Génération de résumés par abstraction

Cette thèse présente le résultat de plusieurs années de recherche dans le domaine de la génération automatique de résumés. Trois contributions majeures, présentées sous la forme d'articles publiés ou soumis pour publication, en forment le coeur. Elles retracent un cheminement qui part des méthodes par extraction en résumé jusqu'aux méthodes par abstraction. L'expérience HexTac, sujet du premier article, a d'abord été menée pour évaluer le niveau de performance des êtres humains dans la rédaction de résumés par extraction de phrases. Les résultats montrent un écart important entre la performance humaine sous la contrainte d'extraire des phrases du texte source par rapport à la rédaction de résumés sans contrainte. Cette limite à la rédaction de résumés par extraction de phrases, observée empiriquement, démontre l'intérêt de développer d'autres approches automatiques pour le résumé. Nous avons ensuite développé un premier système selon l'approche Fully Abstractive Summarization, qui se situe dans la catégorie des approches semi-extractives, comme la compression de phrases et la fusion de phrases. Le développement et l'évaluation du système, décrits dans le second article, ont permis de constater le grand défi de générer un résumé facile à lire sans faire de l'extraction de phrases. Dans cette approche, le niveau de compréhension du contenu du texte source demeure insuffisant pour guider le processus de sélection du contenu pour le résumé, comme dans les approches par extraction de phrases. Enfin, l'approche par abstraction basée sur des connaissances nommée K-BABS est proposée dans un troisième article. Un repérage des éléments d'information pertinents est effectué, menant directement à la génération de phrases pour le résumé. Cette approche a été implémentée dans le système ABSUM, qui produit des résumés très courts mais riches en contenu. Ils ont été évalués selon les standards d'aujourd'hui et cette évaluation montre que des résumés hybrides formés à la fois de la sortie d'ABSUM et de phrases extraites ont un contenu informatif significativement plus élevé qu'un système provenant de l'état de l'art en extraction de phrases.

JSreal : un réalisateur de texte pour la programmation web

Site web associé au mémoire: http://daou.st/JSreal

Style Guidelines for Naming and Labeling Ontologies in the Multilingual Web

In the context of the Semantic Web, natural language descriptions associated with ontologies have proven to be of major importance not only to support ontology developers and adopters, but also to assist in tasks such as ontology mapping, information extraction, or natural language generation. In the state-of-the-art we find some attempts to provide guidelines for URI local names in English, and also some disagreement on the use of URIs for describing ontology elements. When trying to extrapolate these ideas to a multilingual scenario, some of these approaches fail to provide a valid solution. On the basis of some real experiences in the translation of ontologies from English into Spanish, we provide a preliminary set of guidelines for naming and labeling ontologies in a multilingual scenario.

Generating descriptions that summarize geospatial and temporal data

Effective data summarization methods that use AI techniques can help humans understand large sets of data. In this paper, we describe a knowledge-based method for automatically generating summaries of geospatial and temporal data, i.e. data with geographical and temporal references. The method is useful for summarizing data streams, such as GPS traces and traffic information, that are becoming more prevalent with the increasing use of sensors in computing devices. The method presented here is an initial architecture for our ongoing research in this domain. In this paper we describe the data representations we have designed for our method, our implementations of components to perform data abstraction and natural language generation. We also discuss evaluation results that show the ability of our method to generate certain types of geospatial and temporal descriptions.

Enriquecimiento de fuentes de datos con descripciones lingüísticas mediante bases de datos geográficas externas

