Exploració per tema "Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural"
Ara es mostren els items 1-20 de 374
-
A commentary on “The now-or-never bottleneck: a fundamental constraint on language”, by Christiansen and Chater (2016)
(RAM-Verlag, 2017-07-02)
Article
Accés obertIn a recent article, Christiansen and Chater (2016) present a fundamental constraint on language, i.e. a now-or-never bottleneck that arises from our fleeting memory, and explore its implications, e.g., chunk-and-pass ... -
A comparison of approaches for measuring cross-lingual similarity of wikipedia articles
(Springer, 2014)
Text en actes de congrés
Accés obertWikipedia has been used as a source of comparable texts for a range of tasks, such as Statistical Machine Translation and Cross-Language Information Retrieval. Articles written in different languages on the same topic are ... -
A dependency look at the reality of constituency
(RAM-Verlag, 2018)
Article
Accés obertA comment on “Neurophysiological dynamics of phrase-structure building during sentence processing” by Nelson et al (2017), Proceedings of the National Academy of Sciences USA 114(18), E3669-E3678. -
A differentiable BLEU loss. Analysis and first results
(2018)
Text en actes de congrés
Accés obertIn natural language generation tasks, like neural machine translation and image captioning, there is usually a mismatch between the optimized loss and the de facto evaluation criterion, namely token-level maximum likelihood ... -
A global relaxation labeling approach to coreference resolution
(2010)
Text en actes de congrés
Accés restringit per política de l'editorialThis paper presents a constraint-based graph partitioning approach to coreference resolution solved by relaxation labeling. The approach combines the strengths of groupwise classifiers and chain formation methods in ... -
A graph partitioning approach to entity disambiguation using uncertain information
(Springer, 2008-08-31)
Text en actes de congrés
Accés restringit per política de l'editorialThis paper presents a method for Entity Disambiguation in Information Extraction from different sources in the web. Once entities and relations between them are extracted, it is needed to determine which ones are referring ... -
A hybrid approach to treebank construction
(2012-09)
Article
Accés obertEste artículo describe investigación sobre los efectos de la desambiguación morfosintáctica usada como un preproceso de un analizador sintáctico profundo basado en HPSG, en el contexto del desarrollo de un treebank del ... -
A hybrid machine translation architecture guided by syntax
(2014-09-16)
Article
Accés restringit per política de l'editorialThis article presents a hybrid architecture which combines rule-based machine translation (RBMT) with phrase-based statistical machine translation (SMT). The hybrid translation system is guided by the rule-based engine. ... -
A hybrid system for patent translation
(2012)
Comunicació de congrés
Accés obertThis work presents a HMT system for patent translation. The system exploits the high coverage of SMT and the high precision of an RBMT system based on GF to deal with specific issues of the language. The translator is ... -
A joint model for parsing syntactic and semantic dependencies
(Coling 2008 Organizing Committee, 2008)
Text en actes de congrés
Accés obertThis paper describes a system that jointly parses syntactic and semantic dependencies, presented at the CoNLL-2008 shared task (Surdeanu et al., 2008). It combines online Peceptron learning (Collins, 2002) with a parsing ... -
A law of word meaning in dolphin whistle types
(2009-10-30)
Article
Accés obertWe show that dolphin whistle types tend to be used in specific behavioral contexts, which is consistent with the hypothesis that dolphin whistle have some sort of “meaning”. Besides, in some cases, it can be shown that the ... -
A MOOC on approaches to machine translation
(2015-12-10)
Article
Accés obertThis paper describes the design, development, and analysis of a MOOC entitled “Approaches to Machine Translation: Rule-based, statistical and hybrid”, and provides lessons learned and conclusions to be taken into account ... -
A non-linear semantic mapping technique for cross-language sentence matching
(2010-08-01)
Article
Accés restringit per política de l'editorial -
A note on movement in logical grammar
(2018)
Article
Accés obertIn this article, we make some brief remarks on overt and covert movement in logical grammar. With respect to covert movement (e.g. quantification), we observe how a treatment in terms of displacement calculus interacts ... -
A pipeline for large raw text preprocessing and model training of language models at scale
(Universitat Politècnica de Catalunya, 2021-01-25)
Projecte Final de Màster Oficial
Accés obert
Realitzat a/amb: Universitat de Barcelona / Universitat Rovira i VirgiliThe advent of Transformer-based (i.e., based on self-attention architectures) language models has revolutionized the entire field of Natural Language Processing (NLP). Once pre-trained on large, unlabelled corpora, we can ... -
A reply to Kubota and Levine on gapping
(2017-02)
Article
Accés obertIn a series of papers Kubota and Levine give an account of gapping and determiner gapping in terms of hybrid type logical grammar, including anomalous scopal interactions with auxiliaries and negative quantifiers. We make ... -
A Sentiment Analysis Approach to Process Civic Contributions
(Institute of Electrical and Electronics Engineers (IEEE), 2020)
Comunicació de congrés
Accés obertCrowdsourced civic engagement is a novel form of democratic participation that allows citizens to share their ideas and deliberate in a multitude of diverse participatory processes that are emerging all over the world, ... -
A shortest-path method for arc-factored semantic role labeling
(2014)
Comunicació de congrés
Accés restringit per política de l'editorialWe introduce a Semantic Role Labeling (SRL) parser that finds semantic roles for a predicate together with the syntactic paths linking predicates and arguments. Our main contribution is to formulate SRL in terms of ... -
A Speech-based Dialogue System for Household Robots
(Universitat Politècnica de Catalunya / Technische Universiteit Delft, 2011)
Projecte/Treball Final de Carrera
Accés restringit per decisió de l'autorThis thesis studies mechanisms to improve human-robot-interaction through a spoken dialogue for household robots. Therefore, a full dialogue system, in which the semantics of the words play an important role, is ... -
A statistical model from information theory to explain Zipf's law of brevity
(Basque Center on Cognition, Brain and Language, 2019)
Comunicació de congrés
Accés restringit per política de l'editorialBrevity and frequency are two crucial factors in the processes of statistical learning. The compression principle had already been used previously to explain the origin of Zipf’s law for the frequency of words. Here we use ...