paper-with-me

Papers

Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering

2021-04-13 · EMNLP 2021 11 · Daniel Fernández-González, Carlos Gómez-Rodríguez

Discontinuous constituent parsers have always lagged behind continuous approaches in terms of accuracy and speed, as the presence of constituents with discontinuous yield introduces extra complexity to the task. However, a discontinuous tree can be converted into a continuous variant by reordering tokens. Based on that, we propose to reduce discontinuous parsing to a continuous problem, which can then be directly solved by any off-the-shelf continuous parser. To that end, we develop a Pointer Network capable of accurately generating the continuous token arrangement for a given input sentence and define a bijective function to recover the original order. Experiments on the main benchmarks with two continuous parsers prove that our approach is on par in accuracy with purely discontinuous state-of-the-art algorithms, but considerably faster.

📄 PDF Abstract BibTeX arXiv:2104.06239

Code (1)

danifg/Pointer-Network-Reordering 공식 구현 pytorch

Tasks

Sentence

Methods 이 논문이 사용한 방법론

Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
[LivE@PeRson]How do I talk to a real person at Expedia? How do I talk to a real person at Expedia? To speak with a live Expedia agent, call 1 (888) 829-0881 anytime. The customer support team is available 24/7 to help with…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Pointer Network Pointer Networks tackle problems where input and output data are sequential data, but can't be solved by seq2seq type models because discrete categories of output elements…

Similar Papers 제목 키워드 기반

Discontinuous Constituent Parsing with Pointer Networks

2020-02-05 · Daniel Fernández-González, Carlos Gómez-Rodríguez

One of the most complex syntactic representations used in computational linguistics and NLP are discontinuous constituent trees, crucial for representing all grammatical phenomena of languages such as German. Recent adva…

Dependency ParsingPart-Of-Speech TaggingSentence

Multitask Pointer Network for Multi-Representational Parsing

2020-09-21 · Daniel Fernández-González, Carlos Gómez-Rodríguez

We propose a transition-based approach that, by training a single model, can efficiently parse any input sentence with both constituent and dependency trees, supporting both continuous/projective and discontinuous/non-pr…

Sentence

Rethinking Boundaries: End-To-End Recognition of Discontinuous Mentions with Pointer Networks

2021-05-18 · Conference 2021 5 · Hao Fei, Fei Li, Bobo Li, Yijiang Liu 외

A majority of research interests in irregular (eg, nested or discontinuous) named entity recognition (NER) have been paid on nested entities, while discontinuous entities received limited attention. Existing work for dis…

Boundary DetectionDecodernamed-entity-recognitionNamed Entity Recognition+2

Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammars

2022-12-18 · Songlin Yang, Roger P. Levy, Yoon Kim

We study grammar induction with mildly context-sensitive grammars for unsupervised discontinuous parsing. Using the probabilistic linear context-free rewriting system (LCFRS) formalism, our approach fixes the rule struct…

Constituency Parsingparameter estimationTensor Decomposition

Incremental Discontinuous Phrase Structure Parsing with the GAP Transition

2017-04-01 · EACL 2017 4 · Maximin Coavoux, Beno{\^\i}t Crabb{\'e}

This article introduces a novel transition system for discontinuous lexicalized constituent parsing called SR-GAP. It is an extension of the shift-reduce algorithm with an additional gap transition. Evaluation on two Ger…