Listar GI-LYS - Congresos, conferencias, etc. por data de publicación
Mostrando ítems 21-40 de 57
-
A non-projective greedy dependency parser with bidirectional LSTMs
(Association for Computational Linguistics, 2017-08)[Abstract]: The LyS-FASTPARSE team present BIST-COVINGTON, a neural implementation of the Covington (2001) algorithm for non-projective dependency parsing. The bidirectional LSTM approach by Kiperwasser and Goldberg (2016) ... -
Towards fast natural language parsing: FASTPARSE ERC Starting Grant
(Sociedad Española para el Procesamiento del Lenguaje Natural (SEPLN), 2017-09)[Abstract:] The goal of the FASTPARSE project (Fast Natural Language Parsing for Large-Scale NLP), funded by the European Research Council (ERC), is to achieve a breakthrough in the speed of natural language syntactic ... -
Detecting Perspectives in Political Debates
(Association for Computational Linguistics, 2017-09)[Abstract]: We explore how to detect people’s perspectives that occupy a certain proposition. We propose a Bayesian modelling approach where topics (or propositions) and their associated perspectives (or viewpoints) are ... -
Tratamiento sintáctico de la negación en análisis del sentimiento monolingüe y multilingüe
(2017-09-19)[Abstract] Dealing with negation in a proper way is a relevant factor in order to obtain high performance sentiment analysis systems. In this framework, we present a method for the treatment of negation in Spanish that ... -
Global Transition-based Non-projective Dependency Parsing
(Association for Computational Linguistics (ACL), 2018)[Absctract]: Shi, Huang, and Lee (2017a) obtained state-of-the-art results for English and Chinese dependency parsing by combining dynamic-programming implementations of transition-based dependency parsers with a minimal ... -
Constituent Parsing as Sequence Labeling
(Association for Computational Linguistics (ACL), 2018)[Absctract]: We introduce a method to reduce constituent parsing to sequence labeling. For each word wt, it generates a label that encodes: (1) the number of ancestors in the tree that the words wt and wt+1 have in common, ... -
A Transition-Based Algorithm for Unrestricted AMR Parsing
(Association for Computational Linguistics, 2018-06)[Absctract]: Non-projective parsing can be useful to handle cycles and reentrancy in AMR graphs. We explore this idea and introduce a greedy left-to-right non-projective transition-based parser. At each parsing configuration, ... -
Grounding the Semantics of Part-of-Day Nouns Worldwide using Twitter
(Association for Computational Linguistics, 2018-06)[Absctract]: The usage of part-of-day nouns, such as ‘night’, and their time-specific greetings (‘good night’), varies across languages and cultures. We show the possibilities that Twitter offers for studying the semantics ... -
On the Processing and Analysis of Microtexts: From Normalization to Semantics
(M D P I AG, 2018-09-18)[Abstract] User-generated content published on microblogging social platforms constitutes an invaluable source of information for diverse purposes: health surveillance, business intelligence, political analysis, etc. We ... -
Increasing NLP Parsing Efficiency with Chunking
(M D P I AG, 2018-09-19)[Abstract] We introduce a “Chunk-and-Pass” parsing technique influenced by a psycholinguistic model, where linguistic information is processed not word-by-word but rather in larger chunks of words. We present preliminary ... -
Sequence Tagging for Fast Dependency Parsing
(2019)[Abstract] Dependency parsing has been built upon the idea of using parsing methods based on shift-reduce or graph-based algorithms in order to identify binary dependency relations between the words in a sentence. In this ... -
Left-to-Right Dependency Parsing with Pointer Networks
(Association for Computational Linguistics (ACL), 2019)[Abstract]: 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. Similarly to the recent ... -
Viable Dependency Parsing as Sequence Labeling
(Association for Computational Linguistics (ACL), 2019-06)[Abstract]: We recast dependency parsing as a sequence labeling problem, exploring several encodings of dependency trees as labels. While dependency parsing by means of sequence labeling had been attempted in existing work, ... -
Better, Faster, Stronger Sequence Tagging Constituent Parsers
(Association for Computational Linguistics, 2019-06)[Absctract]: 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 parsers: (a) high error rates ... -
Harry Potter and the Action Prediction Challenge from Natural Language
(Association for Computational Linguistics, 2019-06)[Absctract]: We explore the challenge of action prediction from textual descriptions of scenes, a testbed to approximate whether text inference can be used to predict upcoming actions. As a case of study, we consider the ... -
Sequence Labeling Parsing by Learning across Representations
(Association for Computational Linguistics, 2019-07)[Absctract]: We use parsing as sequence labeling as a common framework to learn across constituency and dependency syntactic abstractions. To do so, we cast the problem as multitask learning (MTL). First, we show that ... -
HEAD-QA: A Healthcare Dataset for Complex Reasoning
(Association for Computational Linguistics, 2019-07)[Absctract]: We present HEAD-QA, a multi-choice question answering testbed to encourage research on complex reasoning. The questions come from exams to access a specialized position in the Spanish healthcare system, and ... -
Artificially Evolved Chunks for Morphosyntactic Analysis
(Association for Computational Linguistics, 2019-08)[Absctract]: We introduce a language-agnostic evolutionary technique for automatically extracting chunks from dependency treebanks. We evaluate these chunks on a number of morphosyntactic tasks, namely POS tagging, ... -
Towards Making a Dependency Parser See
(Association for Computational Linguistics, 2019-11)[Absctract]: We explore whether it is possible to leverage eye-tracking data in an RNN dependency parser (for English) when such information is only available during training - i.e. no aggregated or token-level gaze features ... -
Parsing as Pretraining
(2020)[Abstract] Recent analyses suggest that encoders pretrained for language modeling capture certain morpho-syntactic structure. However, probing frameworks for word vectors still do not report results on standard setups ...