Maca - a configurable tool to integrate Polish morphological data

There are a number of morphological analysers for Polish. Most of these, however, are non-free resources. What is more, different analysers employ different tagsets and tokenisation strategies. This situation calls for a simpleand universal framework to join different sources of morphological information, including the existing resources as well as user-provided dictionaries. We present such a configurable framework that allows to write simple configuration files that define tokenisation strategies and the behaviour of morphologicalanalysers, including simple tagset conversion.

Taking on new challenges in multi-word unit processing for Machine Translation

This paper discusses the qualitativecomparative evaluation performed on theresults of two machine translation systemswith different approaches to the processing ofmulti-word units. It proposes a solution forovercoming the difficulties multi-word unitspresent to machine translation by adopting amethodology that combines the lexicongrammar approach with OpenLogos ontologyand semantico-syntactic rules. The paper alsodiscusses the importance of a qualitativeevaluation metrics to correctly evaluate theperformance of machine translation engineswith regards to multi-word units.

Bootstrapping a statistical speech translator from a rule-based one

We describe a series of experiments in which we start with English to French and English to Japanese versions of an Open Source rule-based speech translation system for a medical domain, and bootstrap correspondign statistical systems. Comparative evaluation reveals that the rule-based systems are still significantly better than the statistical ones, despite the fact that considerable effort has been invested in tuning both the recognition and translation components; also, a hybrid system only marginally improved recall at the cost of a los in precision. The result suggests that rule-based architectures may still be preferable to statistical ones for safety-critical speech translation tasks.

A Widely Used Machine Translation Service and its Migration to a Free/Open-Source Solution : the Case of Softcatalà

Softcatalà is a non-profit associationcreated more than 10 years ago to fightthe marginalisation of the Catalan languagein information and communicationtechnologies. It has led the localisationof many applications and thecreation of a website which allows itsusers to translate texts between Spanishand Catalan using an external closed-sourcetranslation engine. Recently,the closed-source translation back-endhas been replaced by a free/open-sourcesolution completely managed by Softcatalà: the Apertium machine translationplatform and the ScaleMT web serviceframework. Thanks to the opennessof the new solution, it is possibleto take advantage of the huge amount ofusers of the Softcatalà translation serviceto improve it, using a series ofmethods presented in this paper. In addition,a study of the translations requestedby the users has been carriedout, and it shows that the translationback-end change has not affected theusage patterns.

An Italian to Catalan RBMT system reusing data from existing language pairs

This paper presents an Italian to CatalanRBMT system automatically built bycombining the linguistic data of theexisting pairs Spanish-Catalan andSpanish-Italian. A lightweight manualpostprocessing is carried out in order tofix inconsistencies in the automaticallyderived dictionaries and to add very frequentwords that are missing accordingto a corpus analysis. The system isevaluated on the KDE4 corpus and outperformsGoogle Translate by approximatelyten absolute points in terms ofboth TER and GTM.

ClInt: A bilingual Spanish-Catalan spoken corpus of clinical interviews

In this paper we present ClInt (Clinical Interview), a bilingual Spanish-Catalan spoken corpus that contains 15 hours of clinical interviews. It consists of audio files aligned with multiple-level transcriptions comprising orthographic, phonetic and morphological information, as well as linguistic and extralinguistic encoding. This is a previously non-existent resource for these languages and it offers a wide-ranging exploitation potential in a broad variety of disciplines such as Linguistics, Natural Language Processing and related fields.

CoCo, a web interface for corpora compilation

CoCo is a collaborative web interface for the compilation of linguistic resources. In this demo we are presenting one of its possible applications: paraphrase acquisition.

A hybrid approach to treebank construction

Este artículo describe investigación sobre los efectos de la desambiguación morfosintáctica usada como un preproceso de un analizador sint´actico profundo basado en HPSG, en el contexto del desarrollo de un treebank del español de código abierto, en el entorno de DELPH-IN. La anotación treebank se realiza manualmente tomando las decisiones apropiadas entre las opciones propuestas por el sistema y ordenadas por un módulo estadístico. Los experimentos presentados muestran que el uso de un etiquetador reduce la ambigüedad de las frases, y contribuye a limitar la cantidad de frases cuyo análisis sobrepasa a el límite de tiempo, y ayuda a al m´odulo estadístico a clasificar el árbol correcto entre los n mejores. Por un lado, nuestros resultados validan los beneficios ya reportados en la literatura de tal preproceso de análisis profundo con respecto a la velocidad, cobertura y precisión. Por otro lado, proponemos una estrategia basada en existentes herramientas de código abierto y recursos para desarrollar con alta consitencia treebanks de sintaxis profunda para idiomas con limitada disponibilidad de recursos lingüísticos.

