Amr Parsing

14 papers with code ยท Natural Language Processing

Each AMR is a single rooted, directed graph. AMRs include PropBank semantic roles, within-sentence coreference, named entities and types, modality, negation, questions, quantities, and so on. See.

Leaderboards

Latest papers without code

Core Semantic First: A Top-down Approach for AMR Parsing

IJCNLP 2019

The output graph spans the nodes by the distance to the root, following the intuition of first grasping the main ideas then digging into more details.

AMR PARSING

AMR Parsing as Sequence-to-Graph Transduction

ACL 2019

Our experimental results outperform all previously reported SMATCH scores, on both AMR 2. 0 (76. 3{\%} on LDC2017T10) and AMR 1. 0 (70. 2{\%} on LDC2014T12).

AMR PARSING DATA AUGMENTATION

SemBleu: A Robust Metric for AMR Parsing Evaluation

ACL 2019

Evaluating AMR parsing accuracy involves comparing pairs of AMR graphs.

AMR PARSING

Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning

ACL 2019

Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs.

AMR PARSING

Automatic Accuracy Prediction for AMR Parsing

SEMEVAL 2019

Secondly, we perform parse selection based on predicted parse accuracies of candidate parses from alternative systems, with the aim of improving overall results.

AMR PARSING REGRESSION

Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning

ACL 2019

Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs.

AMR PARSING

Automatic Accuracy Prediction for AMR Parsing

SEMEVAL 2019

Secondly, we perform parse selection based on predicted parse accuracies of candidate parses from alternative systems, with the aim of improving overall results.

AMR PARSING REGRESSION

An Improved Approach for Semantic Graph Composition with CCG

28 Mar 2019

We define new semantics for the CCG combinators that is better suited to deriving AMR graphs.

AMR PARSING

An empirical evaluation of AMR parsing for legal documents

20 Nov 2018

Many approaches have been proposed to tackle the problem of Abstract Meaning Representation (AMR) parsing, helps solving various natural language processing issues recently.

AMR PARSING

Better Transition-Based AMR Parsing with a Refined Search Space

EMNLP 2018

This paper introduces a simple yet effective transition-based system for Abstract Meaning Representation (AMR) parsing.

AMR PARSING NAMED ENTITY RECOGNITION SEMANTIC PARSING STRUCTURED PREDICTION