Montserrat Marimon

The Spanish Resource Grammar: Pre-processing Strategy and Lexical Acquisition

This paper describes work on the development of an open-source HPSG grammar for Spanish implemented within the LKB system. Following a brief description of the main features of the grammar, we present our approach for pre-processing and ongoing research on automatic lexical acquisition.

Automatic Acquisition of Grammatical Types for Nouns

The work we present here is concerned with the acquisition of deep grammatical information for nouns in Spanish. The aim is to build a learner that can handle noise, but, more interestingly, that is able to overcome the problem of sparse data, especially important in the case of nouns. We have based our work on two main points. Firstly, we have used distributional evidences as features. Secondly, we made the learner deal with all occurrences of a word as a single complex unit. The obtained results show that grammatical features of nouns is a level of generalization that can be successfully approached with a Decision Tree learner.

New perspectives on moral reasoning

En los trabajos de Carol Gilligan aparece la etica del cuidad y la responsabilidad que tiene en cuenta los aspectos diferenciales y las necesidades particulares de las personas. Esta etica se contrapone a la de la justicia descrita por Kholberg, cuyas caracteristicas son el principio de igualdad y la no consideracion de las caracteristicas especificas de cada ser humano. Ambas eticas parecen, sin embargo, complementarias. El trabajo que se presenta incluye ambos enfoques eticos, en una situacion experimental en la cual se pide a sujetos de diferentes edades (desde los 6 anos hasta los 21) que tomen decisiones que implican optar por uno u otro de estos dos enfoques o integrar ambos. El tratamiento de los datos se realiza analizando los modelos organizadores que aparecen, lo cual permite diferenciar los elementos de la situacion que resultan mas destacables para los sujetos de cada edad, el significado que atribuyen a cada uno de ellos, la forma como los organizan para conferir un sentido al conjunto y las implicaciones que hacen derivar de todo ello. El estudio de la evolucion de los modelos organizadores en las diferentes edades muestra que la evolucion de las concepciones eticas esta lejos de ser lineal. Ello conduce a plantearnos el analisis de los procesos de construccion de la etica, mediante modelos teoricos que contemplen la complejidad y al abandono de modelos lineales incapaces de describir los fenomenos observados.

Automatic selection of hpsg-parsed sentences for treebank construction

This article presents an ensemble parse approach to detecting and selecting high-quality linguistic analyses output by a hand-crafted HPSG grammar of Spanish implemented in the LKB system. The approach uses full agreement (i.e., exact syntactic match) along with a MaxEnt parse selection model and a statistical dependency parser trained on the same data. The ultimate goal is to develop a hybrid corpus annotation methodology that combines fully automatic annotation and manual parse selection, in order to make the annotation task more efficient while maintaining high accuracy and the high degree of consistency necessary for any foreseen uses of a treebank.

Integrating shallow linguistic processing into a unification: based Spanish grammar

This paper describes to what extent deep processing may benefit from shallow processing techniques and it presents a NLP system which integrates a linguistic PoS tagger and chunker as a preprocessing module of a broad-coverage unification-based grammar of Spanish. Experiments show that the efficiency of the overall analysis improves significantly and that our system also provides robustness to the linguistic processing, while maintaining both the accuracy and the precision of the grammar.

YATS: Yet Another Text Simplifier

We present a text simplifier for English that has been built with open source software and has both lexical and syntactic simplification capabilities. The lexical simplifier uses a vector space model approach to obtain the most appropriate sense of a given word in a given context and word frequency simplicity measures to rank synonyms. The syntactic simplifier uses linguistically-motivated rule-based syntactic analysis and generation techniques that rely on part-of-speech tags and syntactic dependency information. Experimental results show good performance of the lexical simplification component when compared to a hard-to-beat baseline, good syntactic simplification accuracy, and according to human assessment, improvements over the best reported results in the literature for a system with same architecture as YATS.

Dependency structure annotation in the IULA Spanish LSP Treebank

This paper presents the IULA Spanish LSP Treebank, an open-source treebank of over 40,000 sentences, developed in the framework of the European project METANET4U. The IULA Spanish LSP Treebank is the first technical corpus of Spanish annotated at surface syntactic level, following the dependency grammar theory. We present the method we used to create the resource and the linguistic annotations that the treebank provides, using examples and comparing with similar resources. We also provide the statistics of the treebank and the evaluation results.

Youth purpose through the lens of the Theory of Organizing Models of Thinking

Abstract Purpose represents a unique opportunity for identifying and analyzing the complexity of human reasoning, considering that its constitution brings together cognitive, affective and social elements. In this article, we use the Theory of Organizing Models of Thinking (OMT), an epistemological and methodological approach based on developmental psychologist Jean Piaget’s work, to present a different perspective on how to analyze youth purpose and to explain the cognitive-emotional dynamics of reasoning in everyday thinking. We introduce OMT and its benefits, then explore the insights it can provide through examining seven OMTs used by Brazilian youth about their life purposes. These models focus on: consumerism and financial stability, interpersonal relationships, only work, work and family, idealization of work and family, altruistic intentions, and fragile purpose projections. These models show how reasoning and emotion are complexly linked in everyday thinking.

The CLARIN project: a scientific research infrastructure for the humanities and social sciences

This article presents the CLARIN (Common Language Resources and Technologies) project, a large-scale pan-European collaborative project that aims to promote the use of technological tools in research in the fields of the humanities and social sciences. CLARIN is one of the 35 projects selected by ESFRI (European Strategy Forum on Research Infrastructures) to form a list of infrastructures that need to be built, due to their importance in terms of research, in the next ten years. CLARIN aims to bring the benefits of shared and collaborative access to digital resources to the humanities and social sciences and increase use of specific analysis and exploitation computing tools for intelligent access to large databases. With this in mind, CLARIN is to create the infrastructure needed to offer generic access to large databases, alongside technological tools for the analysis and exploitation of the data. To do so, the project envisions a grid structure using web service and semantic web technologies, a single interface for accessing data and analysis tools, as well as the processing tools and other services needed. This interface, due to the fact that is designed to meet the common research aims in the humanities and social sciences, is easy to use by researchers from different fields without any prior knowledge of the technology involved.