In this paper we discuss our participation to the 2013 Semeval Semantic Textual Similarity task. Our core features include (i) a set of metrics borrowed from automatic machine translation, originally intended to evaluate automatic against reference translations and (ii) an instance of explicit semantic analysis, built upon opening paragraphs of Wikipedia 2010 articles. Our similarity estimator ...

This paper presents I-agent system (Intelligible agent system) to improve multi-agent system (MAS) interoperability. It employs ontology management system and its inference ability to assist semantic translation of message content. Also, it uses Java management extensions to manage and integrate heterogeneous multi-agent systems. Besides, the intelligible service description is provided to supp...

This paper focuses on how automatic translation techniques integrated in a patent retrieval system increase its capabilities and make possible extended features and functionalities. We describe 1) a novel methodology for natural language to SPARQL translation based on a grammar–ontology interoperability automation and a query grammar for the patents domain; 2) a devised strategy for statistical...

This paper describes the system used for our participation in the WMT12 Machine Translation evaluation shared task. We also present a new approach to Machine Translation evaluation based on the recently defined task Semantic Textual Similarity. This problem is addressed using a textual entailment engine entirely based on WordNet semantic features. We described results for the Spanish-English, C...

This paper describes progress in a development of the human-human dialogue corpus for machine translation of spoken language. We have chosen a semantically annotated corpus of phone calls to a train timetable information center. The phone calls consist of inquiries regarding their train traveler plans. Corpus dialogue act tags incorporate abstract semantic meaning. We have enriched a part of th...

Machine translation is one of the disciplines that cover the automatic language processing domain. There are two different approaches to realize a machine translation system; linguistic approach, based on a set of theories and rules that govern the processed language and statistical one, based on probabilities and mathematic theories. Our system emerges from the linguistic school and contains i...

This paper is a detailed discussion of semantic transfer in the context of the Verbmobil Machine Translation project. The use of semantic transfer as a translation mechanism is introduced and justiied by comparison with alternative approaches. Some criteria for evaluation of transfer frameworks are discussed and a comparison is made of three diierent approaches to the representation of translat...

Support verb constructions range from idiosyncratic to predictable. Lexical functions provide a solution to translation of idiosyncratic constructions only. Our corpus research aims to contribute to automatic translation of support verb constructions where the verb selects certain semantic groups of collocates, and where novel collocations can be expected. We investigate samples of support verb...

It is common for information exchange between heterogeneous systems to be syntactically correct but fail to achieve its intended purpose due to semantic mismatches. NATO research group IST-094 is developing a framework to facilitate semantic interoperability. We will show a live demonstration of one possible approach to implementing a message translation broker, following the Semantic Interoper...