Pasar al contenido principal

MULTI-FACETED DOMAIN ADAPTATION FOR ADVANCED TEXTUAL SEMANTIC PROCESSING

TIN2015-65308-C5-1-R

•
Nombre agencia financiadora Ministerio de Economía y Competitividad
Acrónimo agencia financiadora MINECO
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2015
Plan Estatal 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Unidad de gestión Dirección General de Investigación Científica y Técnica
Centro beneficiario UNIVERSIDAD DEL PAIS VASCO EUSKAL HERRIKO UNIBERTSITATEA
Identificador persistente http://dx.doi.org/10.13039/501100003329

Resultados relacionados

Resultados totales (Incluyendo duplicados): 13
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Interpretable semantic textual similarity: Finding and explaining differences between sentences

  • Lopez-Gazpio, Iñigo
  • Maritxalar, Montserrat
  • Gonzalez Agirre, Aitor
  • Rigau Claramunt, German
  • Uria, Larraitz
  • Agirre, Eneko
User acceptance of artificial intelligence agents might depend on their ability to explain their reasoning to the users. We focus on a specific text processing task, the Semantic Textual Similarity task (STS), where systems need to measure the degree of semantic equivalence between two sentences. We propose to add an interpretability layer (iSTS for short) formalized as the alignment between pairs of segments across the two sentences, where the relation between the segments is labeled with a relation type and a similarity score. This way, a system performing STS could use the interpretability layer to explain to users why it returned that specific score for the given sentence pair. We present a publicly available dataset of sentence pairs annotated following the formalization. We then develop an iSTS system trained on this dataset, which given a sentence pair finds what is similar and what is different, in the form of graded and typed segment alignments. When evaluated on the dataset, the system performs better than an informed baseline, showing that the dataset and task are well-defined and feasible. Most importantly, two user studies show how the iSTS system output can be used to automatically produce explanations in natural language. Users performed the two tasks better when having access to the explanations, providing preliminary evidence that our dataset and method to automatically produce explanations do help users understand the output of STS systems better., Aitor Gonzalez-Agirre and Inigo Lopez-Gazpio are supported by doctoral grants from MINECO. The work described in this project has been partially funded by MINECO in projects MUSTER (PCIN-2015-226) and TUNER (TIN 2015-65308-C5-1-R), as well as the Basque Government (A group research team, IT344-10).
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Introducing idioms in the Galician WordNet: methods, problems and results

  • Álvarez de la Granja, María
  • Gómez Clemente, Xosé María
  • Gómez Guinovart, Xavier
This study describes the introduction of verbal idioms in the Galician language version (Galnet) of the semantic network WordNet; a network that does not traditionally include many phraseological units. To enhance Galnet, a list of 803 Galician verbal idioms was developed to then review each of them individually and assess whether they could be introduced in an existing WordNet synset (a group of synonyms expressing the same concept) or not. Of those 803 idioms, 490 (61%) could be included in this network. Besides, Galnet was enlarged with 750 extra verbal idioms, most of them synonyms or variants of the former. In this study, we present the working methodology for the experiment and an analysis of the results, to help understand the most important problems found when trying to introduce idioms in Galnet. We also discuss the reasons preventing the inclusion of some expressions, and the criteria used to introduce the idioms that finally made it into the network., This research has been supported by the Xunta de Galicia and the European Union (under grant GRC2013/40) and by the Ministry of Economy and Competitiveness of the Spanish Government (Project TUNER: Automatic domain adaptation for semantic processing, TIN2015-65308-C5-1-R).
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Through the Eyes of VERTa

  • Comelles, Elisabet
  • Atserias, Jordi
This paper describes a practical demo of VERTa for Spanish. VERTa is an MT evaluation metric that combines linguistic features at different levels. VERTa has been developed for English and Spanish but can be easily adapted to other languages. VERTa can be used to evaluate adequacy, fluency and ranking of sentences. In this paper, VERTa’s modules are described briefly, as well as its graphical interface which provides information on VERTa’s performance and possible MT errors., This work has been funded by the Spanish Government (project TUNER, TIN2015-65308-C5-1-R).
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Robust multilingual Named Entity Recognition with shallow semi-supervised features