El presente trabajo se ha centrado en la investigación de soluciones para automatizar la tarea del enriquecimiento de fuentes de datos sobre redes de sensores con descripciones lingüísticas, con el fin de facilitar la posterior generación de textos en lenguaje natural. El uso de descripciones en lenguaje natural facilita el acceso a los datos a una mayor diversidad de usuarios y, como consecuencia, permite aprovechar mejor las inversiones en redes de sensores. En el trabajo se ha considerado el uso de bases de datos abiertas para abordar la necesidad de disponer de un gran volumen y diversidad de conocimiento geográfico. Se ha analizado también el enriquecimiento de datos dentro de enfoques metodológicos de curación de datos y métodos de generación de lenguaje natural. Como resultado del trabajo, se ha planteado un método general basado en una estrategia de generación y prueba que incluye una forma de representación y uso del conocimiento heurístico con varias etapas de razonamiento para la construcción de descripciones lingüísticas de enriquecimiento de datos. En la evaluación de la propuesta general se han manejado tres escenarios, dos de ellos para generación de referencias geográficas sobre redes de sensores complejas de dimensión real y otro para la generación de referencias temporales. Los resultados de la evaluación han mostrado la validez práctica de la propuesta general exhibiendo mejoras de rendimiento respecto a otros enfoques. Además, el análisis de los resultados ha permitido identificar y cuantificar el impacto previsible de diversas líneas de mejora en bases de datos abiertas. ABSTRACT This work has focused on the search for solutions to automate the task of enrichment sensor-network-based data sources with textual descriptions, so as to facilitate the generation of natural language texts. Using natural language descriptions facilitates data access to a wider range of users and, therefore, allows better leveraging investments in sensor networks. In this work we have considered the use of open databases to address the need for a large volume and diversity of geographical knowledge. We have also analyzed data enrichment in methodological approaches and data curation methods of natural language generation. As a result, it has raised a general method based on a strategy of generating and testing that includes a representation using heuristic knowledge with several stages of reasoning for the construction of linguistic descriptions of data enrichment. In assessing the overall proposal three scenarios have been addressed, two of them in the environmental domain with complex sensor networks and another real dimension in the time domain. The evaluation results have shown the validity and practicality of our proposal, showing performance improvements over other approaches. Furthermore, the analysis of the results has allowed identifying and quantifying the expected impact of various lines of improvement in open databases.

The role of automated feedback in training and retaining biological recorders for citizen science

© 2016 The Authors. Conservation Biology published by Wiley Periodicals, Inc. on behalf of Society for Conservation Biology. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. Acknowledgments The authors thank H. H. Nguyen for his early development work on the BeeWatch interface; E. O'Mahony, I. Pearce, and R. Comont for identifying numerous photographed bumblebees; B. Darvill, D. Ewing, and G. Perkins for enabling our partnership with the Bumblebee Conservation Trust; and S. Blake for his investments in developing the NLG feedback. The study was part of the Digital Conservation project of dot.rural, the University of Aberdeen's Digital Economy Research Hub, funded by RCUK (grant reference EP/G066051/1).

Using WYSIWYM to Create an Open-ended Interface for the Semantic Grid

Publisher PDF

Direction giving: an attempt to increase user engagement

Publisher PDF

Summarising News Stories for Children

Postprint

Learning to Interpret and Generate Instructional Recipes

Thesis (Ph.D.)--University of Washington, 2016-08

A novel concept-level approach for ultra-concise opinion summarization

The Web 2.0 has resulted in a shift as to how users consume and interact with the information, and has introduced a wide range of new textual genres, such as reviews or microblogs, through which users communicate, exchange, and share opinions. The exploitation of all this user-generated content is of great value both for users and companies, in order to assist them in their decision-making processes. Given this context, the analysis and development of automatic methods that can help manage online information in a quicker manner are needed. Therefore, this article proposes and evaluates a novel concept-level approach for ultra-concise opinion abstractive summarization. Our approach is characterized by the integration of syntactic sentence simplification, sentence regeneration and internal concept representation into the summarization process, thus being able to generate abstractive summaries, which is one the most challenging issues for this task. In order to be able to analyze different settings for our approach, the use of the sentence regeneration module was made optional, leading to two different versions of the system (one with sentence regeneration and one without). For testing them, a corpus of 400 English texts, gathered from reviews and tweets belonging to two different domains, was used. Although both versions were shown to be reliable methods for generating this type of summaries, the results obtained indicate that the version without sentence regeneration yielded to better results, improving the results of a number of state-of-the-art systems by 9%, whereas the version with sentence regeneration proved to be more robust to noisy data.

