Semantic Graph Parsing with Recurrent Neural Network DAG Grammars

2019-09-30 · IJCNLP 2019 11 · Federico Fancellu, Sorcha Gilroy, Adam Lopez, Mirella Lapata

Semantic parses are directed acyclic graphs (DAGs), so semantic parsing should be modeled as graph prediction. But predicting graphs presents difficult technical challenges, so it is simpler and more common to predict the linearized graphs found in semantic parsing datasets using well-understood sequence models. The cost of this simplicity is that the predicted strings may not be well-formed graphs. We present recurrent neural network DAG grammars, a graph-aware sequence model that ensures only well-formed graphs while sidestepping many difficulties in graph prediction. We test our model on the Parallel Meaning Bank---a multilingual semantic graphbank. Our approach yields competitive results in English and establishes the first results for German, Italian and Dutch.

📄 PDF Abstract BibTeX arXiv:1910.00051

Code (0)

등록된 구현이 없습니다.

Tasks

DRS Parsing Semantic Parsing

Methods 이 논문이 사용한 방법론

Test 설명 없음

Recurrent Neural Network Grammars

2016-02-25 · NAACL 2016 6 · Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, Noah A. Smith

We introduce recurrent neural network grammars, probabilistic models of sentences with explicit phrase structure. We explain efficient inference procedures that allow application to both parsing and language modeling. Ex…

Constituency Parsing Language Modeling Language Modelling

Polynomial Graph Parsing with Non-Structural Reentrancies

2021-05-05 · Johanna Björklund, Frank Drewes, Anna Jonsson

Graph-based semantic representations are valuable in natural language processing, where it is often simple and effective to represent linguistic concepts as nodes, and relations as edges between them. Several attempts ha…

Abstract Meaning Representation

Universal Recurrent Neural Network Grammar

2021-10-01 · ROCLING 2021 10 · Chinmay Choudhary, Colm O’riordan

Modern approaches to Constituency Parsing are mono-lingual supervised approaches which require large amount of labelled data to be trained on, thus limiting their utility to only a handful of high-resource languages. To …

Constituency Parsing Cross-Lingual Transfer Transfer Learning

BME-UW at SRST-2019: Surface realization with Interpreted Regular Tree Grammars

2019-11-01 · WS 2019 11 · {\'A}d{\'a}m Kov{\'a}cs, Evelin {\'A}cs, Judit {\'A}cs, Andras Kornai 외

The Surface Realization Shared Task involves mapping Universal Dependency graphs to raw text, i.e. restoring word order and inflection from a graph of typed, directed dependencies between lemmas. Interpreted Regular Tree…

Decoder Semantic Parsing

Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars

2021-09-10 · EMNLP 2021 11 · Ryo Yoshida, Hiroshi Noji, Yohei Oseki

In computational linguistics, it has been shown that hierarchical structures make language models (LMs) more human-like. However, the previous literature has been agnostic about a parsing strategy of the hierarchical mod…

Sentence