Meritxell González

IPA and STOUT: Leveraging Linguistic and Source-based Features for Machine Translation Evaluation

This paper describes the UPC submissions to the WMT14 Metrics Shared Task : UPC-IPA and UPC-STOUT. These metrics use a collection of evaluation measures integrated in ASIYA, a toolkit for machine translation evaluation. In addition to some standard metrics, the two submissions take advantage of novel metrics that consider linguistic structures, lexical relationships, and semantics to compare both source and reference translation against the candidate translation. The new metrics are available for several target languages other than English. In the the official WMT14 evaluation, UPC-IPA and UPC-STOUT scored above the average in 7 out of 9 language pairs at the system level and 8 out of 9 at the segment level.

An information state-based dialogue manager for making voice web smarter

In this paper we propose the integration of intelligent components technologies (natural language and discourse management) in voice web interfaces to make them smarter. We describe how we have integrated reusable components of dialogue management and language processing in a multilingual voice system to improve its friendliness and portability. The dialogue management component deals with complex dialogue phenomena, such as user-initiative dialogues, and follows the information state-based theory. The resulting dialogue system supports friendly communication (through the telephone and the web) in several languages: English, Spanish, Catalan and Italian. The dialogue system has been adapted to guide the users to access online public administration services.

Integrating semantic web and language technologies to improve the online public administrations services

In this paper, we describe how domain ontologies are used in a dialogue system guiding the user to access web public administration contents. The current implementation of the system supports speech (through the telephone) and text mode in different languages (English, Spanish, Catalan and Italian).

The patents retrieval prototype in the MOLTO project

This paper describes the patents retrieval prototype developed within the MOLTO project. The prototype aims to provide a multilingual natural language interface for querying the content of patent documents. The developed system is focused on the biomedical and pharmaceutical domain and includes the translation of the patent claims and abstracts into English, French and German. Aiming at the best retrieval results of the patent information and text content, patent documents are preprocessed and semantically annotated. Then, the annotations are stored and indexed in an OWLIM semantic repository, which contains a patent specific ontology and others from different domains. The prototype, accessible online at http://molto-patents.ontotext.com, presents a multilingual natural language interface to query the retrieval system. In MOLTO, the multilingualism of the queries is addressed by means of the GF Tool, which provides an easy way to build and maintain controlled language grammars for interlingual translation in limited domains. The abstract representation obtained from the GF is used to retrieve both the matched RDF instances and the list of patents semantically related to the users search criteria. The online interface allows to browse the retrieved patents and shows on the text the semantic annotations that explain the reason why any particular patent has matched the users criteria.

A flexible dialogue system for enhancing web usability

In this paper, we study how the performance and usability of web dialogue systems could be enhanced by using an appropriate representation of the different types of knowledge involved in communication: general dialogue mechanisms, specific domain-restricted linguistic and conceptual knowledge and information on how well the communication process is doing. We describe the experiments carried out to analyze how to improve this knowledge representation in the web dialogue system we developed.

Using application-specific ontologies to improve performance in a bottom-up parser

This paper describes how the application specific knowledge represented in ontologies is used to improve the processing of user interventions in a multilingual dialogue system for multiple applications. The user interventions are processed by a left-corner parser performing syntactic and semantic analysis in parallel. The parser uses application-restricted grammars and lexicons obtained from ontologies representing the application specific knowledge. It also uses the knowledge of the dialogue context to select the grammar rules related to the dialogue focus.