no code implementations • 9 May 2023 • Daniel Fernández-González
Structured sentiment analysis (SSA) aims to automatically extract people's opinions from a text in natural language and adequately represent that information in a graph structure.
no code implementations • 21 Oct 2022 • Daniel Fernández-González
In this article, we advance the research on shift-reduce semantic parsing for task-oriented dialog.
1 code implementation • 20 May 2022 • Daniel Fernández-González
Semantic role labeling (SRL) focuses on recognizing the predicate-argument structure of a sentence and plays a critical role in many natural language processing tasks such as machine translation and question answering.
1 code implementation • 20 Oct 2021 • Daniel Fernández-González, Carlos Gómez-Rodríguez
In order to achieve deep natural language understanding, syntactic constituent parsing is a vital step, highly demanded by many artificial intelligence systems to process both text and speech.
1 code implementation • 20 May 2021 • Daniel Fernández-González, Carlos Gómez-Rodríguez
Dependency parsing is a crucial step towards deep language understanding and, therefore, widely demanded by numerous Natural Language Processing applications.
1 code implementation • EMNLP 2021 • 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.
1 code implementation • 21 Sep 2020 • 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-projective syntactic structures.
1 code implementation • 27 May 2020 • Daniel Fernández-González, Carlos Gómez-Rodríguez
Sequence-to-sequence constituent parsing requires a linearization to represent trees as sequences.
1 code implementation • 27 May 2020 • Daniel Fernández-González, Carlos Gómez-Rodríguez
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 outperforming graph-based models in this task.
1 code implementation • 5 Feb 2020 • 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.
2 code implementations • 20 Mar 2019 • Daniel Fernández-González, Carlos Gómez-Rodríguez
We propose a novel transition-based algorithm that straightforwardly parses sentences from left to right by building $n$ attachments, with $n$ being the length of the input sentence.
Ranked #11 on Dependency Parsing on Penn Treebank
1 code implementation • 25 Oct 2018 • Daniel Fernández-González, Carlos Gómez-Rodríguez
In addition, by improving the performance of the state-of-the-art in-order shift-reduce parser, we achieve the best accuracy to date (92. 0 F1) obtained by a fully-supervised single-model greedy shift-reduce constituent parser on the WSJ benchmark.
no code implementations • 14 May 2018 • Daniel Fernández-González, Carlos Gómez-Rodríguez
We propose an efficient dynamic oracle for training the 2-Planar transition-based parser, a linear-time parser with over 99% coverage on non-projective syntactic corpora.
no code implementations • 21 Apr 2018 • Daniel Fernández-González, Carlos Gómez-Rodríguez
An increasingly wide range of artificial intelligence applications rely on syntactic information to process and extract meaning from natural language text or speech, with constituent trees being one of the most widely used syntactic formalisms.
1 code implementation • 25 Oct 2017 • Daniel Fernández-González, Carlos Gómez-Rodríguez
We present a novel transition system, based on the Covington non-projective parser, introducing non-local transitions that can directly create arcs involving nodes to the left of the current focus positions.
no code implementations • 11 Jun 2017 • Daniel Fernández-González, Carlos Gómez-Rodríguez
Restricted non-monotonicity has been shown beneficial for the projective arc-eager dependency parser in previous research, as posterior decisions can repair mistakes made in previous states due to the lack of information.
no code implementations • IJCNLP 2015 • Daniel Fernández-González, André F. T. Martins
We reduce phrase-representation parsing to dependency parsing.