  • Agerri, Rodrigo
  • Rigau Claramunt, German
We present a multilingual Named Entity Recognition approach based on a robust and general set of features across languages and datasets. Our system combines shallow local information with clustering semi-supervised features induced on large amounts of unlabeled text. Understanding via empirical experimentation how to effectively combine various types of clustering features allows us to seamlessly export our system to other datasets and languages. The result is a simple but highly competitive system which obtains state of the art results across five languages and twelve datasets. The results are reported on standard shared task evaluation data such as CoNLL for English, Spanish and Dutch. Furthermore, and despite the lack of linguistically motivated features, we also report best results for languages such as Basque and German. In addition, we demonstrate that our method also obtains very competitive results even when the amount of supervised data is cut by half, alleviating the dependency on manually annotated data. Finally, the results show that our emphasis on clustering features is crucial to develop robust out-of-domain models. The system and models are freely available to facilitate its use and guarantee the reproducibility of results., This work has been supported by the European projects NewsReader, EC/FP7/316404 and QTLeap – EC/FP7/610516, and by the Spanish Ministry of Economy and Competitiveness (MINECO) SKATER, Grant No. TIN2012-38584-C06-01 and TUNER, TIN2015-65308-C5-1-R.
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Savana: a global information extraction and terminology expansion framework in the medical domain

  • Espinosa-Anke, Luis
  • Tello, Jorge
  • Pardo, Albert, 1964-
  • Medrano, Ignacio
  • Ureña, Alberto
  • Salcedo, Ignacio
  • Saggion, Horacio
Terminological databases constitute a fundamental source of information in the medical domain. They are used daily both by practitioners in the area, as well as in academia. Several resources of this kind are available, e.g. CIE, SnomedCT or UMLS (Unified Medical Language System). These terminological databases are of high quality due to them being the result of collaborative expert knowledge. However, they may show certain drawbacks in terms of faithfully representing the ever-changing medical domain. Therefore, systems aimed at capturing novel terminological knowledge in heterogeneous text sources, and able to include them in standard terminologies have the potential to add great value to such repositories. This paper presents, first, Savana, a Biomedical Information Extraction system which, combined with a validation phase carried out by medical practitioners, is used to populate the Spanish branch of SnomedCT with novel knowledge. Second, we describe and evaluate a system which, given a novel medical term, finds its most likely hypernym, thus becoming an enabler in the task of terminological database enrichment and expansion., This work is partially funded by the Spanish Ministry of Economy and Competitiveness under the following sponsorships: Maria de Maeztu Units of Excellence Programme (MDM-2015-0502), and TUNER project (TIN2015-65308-C5-5-R, MINECO/FEDER, UE).
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Un detector de la unidad central de un texto basado en técnicas de aprendizaje automático en textos científicos para el euskera

  • Bengoetxea, Kepa
  • Atutxa, Aitziber
  • Iruskieta, Mikel
En este artículo presentamos el primer detector de la Unidad Central (UC) de resúmenes científicos en euskera basado en técnicas de aprendizaje automático. Después de segmentar el texto en unidades de discurso elementales, la detección de la unidad central es crucial para anotar de forma más fiable la estructura relacional de textos bajo la Teoría de la Estructura Retórica o Rhetorical Structure Theory (RST). Además, la unidad central puede ser explotada en diversas tareas como resumen automático, tareas de pregunta y respuesta o análisis del sentimiento. Los resultados obtenidos demuestran que las técnicas de aprendizaje automático superan a las técnicas basadas en reglas a pesar del pequeño tamaño del corpus y de la heterogeneidad de los dominios que éste muestra, dejando todavía lugar para mejoras y desarrollo., Este trabajo a sido financiado en parte por el siguiente proyecto: TIN2015-65308-C5-1-R (MINECO/FEDER).
Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Publicación Artículo científico (JournalArticle)

