José-Miguel Benedí

Also published as: J. M. Benedí, Jose-Miguel Benedi, José Miguel Benedi Ruiz, José Miguel Benedí, José Miguel Benedí Ruíz, José-M. Benedí, José-Miguel Benedí Ruíz


2016

pdf bib
Beyond Prefix-Based Interactive Translation Prediction
Jesús González-Rubio | Daniel Ortiz-Martínez | Francisco Casacuberta | José Miguel Benedi Ruiz
Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning

2013

pdf bib
Interactive Machine Translation using Hierarchical Translation Models
Jesús González-Rubio | Daniel Ortiz-Martínez | José-Miguel Benedí | Francisco Casacuberta
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

2010

pdf bib
Enlarged Search Space for SITG Parsing
Guillem Gascó | Joan-Andreu Sánchez | José-Miguel Benedí
Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics

pdf bib
Interactive Predictive Parsing using a Web-based Architecture
Ricardo Sánchez-Sáez | Luis A. Leiva | Joan-Andreu Sánchez | José-Miguel Benedí
Proceedings of the NAACL HLT 2010 Demonstration Session

pdf bib
Evaluation of HMM-based Models for the Annotation of Unsegmented Dialogue Turns
Carlos-D. Martínez-Hinarejos | Vicent Tamarit | José-M. Benedí
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)

Corpus-based dialogue systems rely on statistical models, whose parameters are inferred from annotated dialogues. The dialogues are usually annotated in terms of Dialogue Acts (DA), and the manual annotation is difficult (as annotation rule are hard to define), error-prone and time-consuming. Therefore, several semi-automatic annotation processes have been proposed to speed-up the process and consequently obtain a dialogue system in less total time. These processes are usually based on statistical models. The standard statistical annotation model is based on Hidden Markov Models (HMM). In this work, we explore the impact of different types of HMM, with different number of states, on annotation accuracy. We performed experiments using these models on two dialogue corpora (Dihana and SwitchBoard) of dissimilar features. The results show that some types of models improve standard HMM in a human-computer task-oriented dialogue corpus (Dihana corpus), but their impact is lower in a human-human non-task-oriented dialogue corpus (SwitchBoard corpus).

pdf bib
Confidence Measures for Error Discrimination in an Interactive Predictive Parsing Framework
Ricardo Sánchez-Sáez | Joan Andreu Sánchez | José Miguel Benedí
Coling 2010: Posters

2009

pdf bib
Improving Unsegmented Dialogue Turns Annotation with N-gram Transducers
Carlos-D. Martínez-Hinarejos | Vicent Tamarit | José-Miguel Benedí
Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation, Volume 1

pdf bib
Interactive Predictive Parsing
Ricardo Sánchez-Sáez | Joan-Andreu Sánchez | José-Miguel Benedí
Proceedings of the 11th International Conference on Parsing Technologies (IWPT’09)

pdf bib
Statistical Confidence Measures for Probabilistic Parsing
Ricardo Sánchez-Sáez | Joan-Andreu Sánchez | José-Miguel Benedí Ruíz
Proceedings of the International Conference RANLP-2009

pdf bib
Improving Unsegmented Statistical Dialogue Act Labelling
Vicent Tamarit | Carlos-D. Martínez-Hinarejos | José Miguel Benedí Ruíz
Proceedings of the International Conference RANLP-2009

2006

pdf bib
Obtaining Word Phrases with Stochastic Inversion Translation Grammars for Phrase-based Statistical Machine Translation
J. A. Sánchez | J. M. Benedí
Proceedings of the 11th Annual conference of the European Association for Machine Translation

pdf bib
Segmented and Unsegmented Dialogue-Act Annotation with Statistical Dialogue Models
Carlos D. Martínez Hinarejos | Ramón Granell | José Miguel Benedí
Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions

pdf bib
Stochastic Inversion Transduction Grammars for Obtaining Word Phrases for Phrase-based Statistical Machine Translation
Joan Andreu Sánchez | José Miguel Benedí
Proceedings on the Workshop on Statistical Machine Translation

pdf bib
Design and acquisition of a telephone spontaneous speech dialogue corpus in Spanish: DIHANA
José-Miguel Benedí | Eduardo Lleida | Amparo Varona | María-José Castro | Isabel Galiano | Raquel Justo | Iñigo López de Letona | Antonio Miguel
Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)

In the framework of the DIHANA project, we present the acquisitionprocess of a spontaneous speech dialogue corpus in Spanish. Theselected application consists of information retrieval by telephone for nationwide trains. A total of 900 dialogues from 225 users were acquired using the “Wizard of Oz” technique. In this work, we present the design and planning of the dialogue scenes and the wizard strategy used for the acquisition of the corpus. Then, we also present the acquisition tools and a description of the acquisition process.

2001

pdf bib
Improvement of a Whole Sentence Maximum Entropy Language Model Using Grammatical Features
Fredy A. Amaya | José Miguel Benedí
Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics

2000

pdf bib
Combination of N-Grams and Stochastic Context-Free Grammars for Language Modeling
Jose-Miguel Benedi | Joan-Andreu Sanchez
COLING 2000 Volume 1: The 18th International Conference on Computational Linguistics

pdf bib
Using Perfect Sampling in Parameter Estimation of a Whole Sentence Maximum Entropy Language Model
F. Amaya | J. M. Benedí
Fourth Conference on Computational Natural Language Learning and the Second Learning Language in Logic Workshop

1997

pdf bib
Using Categories in the EUTRANS System
J. C. Amengual | J. M. Benedí | F. Casacuberta | A. Castaño | A. Castellanos | D. Llorens | A. Marzal | F. Prat | E. Vidal | J. M. Vilar
Spoken Language Translation