1,721,018 research outputs found
In this paper 1 we present and analyze a method of sense tagging which considers bigger units than words, namely phrases. We show that the senses of the individual words in certain phrases are correlated and the respective words are in a particular type of relationships which acts like a chain process. On the basis of the unambiguous phrases, properties of lexical features responsible word disambiguation are found. The tagging guidelines are given in accordance with these properties. We run a series of experiments in order to measure the inter-annotator agreement. The figures suggest that the methodology of phrase sense tagging is consisten
Full text linkEmilian Popescu, Octavian Iliescu et Tudor Teoteoi (Ed.), Études byzantines et post-byzantines. II
No full textEmilian Popescu, Octavian Iliescu et Tudor Teoteoi (Ed.), Études byzantines et post-byzantines. II. In: Revue des études byzantines, tome 51, 1993. pp. 335-336
Emilian Popescu, Octavian Iliescu et Tudor Teoteoi (Ed.), Études byzantines et post-byzantines. II
No full textEmilian Popescu, Octavian Iliescu et Tudor Teoteoi (Ed.), Études byzantines et post-byzantines. II. In: Revue des études byzantines, tome 51, 1993. pp. 335-336
Language Independent First and Last Name Identification in Person Names
No full textIn this paper we address the problem of first name and last name
identification in a news collection. The approach presented is based on corpus
investigation and is language independent. At the core of the system there is a
name classifier based on the values of different parameters. In its most general
form, the name category identification is not an easy task. The hardest problems
are raised by ambiguous tokens – those that can be either a first or a last name
and/or by tokens with just one occurrence. However, the system is able to predict
the name category with high accuracy. The experiments have been run on
an Italian newspaper and the evaluation has been carried on I-CAB
Verbal Phrase Translation
No full textA meaning preserving translation usually involves long distance relationships between words. The CPA approach builds patterns centred on verbs, which capture the normal usage. Aligning the patterns between a source and a target language allows a meaning preserving translation of the verbal phrases. In this paper we present a pilot study of translation from English to Italian using CPA patterns. The results obtained show that the results are judged much better than the baseline translation offered by the Google translator
- …