Introducing idioms in the Galician WordNet: methods, problems and results

  • Álvarez de la Granja, María
  • Gómez Clemente, Xosé María
  • Gómez Guinovart, Xavier
This study describes the introduction of verbal idioms in the Galician language version (Galnet) of the semantic network WordNet; a network that does not traditionally include many phraseological units. To enhance Galnet, a list of 803 Galician verbal idioms was developed to then review each of them individually and assess whether they could be introduced in an existing WordNet synset (a group of synonyms expressing the same concept) or not. Of those 803 idioms, 490 (61%) could be included in this network. Besides, Galnet was enlarged with 750 extra verbal idioms, most of them synonyms or variants of the former. In this study, we present the working methodology for the experiment and an analysis of the results, to help understand the most important problems found when trying to introduce idioms in Galnet. We also discuss the reasons preventing the inclusion of some expressions, and the criteria used to introduce the idioms that finally made it into the network
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Interpretable semantic textual similarity: Finding and explaining differences between sentences

  • Lopez-Gazpio, Iñigo
  • Maritxalar, Montserrat
  • Gonzalez Agirre, Aitor
  • Rigau Claramunt, German
  • Uria, Larraitz
  • Agirre, Eneko
User acceptance of artificial intelligence agents might depend on their ability to explain their reasoning to the users. We focus on a specific text processing task, the Semantic Textual Similarity task (STS), where systems need to measure the degree of semantic equivalence between two sentences. We propose to add an interpretability layer (iSTS for short) formalized as the alignment between pairs of segments across the two sentences, where the relation between the segments is labeled with a relation type and a similarity score. This way, a system performing STS could use the interpretability layer to explain to users why it returned that specific score for the given sentence pair. We present a publicly available dataset of sentence pairs annotated following the formalization. We then develop an iSTS system trained on this dataset, which given a sentence pair finds what is similar and what is different, in the form of graded and typed segment alignments. When evaluated on the dataset, the system performs better than an informed baseline, showing that the dataset and task are well-defined and feasible. Most importantly, two user studies show how the iSTS system output can be used to automatically produce explanations in natural language. Users performed the two tasks better when having access to the explanations, providing preliminary evidence that our dataset and method to automatically produce explanations do help users understand the output of STS systems better., Aitor Gonzalez-Agirre and Inigo Lopez-Gazpio are supported by doctoral grants from MINECO. The work described in this project has been partially funded by MINECO in projects MUSTER (PCIN-2015-226) and TUNER (TIN 2015-65308-C5-1-R), as well as the Basque Government (A group research team, IT344-10).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Introducing idioms in the Galician WordNet: methods, problems and results

  • Álvarez de la Granja, María
  • Gómez Clemente, Xosé María
  • Gómez Guinovart, Xavier
This study describes the introduction of verbal idioms in the Galician language version (Galnet) of the semantic network WordNet; a network that does not traditionally include many phraseological units. To enhance Galnet, a list of 803 Galician verbal idioms was developed to then review each of them individually and assess whether they could be introduced in an existing WordNet synset (a group of synonyms expressing the same concept) or not. Of those 803 idioms, 490 (61%) could be included in this network. Besides, Galnet was enlarged with 750 extra verbal idioms, most of them synonyms or variants of the former. In this study, we present the working methodology for the experiment and an analysis of the results, to help understand the most important problems found when trying to introduce idioms in Galnet. We also discuss the reasons preventing the inclusion of some expressions, and the criteria used to introduce the idioms that finally made it into the network., This research has been supported by the Xunta de Galicia and the European Union (under grant GRC2013/40) and by the Ministry of Economy and Competitiveness of the Spanish Government (Project TUNER: Automatic domain adaptation for semantic processing, TIN2015-65308-C5-1-R).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Un detector de la unidad central de un texto basado en técnicas de aprendizaje automático en textos científicos para el euskera

