A Transition-Based Directed Acyclic Graph Parser for UCCA

@article{Hershcovich2017ATD,
  title={A Transition-Based Directed Acyclic Graph Parser for UCCA},
  author={Daniel Hershcovich and Omri Abend and Ari Rappoport},
  journal={ArXiv},
  year={2017},
  volume={abs/1704.00552}
}
We present the first parser for UCCA, a cross-linguistically applicable framework for semantic representation, which builds on extensive typological work and supports rapid annotation. UCCA poses a challenge for existing parsing techniques, as it exhibits reentrancy (resulting in DAG structures), discontinuous structures and non-terminal nodes corresponding to complex semantic units. To our knowledge, the conjunction of these formal properties is not supported by any existing parser. Our… Expand
Transition-based Semantic Dependency Parsing with Pointer Networks
TLDR
A transition system that, thanks to Pointer Networks, can straightforwardly produce labelled directed acyclic graphs and perform semantic dependency parsing and matches the best fully-supervised accuracy to date on the SemEval 2015 Task 18 datasets among previous state-of-the-art graph-based parsers. Expand
Universal Dependency Parsing with a General Transition-Based DAG Parser
TLDR
TUPA is a general neural transition-based DAG parser, which is used to present the first experiments on recovering enhanced dependencies as part of the general parsing task, to the CoNLL 2018 UD shared task. Expand
Self-Attentive Constituency Parsing for UCCA-based Semantic Parsing
TLDR
This paper proposes a novel self-attentive neural parsing model for the UCCA representation and presents the results for both single-lingual and cross-lingUAL tasks using zero-shot and few-shot learning for low-resource languages. Expand
SemEval 2019 Shared Task: Cross-lingual Semantic Parsing with UCCA - Call for Participation
TLDR
A shared task on UCCA parsing in English, German and French, and call for participants to submit their systems to have a significant contribution to the advancement of UCCC parsing in particular, and semantic parsing in general. Expand
UCCA Graph Parsing as Constituent Tree Parsing
This paper describes a simple UCCA semantic graph parsing approach. The key idea is to convert a UCCA semantic graph into a constituent tree, in which extra labels are deliberately designed to markExpand
Cross-lingual Semantic Representation for NLP with UCCA
This is an introductory tutorial to UCCA (Universal Conceptual Cognitive Annotation), a cross-linguistically applicable framework for semantic representation, with corpora annotated in English,Expand
SemEval-2019 Task 1: Cross-lingual Semantic Parsing with UCCA
TLDR
The SemEval 2019 shared task on Universal Conceptual Cognitive Annotation parsing in English, German and French is presented, and the participating systems and results are discussed. Expand
Comparing Knowledge-Intensive and Data-Intensive Models for English Resource Semantic Parsing
TLDR
A factorization-based parser is introduced that can produce Elementary Dependency Structures much more accurately than previous data-driven parsers, and this analysis is beneficial to in-depth evaluation of several representative parsing techniques and leads to new directions for parser development. Expand
DeepCx: A transition-based approach for shallow semantic parsing with complex constructional triggers
This paper introduces the surface construction labeling (SCL) task, which expands the coverage of Shallow Semantic Parsing (SSP) to include frames triggered by complex constructions. We presentExpand
A Transition-based Parser for Unscoped Episodic Logical Forms
TLDR
This work presents the first learned approach for parsing sentences into ULFs, using a growing set of annotated examples, and learns a sequence-to-sequence model for predicting the transition action sequence within a modified cache transition system. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 103 REFERENCES
Transition-based Dependency DAG Parsing Using Dynamic Oracles
TLDR
This study proposes a new dependency DAG parsing approach which uses a dynamic oracle within a shift-reduce transitionbased parsing framework and obtains competitive performances compared to static oracles. Expand
A Transition-based Algorithm for AMR Parsing
TLDR
A two-stage framework to parse a sentence into its Abstract Meaning Representation (AMR) by using a dependency parser to generate a dependency tree and a novel transition-based algorithm that transforms the dependency tree to an AMR graph. Expand
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
TLDR
The effectiveness of the BiLSTM approach is demonstrated by applying it to a greedy transition-based parser as well as to a globally optimized graph-basedparser. Expand
Shift-Reduce Dependency DAG Parsing
TLDR
This work presents a parsing approach that is nearly as simple as current data-driven transition-based dependency parsing frameworks, but outputs directed acyclic graphs (DAGs). Expand
Peking: Building Semantic Dependency Graphs with a Hybrid Parser
TLDR
A hybrid parser which benefits from both transition-based and graph-based parsing approaches is implemented, and the tree approximation method is explored to take advantage of wellstudied tree parsing techniques. Expand
Parsing as Reduction
TLDR
This work reduces phrase-representation parsing to dependency parsing, and shows that any off-the-shelf, trainable dependency parser can be used to produce constituents, and can perform discontinuous parsing in a very natural manner. Expand
An Incremental Algorithm for Transition-based CCG Parsing
TLDR
This work describes a new algorithm for incremental transition-based Combinatory Categorial Grammar parsing and introduces two new actions in the shift-reduce paradigm based on the idea of ‘revealing’ the required information during parsing. Expand
Alpage: Transition-based Semantic Graph Parsing with Syntactic Features
TLDR
Two transition-based dependency parsers with extended sets of actions to handle non-planar acyclic graphs are developed by the ALPAGE team to participate to the SemEval-2014 Task on Broad-Coverage Semantic Dependency Parsing. Expand
A Discriminative Graph-Based Parser for the Abstract Meaning Representation
TLDR
The first approach to parse sentences into meaning representation, a semantic formalism for which a grow- ing set of annotated examples is available, is introduced, providing a strong baseline for improvement. Expand
An Incremental Parser for Abstract Meaning Representation
TLDR
A transition-based parser for AMR that parses sentences left-to-right, in linear time is described and it is shown that this parser is competitive with the state of the art on the LDC2015E86 dataset and that it outperforms state-of-the-art parsers for recovering named entities and handling polarity. Expand
...
1
2
3
4
5
...