El Proyecto CLARIN: Una infraestructura de investigación científica para las Humanidades y las Ciencias Sociales

En aquest article presentem CLARIN (Common Language Resources and Technologies), un projecte de col·laboració europea a gran escala l"objectiu del qual és potenciar l"ús d"instruments tecnològics en la recerca en els àmbits de les humanitats i les ciències socials. CLARIN és un dels trenta-cinc projectes seleccionats pel Comitè ESFRI (European Strategy Forum on Research Infraestructures) per a la llista de les infraestructures que s"han d"haver construït, per la seva importància per a la recerca, d"aquí a deu anys. CLARIN vol portar a les humanitats i a les ciències socials els beneficis de l"accés compartit i en col·laboració a recursos digitals, i també l"ús del còmput intensiu amb instruments específics d"anàlisi i explotació per a l"accés intel·ligent a grans bases de dades. Amb aquest objectiu, CLARIN crearà la infraestructura necessària per a poder donar un accés genèric a grans bancs de dades i als instruments d"anàlisi i explotació d"aquestes dades mitjançant la utilització de tecnologia. Per a això implementarà, en una estructura de xarxa grid, i mitjançant tecnologia de serveis web i de web semàntic, una única interfície d"accés a les dades i als instruments d"anàlisi, i també a eines de processament i altres serveis necessaris. Aquesta interfície, pel fet de ser dissenyada per a servir els objectius comuns de la recerca en humanitats i ciències socials, en facilitarà l"ús a investigadors de diferents àmbits sense necessitat de tenir coneixements sobre les tecnologies implicades.

The Tibidabo Treebank

En este artículo presentamos el desarrollo de un nuevo recurso de código abierto para el español: el treebank Tibidabo. La anotación se está llevando a cabo de forma semiautomática en la que, en primer lugar, el corpus es analizado automaticamente con una gramática simbólica del español basada en HPSG e implementada en el sistema Linguistic Knowledge Builder, y, en segundo lugar, los resultados del proceso de análisis se desambiguan manualmente. La existencia del treebank Tibidabo nos permitirá futuros trabajos de investigación para el desarrollo y evaluación de una arquitectura híbrida que combine métodos simbólicos y estadísticos para el PLN, así como investigaciones orientadas a la hibridización de técnicas de bajo y alto nivel para el PLN.

Opinion Mining

In this thesis we study the field of opinion mining by giving a comprehensive review of the available research that has been done in this topic. Also using this available knowledge we present a case study of a multilevel opinion mining system for a student organization's sales management system. We describe the field of opinion mining by discussing its historical roots, its motivations and applications as well as the different scientific approaches that have been used to solve this challenging problem of mining opinions. To deal with this huge subfield of natural language processing, we first give an abstraction of the problem of opinion mining and describe the theoretical frameworks that are available for dealing with appraisal language. Then we discuss the relation between opinion mining and computational linguistics which is a crucial pre-processing step for the accuracy of the subsequent steps of opinion mining. The second part of our thesis deals with the semantics of opinions where we describe the different ways used to collect lists of opinion words as well as the methods and techniques available for extracting knowledge from opinions present in unstructured textual data. In the part about collecting lists of opinion words we describe manual, semi manual and automatic ways to do so and give a review of the available lists that are used as gold standards in opinion mining research. For the methods and techniques of opinion mining we divide the task into three levels that are the document, sentence and feature level. The techniques that are presented in the document and sentence level are divided into supervised and unsupervised approaches that are used to determine the subjectivity and polarity of texts and sentences at these levels of analysis. At the feature level we give a description of the techniques available for finding the opinion targets, the polarity of the opinions about these opinion targets and the opinion holders. Also at the feature level we discuss the various ways to summarize and visualize the results of this level of analysis. In the third part of our thesis we present a case study of a sales management system that uses free form text and that can benefit from an opinion mining system. Using the knowledge gathered in the review of this field we provide a theoretical multi level opinion mining system (MLOM) that can perform most of the tasks needed from an opinion mining system. Based on the previous research we give some hints that many of the laborious market research tasks that are done by the sales force, which uses this sales management system, can improve their insight about their partners and by that increase the quality of their sales services and their overall results.

