All posts by Ignacio Iacobacci

PhD. Student in the Department of Computer Science at the Sapienza University of Rome. His research interests lie in the fields of Machine Learning, Natural Language Processing, Neural Networks. Working on Statistical Language Modelling as Embeddings and their applications.

Embedding Words and Senses Together via Joint Knowledge-Enhanced Training

Embedding Words and Senses Together via Joint Knowledge-Enhanced Training

We propose a new model that jointly learns word and sense embeddings and represents them in a unified vector space by exploiting large corpora and knowledge obtained from semantic networks. We evaluate the main features of our approach qualitatively and quantitatively in various tasks, highlighting the advantages of the proposed method with respect to state-of-the-art word- and sense-based models.

[site] [source] [paper]

Advertisements

[Tutorial] Semantic Representations of Word Senses and Concepts

[Tutorial] Semantic Representations of Word Senses and Concepts

This tutorial will first provide a brief overview of the recent literature concerning word representation (both count based and neural network based). It will then describe the advantages of moving from the word level to the deeper level of word senses and concepts, providing an extensive review of state ­of ­the ­art systems. Approaches covered will not only include those which draw upon knowledge resources such as WordNet, Wikipedia, BabelNet or FreeBase as reference, but also the so ­called multi ­prototype approaches which learn sense distinctions by using different clustering techniques. Our tutorial will discuss the advantages and potential limitations of all approaches, showing their most successful applications to date. We will conclude by presenting current open problems and lines of future work.

[presentation] [paper]

Negated Findings Detection in Radiology Reports in Spanish: an Adaptation of NegEx to Spanish

Negated Findings Detection in Radiology Reports in Spanish: an Adaptation of NegEx to Spanish

We present SpRadNeg, an adaptation of NegEx to the Spanish language. NegEx is an English rule-based negation detection algorithm. We have tested SpRadNeg with radiology reports, obtaining a precision of 0.87 and a recall of 0.49. We also propose a method to automatize text annotation based on Machine Learning techniques with 0.91 precision and 0.89 recall.

[paper]