-Based Evaluation of Machine Translation , 2016, EMNLP.

[4]  Ding Liu,et al.  Semantic Role Features for Machine Translation , 2010, COLING.

[5]  Philipp Koehn,et al.  Abstract Meaning Representation for Sembanking , 2013, LAW@ACL.

[6]  Ari Rappoport,et al.  Universal Conceptual Cognitive Annotation (UCCA) , 2013, ACL.

[7]  Young-Bum Kim,et al.  Cross-Lingual Transfer Learning for POS Tagging without Cross-Lingual Resources , 2017, EMNLP.

[8]  Roberto Basili,et al.  Textual Inference and Meaning Representation in Human Robot Interaction , 2013, JSSP.

[9]  Sheng Zhang,et al.  Universal Decompositional Semantics on Universal Dependencies , 2016, EMNLP.

[10]  Guillaume Lample,et al.  Word Translation Without Parallel Data , 2017, ICLR.

[11]  Tom M. Mitchell,et al.  A Joint Sequential and Relational Model for Frame-Semantic Parsing , 2017, EMNLP.

[12]  John B. Lowe,et al.  The Berkeley FrameNet Project , 1998, ACL.

[13]  Dilek Z. Hakkani-Tür,et al.  Semi-supervised learning for spoken language understanding semantic role labeling , 2005, IEEE Workshop on Automatic Speech Recognition and Understanding, 2005..

[14]  Frédéric Béchet,et al.  Robust Semantic Parsing with Adversarial Learning for Domain Generalization , 2019, NAACL.

[15]  Guy Lapalme,et al.  Framework for Abstractive Summarization using Text-to-Text Generation , 2011, Monolingual@ACL.

[16]  Frédéric Béchet,et al.  Sources of Complexity in Semantic Frame Parsing for Information Extraction , 2018, ArXiv.

[17]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[18]  Luke S. Zettlemoyer,et al.  Deep Semantic Role Labeling: What Works and What’s Next , 2017, ACL.

[19]  Ari Rappoport,et al.  A Transition-Based Directed Acyclic Graph Parser for UCCA , 2017, ACL.

[20]  Mirella Lapata,et al.  Using Semantic Roles to Improve Question Answering , 2007, EMNLP.

[21]  Jürgen Schmidhuber,et al.  Training Very Deep Networks , 2015, NIPS.

[22]  Daniel Gildea,et al.  The Proposition Bank: An Annotated Corpus of Semantic Roles , 2005, CL.