Matches in ScholarlyData for { ?s ?p ?o. }
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent chamberlain-jon.
- item-3 previous item-2.
- 592 creator oliver-lemon.
- 592 creator verena-rieser.
- 592 type InProceedings.
- 592 label "Automatic Learning and Evaluation of User-Centered Objective Functions for Dialogue System Optimisation".
- 592 sameAs 592.
- 592 abstract "The ultimate goal when building dialogue systems is to satisfy the needs of real users, but quality assurance for dialogue strategies is a non-trivial problem. The applied evaluation metrics and resulting design principles are often obscure, emerge by trial-and-error, and are highly context dependent. This paper introduces data-driven methods for obtaining reliable objective functions for system design. In particular, we test whether an objective function obtained from Wizard-of-Oz (WOZ) data is a valid estimate of real users preferences. We test this in a test-retest comparison between the model obtained from the WOZ study and the models obtained when testing with real users. We can show that, despite a low fit to the initial data, the objective function obtained from WOZ data makes accurate predictions for automatic dialogue evaluation, and, when automatically optimising a policy using these predictions, the improvement over a strategy simply mimicking the data becomes clear from an error analysis.".
- 592 hasAuthorList authorList.
- 592 hasTopic Linguistics.
- 592 isPartOf proceedings.
- 592 keyword "Acquisition, Machine Learning".
- 592 keyword "Dialogue & Natural Interactivity".
- 592 keyword "Usability, user satisfaction".
- 592 title "Automatic Learning and Evaluation of User-Centered Objective Functions for Dialogue System Optimisation".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasLastItem item-2.
- item-1 type ListItem.
- item-1 hasContent verena-rieser.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent oliver-lemon.
- item-2 previous item-1.
- 594 creator georgiana-dinu.
- 594 creator grzegorz-chrupala.
- 594 creator josef-van-genabith.
- 594 type InProceedings.
- 594 label "Learning Morphology with Morfette".
- 594 sameAs 594.
- 594 abstract "Morfette is a modular, data-driven, probabilistic system which learns to perform joint morphological tagging and lemmatization from morphologically annotated corpora. The system is composed of two learning modules which are trained to predict morphological tags and lemmas using the Maximum Entropy classifier. The third module dynamically combines the predictions of the Maximum-Entropy models and outputs a probability distribution over tag-lemma pair sequences. The lemmatization module exploits the idea of recasting lemmatization as a classification task by using class labels which encode mappings from word forms to lemmas. Experimental evaluation results and error analysis on three morphologically rich languages show that the system achieves high accuracy with no language-specific feature engineering or additional resources.".
- 594 hasAuthorList authorList.
- 594 hasTopic Linguistics.
- 594 isPartOf proceedings.
- 594 keyword "Acquisition, Machine Learning".
- 594 keyword "Morphology".
- 594 keyword "Statistical methods".
- 594 title "Learning Morphology with Morfette".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasItem item-3.
- authorList hasLastItem item-3.
- item-1 type ListItem.
- item-1 hasContent grzegorz-chrupala.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent georgiana-dinu.
- item-2 next item-3.
- item-2 previous item-1.
- item-3 type ListItem.
- item-3 hasContent josef-van-genabith.
- item-3 previous item-2.
- 595 creator alessandra-potrich.
- 595 creator emanuele-pianta.
- 595 type InProceedings.
- 595 label "L-ISA: Learning Domain Specific Isa-Relations from the Web".
- 595 sameAs 595.
- 595 abstract "Automated extraction of ontological knowledge from text corpora is a relevant task in Natural Language Processing. In this paper, we focus on the problem of finding hypernyms for relevant concepts in a specific domain (e.g. Optical Recording) in the context of a concrete and challenging application scenario (patent processing). To this end information available on the Web is exploited. The extraction method includes four mains steps. Firstly, the Google search engine is exploited to retrieve possible instances of isa-patterns reported in the literature. Then, the returned snippets are filtered on the basis of lexico-syntactic criteria (e.g. the candidate hypernym must be expressed as a noun phrase without complex modifiers). In a further filtering step, only candidate hypernyms compatible with the target domain are kept. Finally a candidate ranking mechanism is applied to select one hypernym as output of the algorithm. The extraction method was evaluated on 100 concepts of the Optical Recording domain. Moreover, the reliability of isa-patterns reported in the literature as predictors of isa-relations was assessed by manually evaluating the template instances remaining after lexico-syntactic filtering, for 3 concepts of the same domain. While more extensive testing is needed the method appears promising especially for its portability across different domains.".
- 595 hasAuthorList authorList.
- 595 hasTopic Linguistics.
- 595 isPartOf proceedings.
- 595 keyword "Information Extraction, Information Retrieval".
- 595 keyword "Knowledge representation".
- 595 keyword "Ontologies".
- 595 title "L-ISA: Learning Domain Specific Isa-Relations from the Web".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.
- authorList hasLastItem item-2.
- item-1 type ListItem.
- item-1 hasContent alessandra-potrich.
- item-1 next item-2.
- item-2 type ListItem.
- item-2 hasContent emanuele-pianta.
- item-2 previous item-1.
- 596 creator gaelle-vidal.
- 596 creator laure-charonnat.
- 596 creator olivier-boeffard.
- 596 type InProceedings.
- 596 label "Automatic Phone Segmentation of Expressive Speech".
- 596 sameAs 596.
- 596 abstract "In order to improve the flexibility and the precision of an automatic phone segmentation system for a type of expressive speech, the dubbing into French of fiction movies, we developed both the phonetic labeling process and the alignment process. The automatic labelling system relies on an automatic grapheme-to-phoneme conversion including all the variants of the phonetic chain and on HMM modeling. In this article, we will distinguish three sets of phone models: a set of context independent models, a set of left and right context dependant models and finally a mixing of the two that combines phone and triphone models according to the precision of alignment obtained for each phonetic broad-class. The three models are evaluated on a test corpus. On the one hand we notice a little decrease in the score of phonetic labelling mainly due to pauses insertions, but on the other hand the mixed set of models gives the best results for the score of precision of the alignment.".
- 596 hasAuthorList authorList.
- 596 hasTopic Linguistics.
- 596 isPartOf proceedings.
- 596 keyword "Corpus (creation, annotation, etc.)".
- 596 keyword "Statistical methods".
- 596 keyword "Tagging".
- 596 title "Automatic Phone Segmentation of Expressive Speech".
- authorList type List.
- authorList hasFirstItem item-1.
- authorList hasItem item-1.
- authorList hasItem item-2.