Link discovery for Chinese/English cross-language web information retrieval

Nowadays people heavily rely on the Internet for information and knowledge. Wikipedia is an online multilingual encyclopaedia that contains a very large number of detailed articles covering most written languages. It is often considered to be a treasury of human knowledge. It includes extensive hypertext links between documents of the same language for easy navigation. However, the pages in different languages are rarely cross-linked except for direct equivalent pages on the same subject in different languages. This could pose serious difficulties to users seeking information or knowledge from different lingual sources, or where there is no equivalent page in one language or another. In this thesis, a new information retrieval task—cross-lingual link discovery (CLLD) is proposed to tackle the problem of the lack of cross-lingual anchored links in a knowledge base such as Wikipedia. In contrast to traditional information retrieval tasks, cross language link discovery algorithms actively recommend a set of meaningful anchors in a source document and establish links to documents in an alternative language. In other words, cross-lingual link discovery is a way of automatically finding hypertext links between documents in different languages, which is particularly helpful for knowledge discovery in different language domains. This study is specifically focused on Chinese / English link discovery (C/ELD). Chinese / English link discovery is a special case of cross-lingual link discovery task. It involves tasks including natural language processing (NLP), cross-lingual information retrieval (CLIR) and cross-lingual link discovery. To justify the effectiveness of CLLD, a standard evaluation framework is also proposed. The evaluation framework includes topics, document collections, a gold standard dataset, evaluation metrics, and toolkits for run pooling, link assessment and system evaluation. With the evaluation framework, performance of CLLD approaches and systems can be quantified. This thesis contributes to the research on natural language processing and cross-lingual information retrieval in CLLD: 1) a new simple, but effective Chinese segmentation method, n-gram mutual information, is presented for determining the boundaries of Chinese text; 2) a voting mechanism of name entity translation is demonstrated for achieving a high precision of English / Chinese machine translation; 3) a link mining approach that mines the existing link structure for anchor probabilities achieves encouraging results in suggesting cross-lingual Chinese / English links in Wikipedia. This approach was examined in the experiments for better, automatic generation of cross-lingual links that were carried out as part of the study. The overall major contribution of this thesis is the provision of a standard evaluation framework for cross-lingual link discovery research. It is important in CLLD evaluation to have this framework which helps in benchmarking the performance of various CLLD systems and in identifying good CLLD realisation approaches. The evaluation methods and the evaluation framework described in this thesis have been utilised to quantify the system performance in the NTCIR-9 Crosslink task which is the first information retrieval track of this kind.

Behavioral Model Generation from Use Cases Based on Ontology Mapping and GRASP Patterns

This paper contributes a new approach for developing UML software designs from Natural Language (NL), making use of a meta-domain oriented ontology, well established software design principles and Natural Language Processing (NLP) tools. In the approach described here, banks of grammatical rules are used to assign event flows from essential use cases. A domain specific ontology is also constructed, permitting semantic mapping between the NL input and the modeled domain. Rules based on the widely-used General Responsibility Assignment Software Principles (GRASP) are then applied to derive behavioral models.

BIOMEDICAL LANGUAGE UNDERSTANDING AND EXTRACTION (BLUE-TEXT): A MINIMAL SYNTACTIC, SEMANTIC METHOD

Clinical text understanding (CTU) is of interest to health informatics because critical clinical information frequently represented as unconstrained text in electronic health records are extensively used by human experts to guide clinical practice, decision making, and to document delivery of care, but are largely unusable by information systems for queries and computations. Recent initiatives advocating for translational research call for generation of technologies that can integrate structured clinical data with unstructured data, provide a unified interface to all data, and contextualize clinical information for reuse in multidisciplinary and collaborative environment envisioned by CTSA program. This implies that technologies for the processing and interpretation of clinical text should be evaluated not only in terms of their validity and reliability in their intended environment, but also in light of their interoperability, and ability to support information integration and contextualization in a distributed and dynamic environment. This vision adds a new layer of information representation requirements that needs to be accounted for when conceptualizing implementation or acquisition of clinical text processing tools and technologies for multidisciplinary research. On the other hand, electronic health records frequently contain unconstrained clinical text with high variability in use of terms and documentation practices, and without commitmentto grammatical or syntactic structure of the language (e.g. Triage notes, physician and nurse notes, chief complaints, etc). This hinders performance of natural language processing technologies which typically rely heavily on the syntax of language and grammatical structure of the text. This document introduces our method to transform unconstrained clinical text found in electronic health information systems to a formal (computationally understandable) representation that is suitable for querying, integration, contextualization and reuse, and is resilient to the grammatical and syntactic irregularities of the clinical text. We present our design rationale, method, and results of evaluation in processing chief complaints and triage notes from 8 different emergency departments in Houston Texas. At the end, we will discuss significance of our contribution in enabling use of clinical text in a practical bio-surveillance setting.