Search

We present a detailed analysis of a graph- based annotation strategy that we employed to annotate a corpus of 11,292 real-world En- glish to Spanish automatic translations with relative (ranking) and absolute (adequate/non- adequate) quality assessments. The proposed approach, inspired by previous work in In- teractive Evolutionary Computation and Inter- active Genetic Algorithms, results in a sim- pler and faster annotation process. We em- pirically compare the method against a tra- ditional, explicit ranking approach, and show that the graph-based strategy: 1) is consider- ably faster, and 2) produces consistently more reliable annotations

This paper presents our experiments in question answering for speech corpora. These experiments focus on improving the answer extraction step of the QA process. We present two approaches to answer extraction in question answering for speech corpora that apply machine learning to improve the coverage and precision of the extraction. The first one is a reranker that uses only lexical information, the second one uses dependency parsing to score robust similarity between syntactic structures. Our experimental results show that the proposed learning models improve our previous results using only hand-made ranking rules with small syntactic information. Moreover, this results show also that a dependency parser can be useful for speech transcripts even if it was trained with written text data from a news collection. We evaluate the system on manual transcripts of speech from EPPS English corpus and a set of questions transcribed from spontaneous oral questions. This data belongs to the CLEF 2009 track on QA on speech transcripts (QAst).

En este artículo presentamos una metodología para la adquisición automática de información léxica y morfosintáctica a partir de corpus sin anotar. El sistema utiliza información sobre la morfología flexiva de la lengua a tratar, así como información léxica y morfosintáctica de las palabras pertenecientes a clases no flexivas y de las palabras cuya flexión no corresponde a paradigmas regulares. Se trata de un sistema en desarrollo por lo que las evaluaciones que incluímos son preliminares. This paper presents a methodology for the automatic acquisition of lexical and morpho-syntactic information from raw corpora. The system uses information about the inflectional morohology of the language and lexical and morho-syntactic information of the words belonging to non-inflectional categories and of the words not belonging to regular paradigms. En aquest article presentem una metodologia per a l'adquisició automàtica d'informació lèxica i morfosintàctica a partir de corpus sense anotar. El sistema utilitza informació sobre la morfologia flexiva de la llengua a tractar, així com informació lèxica i morfosintàctica de les paraules pertanyents a classes no flexives i de les paraules la flexió de les quals no correspon a paradigmes regulars. Es tracta d'un sistema en desenvolupament pel que les avaluacions que incloem són preliminars.

The present report describes a rewrite system, based on the one proposed by Patrick Saint-Dizier in 1985, whose main goal is to reorder the range of quantifiers introduced by determiners in natural language sentences, in order to generate all valid semantic interpretations. The paper starts by describing Patrick Saint-Dizier's method and analyzing, on the one hand, in which situations it works properly and, on the other hand, the problems it presents. Solutions to these problems are presented later and a whole rewrite system for the Catalan language is proposed. Finally, several realistic examples are presented and an appraisal of our method is done, pointing out its advantages, its limitations, and some open questions that can be considered in future works. El present treball descriu un sistema de reescriptura, basat en el proposat per Patrick Saint-Dizier l'any 1985, que permet reordenar el rang dels quantificadors introduïts pels determinants que apareixen en frases de llenguatge natural, amb l'objectiu de generar totes les interpretacions semàntiques vàlides. Es comença fent una descripció del mètode de Patrick Saint-Dizier, analitzant les situacions que resol satisfactòriament i també els problemes que presenta. A continuació es proposen solucions a aquests problemes i es descriu un nou sistema de reescriptura adaptat per la llengua catalana. Finalment es presenten alguns exemples de mida realista i es fa una valoració del comportament del mètode presentat, així com diversos apunts sobre possibles línees de treball en el futur.

We present a system developed for the CoNLL-2009 Shared Task (Hajic et al., 2009). We extend the Carreras (2007) parser to jointly annotate syntactic and semantic dependencies. This state-of-the-art parser factorizes the built tree in second-order factors. We include semantic dependencies in the factors and extend their score function to combine syntactic and semantic scores. The parser is coupled with an on-line averaged perceptron (Collins, 2002) as the learning method. Our averaged results for all seven languages are 71.49 macro F1, 79.11 LAS and 63.06 semantic F1.

En este artículo se presenta la metodología seguida en el proceso de anotación semántica automática (estructura argumental y papeles temáticos de los predicados verbales) del corpus CESS-ECE-CAT/ESP, así como la evaluación de los resultados obtenidos. A partir de un léxico verbal (1.482 verbos) con información sobre las funciones sintácticas de cada verbo y su proyección temático-argumental, se ha anotado automáticamente el treebank CESS-ECE aplicando un conjunto de reglas simples sobre los árboles sintácticos. Se ha conseguido anotar automáticamente el 60% de los argumentos y papeles temáticos, con un error muy bajo (inferior al 2%). Este índice de calidad elevado permite usar la presente metodología para semiautomatizar el proceso de anotación semántica del corpus, con el consiguiente ahorro en tiempo de anotación manual. Una vez completada la anotación este corpus podrá ser utilizado como fuente de información para los sistemas de anotación automática de papeles temáticos. In this paper we present the methodology followed in the automatic semantic annotation (argument structure and thematic roles of the verbal predicates) of the CESS-ECECAT/ ESP corpus. Building from a verbal lexicon (1,482 entries) with information about the syntactic functions and their projection to arguments and thematic roles, we present a set of simple rules to automatically enrich syntactic trees with semantic information. This procedure permits to automatically annotate 60% of the expected arguments and thematic roles with a fairly low error rate (below 2%). Given the high quality of the obtained results, we claim that this methodology provides substantial savings in manual annotation effort and allows a semiautomatic approach to corpus annotation. Once completed, the CESS-ECE corpus will permit researchers to develop complete systems for automatic Semantic Role Labeling of Catalan and Spanish.

Este trabajo aprovecha la naturaleza multilingüe de Wikipedia para construir sistemas de traducción especializados en diferentes áreas de conocimiento. En él se describen los procedimientos seguidos para extraer corpus paralelos de los artículos de Wikipedia y los mecanismos para su evaluación.

This master thesis is focused on the development of a system for automatically processing a large database of textual hotel reviews in natural language to extract relevant opinions from users on a series of predefined features of quality (service, food, location, etc) The information extracted has to be categorized according to polarity (positive/negative opinions) and arranged so that the final search application can use it to display complementary information of each hotel based on the extracted opinions. Initially a set of hotel reviews is data mined from online sources; a subset of this dataset is then filtered and manually annotated to create a corpus and to help with the creation of a taxonomy for the domain of hotel reviews. A system is then designed to detect, extract and evaluate opinions, and evaluated using the corpus built.

Generally, NLP tools use well-formed and annotated data to learn patterns by using machine learning techniques. However, in this work we will focus on the language used in an on-line platform for machine translation. In this area it is usual to have a framework such the following: a web-page which offer a service of translation between pairs of languages. The problem is that the casual users utilize the service to translate any type of text (cut and paste, single words, bad formatting, snipets, informal language, pre-traductions, etc.). Hence, in this situation we will find very often words with mistakes that make the system provides a bad translation because it is not able to understand the input. The main goal of our work is, once we have identified the problem of dealing with non-standard-input is to develop a robust PoS tagger from the SVMTagger.