This work looks at a temporal aspect of multiword expressions (MWEs), namely that the behaviour of a given n-gram and its status as a MWE change over time. We propose a model in which context words have particular probabilities given a usage choice for an n-gram, and those usage choices have time dependent probabilities, and we put forward an expectationmaximisation technique for estimating the...

The huge amount of available spoken documents has raised the need for tools to perform automatic searches within large audio databases. These collections usually consist of documents with a great variability regarding speaker, language or recording channel, among others. Reducing this variability would boost the performance of query-by-example search on speech systems, especially in zero-resour...

Many researchers have worked on example-based machine translation and different techniques have been investigated in the area. In literature, a method of using translation templates learned from bilingual example pairs was proposed. The paper investigates the possibility of applying the same idea for close languages where word order is preserved. In addition to applying the original algorithm f...

This paper presents mwetoolkit+sem: an extension of the mwetoolkit that estimates semantic compositionality scores for multiword expressions (MWEs) based on word embeddings. First, we describe our implementation of vector-space operations working on distributional vectors. The compositionality score is based on the cosine distance between the MWE vector and the composition of the vectors of its...

We pose the content-based retrieval problem as a problem of statistical inference and develop a Bayesian framework for indexing and retrieval in the context of large multimedia databases. All the indexing is carried out in the compressed domain and leads to eecient retrieval without compromise of the compression eeciency. The framework allows the integration of information from diierent sources...

To automatically retrieve documents or images from a database, retrieval systems use similarity measures to compare a request based on features extracted from the documents. As a result, documents are ordered in a list by decreasing correspondance to the request. Several comparison measures are used in the field and it is difficult to choose one or another. In this paper, we show that they can ...