Projects




ASSET-Intelligent Assistance for Everyone Everywhere

In the market of technological devices and advanced remote services, high-quality support that helps end-users to resolve difficulties in using such products represents a decisive factor for economic agents in the industry. This project aims to lower the barrier to entry into the market, and thus increase the potential for success of new business projects whose activities are focused on more intensive knowledge and technology. In order to meet this goal, the project will investigate and develop the innovative application of leading technologies to significantly increase the degree of automation in the full-support service provided by Higher Functions, a market leader in technological support.
Scientific Coordinator of the project: António Branco
Partners: Higher Functions, Lda, Portugal; University of Lisbon, Portugal
P2020: 3279


QTLeap - Quality Translation by Deep Language Engineering Approaches

The goal of QTLeap project is to research on and deliver an articulated methodology for machine translation that explores deep language engineering approaches in view of breaking the way to translations of higher quality.
Head of Project: António Branco
Partners: University of Lisbon, Portugal; DFKI-German Research Center for Artificial Intelligence, Germany; Charles University in Prague, Czech republic; Bulgarian Academy of Sciences, Bulgaria; Humboldt University Berlin, Germany; University of Basque Country, Spain; University of Groningen, The Netherlands; Higher Functions, Lda, Portugal
ECFP7: 610516


PARSEME-Parsing and Multi-word Expresssions

PARSEME is an interdisciplinary scientific network devoted to the role of multi-word expressions (MWEs) in parsing. It gathers interdisciplinary experts (linguists, computational linguists, computer scientists, psycholinguists, and industrials) from 31 countries which have signed the Memorandum of Understanding. It represents 30 languages and 6 dialects from 10 language families. It covers different parsing frameworks: CCG (Combinatory Categorial Grammar), DG (Dependency Grammar), GG (Generative Grammar), HPSG (Head-driven Phrase Structure Grammar), LFG (Lexical Functional Grammar), TAG (Tree Adjoining Grammar), ... It addresses different methodologies (symbolic, probabilistic and hybrid parsing) and language technology applications (machine translation, information retrieval, ...).
Head of the Portuguese participation: António Branco
COST Action: IC1207


DP4LT - Deep Language Engineering for Language Technology

The central aim of the DP4LT project is to improve the robustness of deep language processing by tackling the issue of lexical creativity with new methods, namely with classifiers relying on linguistically informed, structured features. Other important goals are the construction or enhancement of datasets, tools and deep grammar for the processing of Portuguese, to be released as resources to support research and innovation.
Head of Project: António Branco
PTDC/EEI-SII/1940/2012


S4S - Smartphones for Seniors

Smartphones for Seniors (S4S), is a Portuguese collaborative R&D project coordinated by Microsoft, which aims to provide more adapted technology to the senior population  in mobile scenarios, by customizing the user interfaces of the basic functions of a Windows Phone 7 smartphone. It also includes the redesign of more advanced tools such as video calling and communication with social media in order to allow remote interaction with users of social networks, as well as synchronous or asynchronous conversation, covering also audiovisual communication.
Head of Project: Daniela Braga
QREN


METANET4U - Enhancing the European Linguistic Infrastructure

METANET4U is a European project aiming at supporting language technology for European languages and multilingualism. It is a project in the META-NET Network of Excellence, a cluster of projects aiming at fostering the mission of META. META is the Multilingual Europe Technology Alliance, dedicated to building the technological foundations of a multilingual European information society.
Head of Project: António Branco
Partners: University of Lisbon, Portugal; Instituto Superior Técnico, Portugal; The University of Manchester, United Kingdom; University "Alexandru Ioan Cuza", Romania; Romanian Academy, Romania; University of Malta; Technical University of Catalonia, Spain; Universitat Pompeu Fabra, Spain
ECICTPSP:270893


CLARIN - Common Language Resources and Technology Infrastructure

The CLARIN project is a large-scale pan-European collaborative effort to create, coordinate and make language resources and technology available and readily usable under an ESFRI Research Infrastructure. CLARIN offers scholars the tools to allow computer-aided language processing, addressing one or more of the multiple roles language plays (i.e. carrier of cultural content and knowledge, instrument of communication, component of identity and object of study) in the Humanities and Social Sciences.
Head of Project: Steven Krawer
Head of project at the Univ Lisbon and of Portuguese CLARIN network: António Branco
ECFP7:212230


SemanticShare - Resources and Tools for Semantic Processing

A central result of SemanticShare is an annotated corpus of Portuguese, part of it aligned with similar corpora for others languages.
These texts are annotated with manually verified grammatical representations. These internal representations are informed by advanced linguistic analysis, encompass different layers of linguistic information and are accessed under different views. These views correspond to corpora of the last and next generations:
- LogicalFormBank: With sentence-level semantic representations;
- PropBank: With phrases labeled with semantic functions and roles.

