Listar GI-LYS - Congresos, conferencias, etc. por título
Mostrando ítems 1-20 de 71
-
4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees
(Association for Computational Linguistics, 2023-12)[Absctract]: We introduce an encoding for parsing as sequence labeling that can represent any projective dependency tree as a sequence of 4-bit labels, one per word. The bits in each word’s label represent (1) whether it ... -
A comparison of statistical association measures for identifying dependency-based collocations in various languages
(Association for Computational Linguistics (ACL), 2019)[Abstract] This paper presents an exploration of different statistical association measures to automatically identify collocations from corpora in English, Portuguese, and Spanish. To evaluate the impact of the association ... -
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) ... -
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, ... -
A Unifying Theory of Transition-based and Sequence Labeling Parsing
(International Committee on Computational Linguistics, 2020-12)[Absctract]: 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 theoretical relation between ... -
Another Dead End for Morphological Tags? Perturbed Inputs and Parsing
(Association for Computational Linguistics, 2023-07)[Absctract]: The usefulness of part-of-speech tags for parsing has been heavily questioned due to the success of word-contextualized parsers. Yet, most studies are limited to coarse-grained tags and high quality written ... -
Any papyrus about "a hand over a stool and a bread loaf, followed by a boat"? Dealing with hieroglyphic texts in IR
(ACM International Conference Proceeding Series, 2016-06)[Abstract] Digital Heritage deals with the use of computing and information technologies for the preservation and study of the human cultural legacy. Within this context, we present here a Text Retrieval system developed ... -
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, ... -
Assessment of Pre-Trained Models Across Languages and Grammars
(Association for Computational Linguistics, 2023-11)[Absctract]: We present an approach for assessing how multilingual large language models (LLMs) learn syntax in terms of multi-formalism syntactic structures. We aim to recover constituent and dependency structures by ... -
BERTbek: A Pretrained Language Model for Uzbek
(European Language Resources Association (ELRA), 2024-05)[Abstract]: Recent advances in neural networks based language representation made it possible for pretrained language models to outperform previous models in many downstream natural language processing (NLP) tasks. These ... -
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 ... -
Bracketing Encodings for 2-Planar Dependency Parsing
(International Committee on Computational Linguistics, 2020-12)[Absctract]: We present a bracketing-based encoding that can be used to represent any 2-planar dependency tree over a sentence of length n as a sequence of n labels, hence providing almost total coverage of crossing arcs ... -
Cognitive Constraints Built into Formal Grammars: Implications for Language Evolution
(Ravignani, A., Barbieri, C., Martins, M., Flaherty, M., Jadoul, Y., Lattenkamp, E., Little, H., Mudd, K., Verhoef, T., 2020-04-17)[Abstract] We study the validity of the cognitive independence assumption using an ensemble of artificial syntactic structures from various classes of dependency grammars. Our findings show that memory limitations have ... -
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, ... -
Cross-lingual Inflection as a Data Augmentation Method for Parsing
(Association for Computational Linguistics, 2022-05)[Absctract]: We propose a morphology-based method for low-resource (LR) dependency parsing. We train a morphological inflector for target LR languages, and apply it to related rich-resource (RR) treebanks to create ... -
Dancing in the Syntax Forest: Fast, Accurate and Explainable Sentiment Analysis with SALSA
(CEUR-WS, 2024)[Abstract]: Sentiment analysis is a key technology for companies and institutions to gauge public opinion on products, services or events. However, for large-scale sentiment analysis to be accessible to entities with modest ... -
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 ... -
Discontinuous Constituent Parsing as Sequence Labeling
(Association for Computational Linguistics, 2020-11)[Absctract]: This paper reduces discontinuous parsing to sequence labeling. It first shows that existing reductions for constituent parsing as labeling do not support discontinuities. Second, it fills this gap and proposes ... -
EN-ES-CS: An English-Spanish Code-Switching Twitter Corpus for Multilingual Sentiment Analysis
(European Language Resources Association (ELRA), 2016-05)[Abstract]: Code-switching texts are those that contain terms in two or more different languages, and they appear increasingly often in social media. The aim of this paper is to provide a resource to the research community ... -
Entity linking with distributional semantics
(Springer, 2016-07)[Abstract] Entity Linking (EL) consists in linking name mentions in a given text with their referring entities in external knowledge bases such as DBpedia/Wikipedia. In this paper, we propose an EL approach whose main ...