A survey of syntactic-semantic parsing based on constituent and dependency structures

MS Zhang - Science China Technological Sciences, 2020 - Springer
Syntactic and semantic parsing has been investigated for decades, which is one primary
topic in the natural language processing community. This article aims for a brief survey on …

Bottom-up constituency parsing and nested named entity recognition with pointer networks

S Yang, K Tu - arXiv preprint arXiv:2110.05419, 2021 - arxiv.org
Constituency parsing and nested named entity recognition (NER) are similar tasks since
they both aim to predict a collection of nested and non-crossing spans. In this work, we cast …

Constituent parsing as sequence labeling

C Gómez-Rodríguez, D Vilares - arXiv preprint arXiv:1810.08994, 2018 - arxiv.org
We introduce a method to reduce constituent parsing to sequence labeling. For each word
w_t, it generates a label that encodes:(1) the number of ancestors in the tree that the words …

Transition-based semantic dependency parsing with pointer networks

D Fernández-González… - arXiv preprint arXiv …, 2020 - arxiv.org
Transition-based parsers implemented with Pointer Networks have become the new state of
the art in dependency parsing, excelling in producing labelled syntactic trees and …

On the use of parsing for named entity recognition

MA Alonso, C Gómez-Rodríguez, J Vilares - Applied sciences, 2021 - mdpi.com
Parsing is a core natural language processing technique that can be used to obtain the
structure underlying sentences in human languages. Named entity recognition (NER) is the …

N-ary constituent tree parsing with recursive semi-Markov model

X Xin, J Li, Z Tan - Proceedings of the 59th Annual Meeting of the …, 2021 - aclanthology.org
In this paper, we study the task of graph-based constituent parsing in the setting that
binarization is not conducted as a pre-processing step, where a constituent tree may consist …

Better, faster, stronger sequence tagging constituent parsers

D Vilares, M Abdou, A Søgaard - arXiv preprint arXiv:1902.10985, 2019 - arxiv.org
Sequence tagging models for constituent parsing are faster, but less accurate than other
types of parsers. In this work, we address the following weaknesses of such constituent …

Discontinuous constituency parsing with a stack-free transition system and a dynamic oracle

M Coavoux, SB Cohen - arXiv preprint arXiv:1904.00615, 2019 - arxiv.org
We introduce a novel transition system for discontinuous constituency parsing. Instead of
storing subtrees in a stack--ie a data structure with linear-time sequential access--the …

A unifying theory of transition-based and sequence labeling parsing

C Gómez-Rodríguez, M Strzyz, D Vilares - arXiv preprint arXiv:2011.00584, 2020 - arxiv.org
We define a mapping from transition-based parsing algorithms that read sentences from left
to right to sequence labeling encodings of syntactic trees. This not only establishes a …

Enriched in-order linearization for faster sequence-to-sequence constituent parsing

D Fernández-González… - arXiv preprint arXiv …, 2020 - arxiv.org
Sequence-to-sequence constituent parsing requires a linearization to represent trees as
sequences. Top-down tree linearizations, which can be based on brackets or shift-reduce …