  • Bengoetxea, Kepa
  • Atutxa, Aitziber
  • Iruskieta, Mikel
En este artículo presentamos el primer detector de la Unidad Central (UC) de resúmenes científicos en euskera basado en técnicas de aprendizaje automático. Después de segmentar el texto en unidades de discurso elementales, la detección de la unidad central es crucial para anotar de forma más fiable la estructura relacional de textos bajo la Teoría de la Estructura Retórica o Rhetorical Structure Theory (RST). Además, la unidad central puede ser explotada en diversas tareas como resumen automático, tareas de pregunta y respuesta o análisis del sentimiento. Los resultados obtenidos demuestran que las técnicas de aprendizaje automático superan a las técnicas basadas en reglas a pesar del pequeño tamaño del corpus y de la heterogeneidad de los dominios que éste muestra, dejando todavía lugar para mejoras y desarrollo., Este trabajo a sido financiado en parte por el siguiente proyecto: TIN2015-65308-C5-1-R (MINECO/FEDER).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Through the Eyes of VERTa

  • Comelles, Elisabet
  • Atserias, Jordi
This paper describes a practical demo of VERTa for Spanish. VERTa is an MT evaluation metric that combines linguistic features at different levels. VERTa has been developed for English and Spanish but can be easily adapted to other languages. VERTa can be used to evaluate adequacy, fluency and ranking of sentences. In this paper, VERTa’s modules are described briefly, as well as its graphical interface which provides information on VERTa’s performance and possible MT errors., This work has been funded by the Spanish Government (project TUNER, TIN2015-65308-C5-1-R).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Savana: a global information extraction and terminology expansion framework in the medical domain

  • Espinosa-Anke, Luis
  • Tello, Jorge
  • Pardo, Albert, 1964-
  • Medrano, Ignacio
  • Ureña, Alberto
  • Salcedo, Ignacio
  • Saggion, Horacio
Terminological databases constitute a fundamental source of information in the medical domain. They are used daily both by practitioners in the area, as well as in academia. Several resources of this kind are available, e.g. CIE, SnomedCT or UMLS (Unified Medical Language System). These terminological databases are of high quality due to them being the result of collaborative expert knowledge. However, they may show certain drawbacks in terms of faithfully representing the ever-changing medical domain. Therefore, systems aimed at capturing novel terminological knowledge in heterogeneous text sources, and able to include them in standard terminologies have the potential to add great value to such repositories. This paper presents, first, Savana, a Biomedical Information Extraction system which, combined with a validation phase carried out by medical practitioners, is used to populate the Spanish branch of SnomedCT with novel knowledge. Second, we describe and evaluate a system which, given a novel medical term, finds its most likely hypernym, thus becoming an enabler in the task of terminological database enrichment and expansion., This work is partially funded by the Spanish Ministry of Economy and Competitiveness under the following sponsorships: Maria de Maeztu Units of Excellence Programme (MDM-2015-0502), and TUNER project (TIN2015-65308-C5-5-R, MINECO/FEDER, UE).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Robust multilingual Named Entity Recognition with shallow semi-supervised features

  • Agerri, Rodrigo
  • Rigau Claramunt, German
We present a multilingual Named Entity Recognition approach based on a robust and general set of features across languages and datasets. Our system combines shallow local information with clustering semi-supervised features induced on large amounts of unlabeled text. Understanding via empirical experimentation how to effectively combine various types of clustering features allows us to seamlessly export our system to other datasets and languages. The result is a simple but highly competitive system which obtains state of the art results across five languages and twelve datasets. The results are reported on standard shared task evaluation data such as CoNLL for English, Spanish and Dutch. Furthermore, and despite the lack of linguistically motivated features, we also report best results for languages such as Basque and German. In addition, we demonstrate that our method also obtains very competitive results even when the amount of supervised data is cut by half, alleviating the dependency on manually annotated data. Finally, the results show that our emphasis on clustering features is crucial to develop robust out-of-domain models. The system and models are freely available to facilitate its use and guarantee the reproducibility of results., This work has been supported by the European projects NewsReader, EC/FP7/316404 and QTLeap – EC/FP7/610516, and by the Spanish Ministry of Economy and Competitiveness (MINECO) SKATER, Grant No. TIN2012-38584-C06-01 and TUNER, TIN2015-65308-C5-1-R.