Rule-based machine translation between Bulgarian and Macedonian

This paper describes the development of a two-way shallow-transfer rule-based machine translation system between Bulgarian and Macedonian. It gives an account of the resources and the methods used for constructing the system, including the development of monolingual and bilingual dictionaries, syntactic transfer rules and constraint grammars. An evaluation of thesystem's performance was carried out and compared to another commercially available MT system for the two languages. Some future work was suggested.

Biomedical Event Extraction with Machine Learning

Biomedical natural language processing (BioNLP) is a subfield of natural language processing, an area of computational linguistics concerned with developing programs that work with natural language: written texts and speech. Biomedical relation extraction concerns the detection of semantic relations such as protein-protein interactions (PPI) from scientific texts. The aim is to enhance information retrieval by detecting relations between concepts, not just individual concepts as with a keyword search. In recent years, events have been proposed as a more detailed alternative for simple pairwise PPI relations. Events provide a systematic, structural representation for annotating the content of natural language texts. Events are characterized by annotated trigger words, directed and typed arguments and the ability to nest other events. For example, the sentence “Protein A causes protein B to bind protein C” can be annotated with the nested event structure CAUSE(A, BIND(B, C)). Converted to such formal representations, the information of natural language texts can be used by computational applications. Biomedical event annotations were introduced by the BioInfer and GENIA corpora, and event extraction was popularized by the BioNLP'09 Shared Task on Event Extraction. In this thesis we present a method for automated event extraction, implemented as the Turku Event Extraction System (TEES). A unified graph format is defined for representing event annotations and the problem of extracting complex event structures is decomposed into a number of independent classification tasks. These classification tasks are solved using SVM and RLS classifiers, utilizing rich feature representations built from full dependency parsing. Building on earlier work on pairwise relation extraction and using a generalized graph representation, the resulting TEES system is capable of detecting binary relations as well as complex event structures. We show that this event extraction system has good performance, reaching the first place in the BioNLP'09 Shared Task on Event Extraction. Subsequently, TEES has achieved several first ranks in the BioNLP'11 and BioNLP'13 Shared Tasks, as well as shown competitive performance in the binary relation Drug-Drug Interaction Extraction 2011 and 2013 shared tasks. The Turku Event Extraction System is published as a freely available open-source project, documenting the research in detail as well as making the method available for practical applications. In particular, in this thesis we describe the application of the event extraction method to PubMed-scale text mining, showing how the developed approach not only shows good performance, but is generalizable and applicable to large-scale real-world text mining projects. Finally, we discuss related literature, summarize the contributions of the work and present some thoughts on future directions for biomedical event extraction. This thesis includes and builds on six original research publications. The first of these introduces the analysis of dependency parses that leads to development of TEES. The entries in the three BioNLP Shared Tasks, as well as in the DDIExtraction 2011 task are covered in four publications, and the sixth one demonstrates the application of the system to PubMed-scale text mining.

Text Summarization by Sentence Extraction and Syntactic Pruning

Nous présentons une méthode hybride pour le résumé de texte, en combinant l'extraction de phrases et l'élagage syntaxique des phrases extraites. L'élagage syntaxique est effectué sur la base d’une analyse complète des phrases selon un parseur de dépendances, analyse réalisée par la grammaire développée au sein d'un logiciel commercial de correction grammaticale, le Correcteur 101. Des sous-arbres de l'analyse syntaxique sont supprimés quand ils sont identifiés par les relations ciblées. L'analyse est réalisée sur un corpus de divers textes. Le taux de réduction des phrases extraites est d’en moyenne environ 74%, tout en conservant la grammaticalité ou la lisibilité dans une proportion de plus de 64%. Étant donné ces premiers résultats sur un ensemble limité de relations syntaxiques, cela laisse entrevoir des possibilités pour une application de résumé automatique de texte.

A Document Browsing Tool Based on Book Indexes

This research project is a contribution to the global field of information retrieval, specifically, to develop tools to enable information access in digital documents. We recognize the need to provide the user with flexible access to the contents of large, potentially complex digital documents, with means other than a search function or a handful of metadata elements. The goal is to produce a text browsing tool offering a maximum of information based on a fairly superficial linguistic analysis. We are concerned with a type of extensive single-document indexing, and not indexing by a set of keywords (see Klement, 2002, for a clear distinction between the two). The desired browsing tool would not only give at a glance the main topics discussed in the document, but would also present relationships between these topics. It would also give direct access to the text (via hypertext links to specific passages). The present paper, after reviewing previous research on this and similar topics, discusses the methodology and the main characteristics of a prototype we have devised. Experimental results are presented, as well as an analysis of remaining hurdles and potential applications.