A survey of cross-lingual features for zero-shot cross-lingual semantic parsing

The availability of corpora to train semantic parsers in English has lead to significant advances in the field. Unfortunately, for languages other than English, annotation is scarce and so are developed parsers. We then ask: could a parser trained in English be applied to language that it hasn't been trained on? To answer this question we explore zero-shot cross-lingual semantic parsing where we train an available coarse-to-fine semantic parser (Liu et al., 2018) using cross-lingual word embeddings and universal dependencies in English and test it on Italian, German and Dutch. Results on the Parallel Meaning Bank - a multilingual semantic graphbank, show that Universal Dependency features significantly boost performance when used in conjunction with other lexical features but modelling the UD structure directly when encoding the input does not.

[1]  Mirella Lapata,et al.  Discourse Representation Structure Parsing , 2018, ACL.

[2]  Shujian Huang,et al.  Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder , 2017, ACL.

[3]  Mirella Lapata,et al.  Language to Logical Form with Neural Attention , 2016, ACL.

[4]  Antonio Toral,et al.  Exploring Neural Methods for Parsing Discourse Representation Structures , 2018, TACL.

[5]  Dan Klein,et al.  Learning Dependency-Based Compositional Semantics , 2011, CL.

[6]  Dominique Estival,et al.  Multilingual Semantic Parsing And Code-Switching , 2017, CoNLL.

[7]  Shay B. Cohen,et al.  Cross-Lingual Abstract Meaning Representation Parsing , 2017, NAACL.

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

[9]  Percy Liang,et al.  Data Recombination for Neural Semantic Parsing , 2016, ACL.

[10]  Milan Straka,et al.  Tokenizing, POS Tagging, Lemmatizing and Parsing UD 2.0 with UDPipe , 2017, CoNLL.

[11]  Bonnie L. Webber,et al.  Neural Networks for Cross-lingual Negation Scope Detection , 2018, ArXiv.

[12]  Uwe Reyle,et al.  From Discourse to Logic - Introduction to Modeltheoretic Semantics of Natural Language, Formal Logic and Discourse Representation Theory , 1993, Studies in linguistics and philosophy.

[13]  Johan Bos,et al.  Evaluating Scoped Meaning Representations , 2018, LREC.

[14]  Sheng Zhang,et al.  Cross-lingual Semantic Parsing , 2018, ArXiv.

[15]  Christopher D. Manning,et al.  Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks , 2015, ACL.

[16]  Slav Petrov,et al.  A Universal Part-of-Speech Tagset , 2011, LREC.

[17]  Wei Lu,et al.  Neural Architectures for Multilingual Semantic Parsing , 2017, ACL.

[18]  Johan Bos,et al.  The Parallel Meaning Bank: Towards a Multilingual Corpus of Translations Annotated with Compositional Meaning Representations , 2017, EACL.

[19]  Mirella Lapata,et al.  Coarse-to-Fine Decoding for Neural Semantic Parsing , 2018, ACL.

[20]  Luke S. Zettlemoyer,et al.  Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars , 2005, UAI.

[21]  Mirella Lapata,et al.  Learning Structured Natural Language Representations for Semantic Parsing , 2017, ACL.

[22]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[23]  Mark Steedman,et al.  Universal Semantic Parsing , 2017, EMNLP.

[24]  Dan Flickinger,et al.  Translation using Minimal Recursion Semantics , 1995, TMI.

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

[26]  Noah A. Smith,et al.  Polyglot Semantic Role Labeling , 2018, ACL.

[27]  Mirella Lapata,et al.  Cross-linguistic Projection of Role-Semantic Information , 2005, HLT/EMNLP.