Other participants: Pontifícia Universidade Católica do Rio Grande do Sul, Brazil.
Head of project: António Branco
FCT/PTDC/PLP/81157/2006


LT4eL - Language Technology for E-learning

The central goal of the LT4eL project is to improve on existing eLearning platforms by allowing for the construction of user specific courses through the semantic querying for topics of interests. Specifically, we will enable the creation of personalized content and will allow for decentralization and co-operation of content management as well as for retrieval of information in different languages.
In order to reach this objective, we will integrate significant research which has been carried out in the area of Language Technology and the Semantic Web. Specifically, we will improve the retrieval of static and dynamic content by employing Language Technology resources and tools  for the semi-automatic generation of descriptive metadata.
Other participants: Utrecht University (coord.), The Netherlands, University of Tübingen, University of Cologne, University of  Hamburg, Germany, University “Al.I.Cuza” of Iasi, Romenia, Charles University Prague, Check Republic, Bulgarian Academy of Sciences, Bulgaria, Polish Academy of Sciences, Poland, University of Malta, Malta, Zürich University of Applied Sciences Winterthur, Switzerland, Open University, UK.
Head of Project: Paola Monachesi
Head of project at the Univ Lisbon: António Branco
ECFP6: STREP 27391


QueXting - Question Answering in the Portuguese Web

The central goal of the QueXting project is to contribute for an improved acess to information by users of the Portuguese web by means of making freely acessible a state of the art, online Question Answering (QA) service allowing to obtain answers to questions worded in plain Portuguese on the basis of the information contained in the Portuguese Web. Instrumental to this goal is the rapid ramp-up of the underlying QA engine by:
- Adopting language-independent system architecture and taking advantage of the search engines for document retrieval available online;
- Exploiting the NLP tools for Portuguese that our group have developed and use them as the components required to be geared to the Portuguese language.
Concomintantly, the project aims at fostering R&D on QA by developing reusable Portuguese-specific Question/Answer taxonomy, Question/Answer dictionary, and ontologies, and by using the resulting QA engine as a platform for training, teaching and further advanced R&D on QA.
Head of project: António Branco
FCT/POSI/PLP/61490/2004


GramaXing - Computational Grammar for Deep Linguistic Processing of Portuguese

Goals: The central goal of GramaXing is to contribute to the enhanced multilinguality of the semantic web and information society by developing a general purpose computational core grammar of Portuguese, the fifth language in the world in terms of native speakers. This grammar will perform automatic semantic analysis according to state of the art technology that supports the development of high-level natural language applications and semantic web tools. Another major goal of this project  is to join  Delphin, the world leading research initiative on advanced grammar engineering, and add Portuguese to the set of languages being addressed by this initiative.
Other participants: University of Minho, Portugal; Federal University of Santa Catarina, Brazil; and University of Saarland, Germany.
Head of project: António Branco
FCT/PLUS/PLP/50301/2003


PALPORT - Fine-grained Psycholinguistic Assessment of Aphasia and Other Language Impairments

Goals: The most common cause of Aphasic syndromes is the Cerebral Vascular Accident (CVA). CVAs are the main cause of death in the Portuguese population. It is estimated that 8% of our population over 50 years of age already suffered a CVA. Of these survivors, 80% to 90% were left with severe disabilities, namely language disorders. We propose to develop a computerized battery of psycholinguistic tests, capable of yielding a detailed psycholinguist characterization of language disorders, at the phonemic, morphological, lexical, sentential, prosodic and discourse levels, probing the written and the auditory code in both comprehension and production tasks.
Other participants: University of Coimbra, Faculdade de Psicologia e de Ciências da Educação (coord.), and Hospitais da Universidade de Coimbra.
Head of Project: Isabel Festas
Head of project at the Univ of Lisbon: António Branco (NLX Group)
FCT/RIPD/PSI/63557/2005


TagShare - Tagging and Shallow Processing Tools and Resources

Goals: Development of a set of linguistic resources and software component tools to support the computational processing of Portuguese. These resources and tools are geared to shallow morpho-syntactic processing: They are aimed at automatically associating lexemes with basic linguistic information that can be uncovered by means of computationally efficient procedures that look into the word structure and/or into a very limited amount of context (e.g. POS tagging, inflectional analysis, multi-word lexeme recognition, named entity recognition, etc.).
Other participants: CLUL-Center of Linguistics of the University of Lisbon.
Head of project: António Branco
FCT/POSI/PLP/47058/2002


LTRC - Language Typology Resource Center

Goals: Creation of web-acessible electronic archive for typological description, including research tools such as typological databases, language-typological expert systems, extensive scientific grammars, and corpora, etc.
Other participants: Utrecht University (coordinator), Max Planck Institute, University of Amsterdam, Nijmegen University, Leiden University, Tilburg University, Freie Univ. Berlin, Stockholm University, University of Surrey, University of Konstanz, University of Lancaster, ZAS Berlin.
Head of Project: Martin Evearert
Head of project at the Univ Lisbon: António Branco (NLX Group)
ECFP6: HPRI-CT-2001-40028


Nexing - Natural Negation Modeling and Processing

Goals: Improving the automated mapping between form and meaning, on the one hand, and between meaning and knowledge representation, on the other hand, concerning natural language negation.
Other participants: The IPCDVS-Institute for Cognitive Psychology of the Faculty of Psychology and Education Sciences of the Universiy of Coimbra; and the FCHS-Faculty of Human Sciences of the University of Algarve.
Head of project: António Branco
FCT/SAPIENS99/34076/1999