Muath Alzghool

Using various indexing schemes and multiple translations in the CL-SR task at CLEF 2005

We present the participation of the University of Ottawa in the Cross-Language Spoken Document Retrieval task at CLEF 2005. In order to translate the queries, we combined the results of several online Machine Translation tools. For the Information Retrieval component we used the SMART system [1], with several weighting schemes for indexing the documents and the queries. One scheme in particular led to better results than other combinations. We present the results of the submitted runs and of many un-official runs. We compare the effect of several translations from each language. We present results on phonetic transcripts of the collection and queries and on the combination of text and phonetic transcripts. We also include the results when the manual summaries and keywords are indexed.

Investigating Cross-Language Speech Retrieval for a Spontaneous Conversational Speech Collection

Cross-language retrieval of spontaneous speech combines the challenges of working with noisy automated transcription and language translation. The CLEF 2005 Cross-Language Speech Retrieval (CL-SR) task provides a standard test collection to investigate these challenges. We show that we can improve retrieval performance: by careful selection of the term weighting scheme; by decomposing automated transcripts into phonetic substrings to help ameliorate transcription errors; and by combining automatic transcriptions with manually-assigned metadata. We further show that topic translation with online machine translation resources yields effective CL-SR.

Experiments for the cross language speech retrieval task at CLEF 2006

This paper presents the second participation of the University of Ottawa group in the Cross-Language Speech Retrieval (CL-SR) task at CLEF 2006. We present the results of the submitted runs for the English collection and very briefly for the Czech collection, followed by many additional experiments. We have used two Information Retrieval systems in our experiments: SMART and Terrier, with several query expansion techniques (including a new method based on log-likelihood scores for collocations). Our experiments showed that query expansion methods do not help much for this collection. We tested different Automatic Speech Recognition transcripts and combinations. The retrieval results did not improve, probably because the speech recognition errors happened for the words that are important in retrieval. We present cross-language experiments, where the queries are automatically translated by combining the results of several online machine translation tools. Our experiments showed that high quality automatic translations (for French) led to results comparable with monolingual English, while the performance decreased for the other languages. Experiments on indexing the manual summaries and keywords gave the best retrieval results.

Clustering for photo retrieval at Image CLEF 2008

This paper presents the first participation of the University of Ottawa group in the Photo Retrieval task at Image CLEF 2008. Our system uses Lucene for text indexing and LIRE for image indexing. We experiment with several clustering methods in order to retrieve images from diverse clusters. The clustering methods are: k-means clustering, hierarchical clustering, and our own method based on WordNet. We present results for thirteen runs, in order to compare retrieval based on text description, to image-only retrieval, and to merged retrieval, and to compare results for the different clustering methods.

Clustering the topics using TF-IDF for model fusion

Users tend to express their queries in various ways: sometimes they use more general terms, sometimes more specific terms. Information retrieval systems need to be able to accommodate this variety of user needs. Some retrieval models perform better when the queries are general, others perform better when the queries are more specific, and others when a combination is available. In this paper we are looking for a system that will perform well in all these cases, we present a new method for combining the results of different models in order to improve the performance on a difficult task: Information Retrieval from spontaneous speech. Our technique is based on clustering the training topics according to their tf-idf (term frequency-inverse document frequency) properties, and selecting the best models for each cluster. When the system runs on a test topic, the cluster of the topic needs to be determined and the combination of models of this cluster is used. We report improvements on the Malach collection used at CLEF-CLSR 2007.

Model Fusion Experiments for the CLSR Task at CLEF 2007

This paper presents the participation of the University of Ottawa group in the Cross-Language Speech Retrieval (CL-SR) task at CLEF 2007. We present the results of the submitted runs for the English collection. We have used two Information Retrieval systems in our experiments: SMART and Terrier, with two query expansion techniques: one based on a thesaurus and the second one based on blind relevant feedback. We proposed two novel data fusion methods for merging the results of several models (retrieval schemes available in SMART and Terrier). Our experiments showed that the combination of query expansion methods and data fusion methods helps to improve the retrieval performance. We also present cross-language experiments, where the queries are automatically translated by combining the results of several online machine translation tools. Experiments on indexing the manual summaries and keywords gave the best retrieval results.

Exploring fusion in a spontaneous speech retrieval task

In this paper we present two novel model fusion techniques. We fuse together results from several Information Retrieval models or variations of the models. We test them on a collection of spontaneous speech transcripts. We also fuse results obtained with different documents representations (automatic transcripts or manual data). Our first fusion model is training the weighs based on the training data, but in an efficient and novel way. The second fusion model works for results with high variation, such as results obtained from automatic vs. manual document representations.