Køpsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding

We present Kopsala, the Copenhagen-Uppsala system for the Enhanced Universal Dependencies Shared Task at IWPT 2020. Our system is a pipeline consisting of off-the-shelf models for everything but enhanced graph parsing, and for the latter, a transition-based graph parser adapted from Che et al. (2019). We train a single enhanced parser model per language, using gold sentence splitting and tokenization for training, and rely only on tokenized surface forms and multilingual BERT for encoding. While a bug introduced just before submission resulted in a severe drop in precision, its post-submission fix would bring us to 4th place in the official ranking, according to average ELAS. Our parser demonstrates that a unified pipeline is effective for both Meaning Representation Parsing and Enhanced Universal Dependencies.

[1]  Jan Hajic,et al.  UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing , 2016, LREC.

[2]  Christopher D. Manning,et al.  Enhanced English Universal Dependencies: An Improved Representation for Natural Language Understanding Tasks , 2016, LREC.

[3]  Noah A. Smith,et al.  Transition-Based Dependency Parsing with Stack Long Short-Term Memory , 2015, ACL.

[4]  Christopher D. Manning,et al.  Stanza: A Python Natural Language Processing Toolkit for Many Human Languages , 2020, ACL.

[5]  Stephan Oepen,et al.  MRP 2019: Cross-Framework Meaning Representation Parsing , 2019, CoNLL.

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

[7]  Phil Blunsom,et al.  Robust Incremental Neural Semantic Graph Parsing , 2017, ACL.

[8]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[9]  Ari Rappoport,et al.  Universal Dependency Parsing with a General Transition-Based DAG Parser , 2018, CoNLL.

[10]  Deyi Xiong,et al.  Neural Machine Translation with Decoding History Enhanced Attention , 2018, COLING.

[11]  Sampo Pyysalo,et al.  Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection , 2020, LREC.

[12]  Dan Kondratyuk,et al.  Cross Framework Meaning Representation Parsing , 2019 .

[13]  Maria Leonor Pacheco,et al.  of the Association for Computational Linguistics: , 2001 .

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

[15]  Joakim Nivre,et al.  An Efficient Algorithm for Projective Dependency Parsing , 2003, IWPT.

[16]  Gosse Bouma,et al.  Overview of the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies , 2020, IWPT.

[17]  Joakim Nivre,et al.  Enhancing Universal Dependency Treebanks: A Case Study , 2018, UDW@EMNLP.

[18]  Yijia Liu,et al.  HIT-SCIR at MRP 2019: A Unified Pipeline for Meaning Representation Parsing via Efficient Training and Effective Encoding , 2019, CoNLL.

[19]  Yijia Liu,et al.  An AMR Aligner Tuned by Transition-based Parser , 2018, EMNLP.

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

[21]  Luke S. Zettlemoyer,et al.  AllenNLP: A Deep Semantic Natural Language Processing Platform , 2018, ArXiv.