Vivi Nastase

Learn More
The NLP community has shown a renewed interest in deeper semantic analyses, among them automatic recognition of relations between pairs of words in a text. We present an evaluation task designed to provide a framework for comparing different approaches to classifying semantic relations between nominals in a sentence. This is part of SemEval, the 4 edition(More)
We study the performance of two representations of word meaning in learning noun-modifier semantic relations. One representation is based on lexical resources, in particular WordNet, the other – on a corpus. We experimented with decision trees, instance-based learning and Support Vector Machines. All these methods work well in this learning task. We report(More)
This paper describes a multi-lingual concept network obtained automatically by mining for concepts and relations and exploiting a variety of sources of knowledge from Wikipedia. Concepts and their lexicalizations are extracted from Wikipedia pages. Relations are extracted from the category and page network, infoboxes and the body of the articles. The(More)
Information of interest to users is often distributed over a set of documents. Users can specify their request for information as a query/topic – a set of one or more sentences or questions. Producing a good summary of the relevant information relies on understanding the query and linking it with the associated set of documents. To “understand” the query we(More)
å Ü à ß Ö × Ó ae ç è é ê ë ì í î ï ð î ï ñ é î ñ í ò ó ë ï ò ô õ í ê í õ ö è ï ÷ ñ ð ô ò ø ô ò ù ø í ë ï ð ú ë ï í ù ø î ù õ ë í ò ï ë ù ø î û í õ ô î ó ê ô ù ô ó ò ê í ò ù ë ê î ù ô ë ï ì ê ë ü ð í ý ò þ ÿ ø í í ¡ ¡ ë ê õ ò ù ø î ù é ò í ò ì í ÷ ó ô î ð ó ø î ê î ó ù í ê ò î ê í ü ë ê ê ë ¡ í õ ê ë ý ë ù ø í ê ð î ï ñ é î ñ í ò
We investigate the use of syntactically related pairs of words for the task of text classification. The set of all pairs of syntactically related words should intuitively provide a better description of what a document is about, than the set of proximity-based N-grams or selective syntactic phrases. We generate syntactically related word pairs using a(More)