Factors associated with successful answering of clinical questions using an information retrieval system*

Objectives: Despite the growing use of online databases by clinicians, there has been very little research documenting how effectively they are used. This study assessed the ability of medical and nurse-practitioner students to answer clinical questions using an information retrieval system. It also attempted to identify the demographic, experience, cognitive, personality, search mechanics, and user-satisfaction factors associated with successful use of a retrieval system.

General and specific brain regions involved in encoding and retrieval of events: what, where, and when.

Remembering an event involves not only what happened, but also where and when it occurred. We measured regional cerebral blood flow by positron emission tomography during initial encoding and subsequent retrieval of item, location, and time information. Multivariate image analysis showed that left frontal brain regions were always activated during encoding, and right superior frontal regions were always activated at retrieval. Pairwise image subtraction analyses revealed information-specific activations at (i) encoding, item information in left hippocampal, location information in right parietal, and time information in left fusiform regions; and (ii) retrieval, item in right inferior frontal and temporal, location in left frontal, and time in anterior cingulate cortices. These results point to the existence of general encoding and retrieval networks of episodic memory whose operations are augmented by unique brain areas recruited for processing specific aspects of remembered events.

Memory for object features versus memory for object location: a positron-emission tomography study of encoding and retrieval processes.

Regional cerebral blood flow was measured with positron-emission tomography during two encoding and two retrieval tasks that were designed to compare memory for object features with memory for object locations. Bilateral increases in regional cerebral blood flow were observed in both anterior and posterior regions of inferior temporal cortex and in ventral regions of prestriate cortex, when the condition that required retrieval of object locations was subtracted from the condition that required retrieval of object features. During encoding, these changes were less pronounced and were restricted to the left inferior temporal cortex and right ventral prestriate cortex. In contrast, both encoding and retrieval of object location were associated with bilateral changes in dorsal prestriate and posterior parietal cortex. Finally, the two encoding conditions activated left frontal lobe regions preferentially, whereas the two retrieval conditions activated right frontal lobe regions. These findings confirm that, in human subjects, memory for object features is mediated by a distributed system that includes ventral prestriate cortex and both anterior and posterior regions of the inferior temporal gyrus. In contrast, memory for the locations of objects appears to be mediated by an anatomically distinct system that includes more dorsal regions of prestriate cortex and posterior regions of the parietal lobe.

Functional activation of the human ventrolateral frontal cortex during mnemonic retrieval of verbal information.

Regional cerebral blood flow was measured with positron emission tomography during the performance of a verbal free recall task, a verbal paired associate task, and tasks that required the production of verbal responses either by speaking or writing. Examination of the differences in regional cerebral blood flow between these conditions demonstrated that the left ventrolateral frontal cortical area 45 is involved in the recall of verbal information from long-term memory, in addition to its contribution to speech. The act of writing activated a network of areas involving posterior parietal cortex and sensorimotor areas but not ventrolateral frontal cortex.

Spoken document retrieval experiments with IR-n system

This paper describes the first participation of IR-n system at Spoken Document Retrieval, focusing on the experiments we made before participation and showing the results we obtained. IR-n system is an Information Retrieval system based on passages and the recognition of sentences to define them. So, the main goal of this experiment is to adapt IR-n system to the spoken document structure by means of the utterance splitter and the overlapping passage technique allowing to match utterances and sentences.

Using WordNet relations and semantic classes in information retrieval tasks

In this paper we explore the use of semantic classes in an existing information retrieval system in order to improve its results. Thus, we use two different ontologies of semantic classes (WordNet domain and Basic Level Concepts) in order to re-rank the retrieved documents and obtain better recall and precision. Finally, we implement a new method for weighting the expanded terms taking into account the weights of the original query terms and their relations in WordNet with respect to the new ones (which have demonstrated to improve the results). The evaluation of these approaches was carried out in the CLEF Robust-WSD Task, obtaining an improvement of 1.8% in GMAP for the semantic classes approach and 10% in MAP employing the WordNet term weighting approach.

Towards a unified framework for opinion retrieval, mining and summarization

The exponential increase of subjective, user-generated content since the birth of the Social Web, has led to the necessity of developing automatic text processing systems able to extract, process and present relevant knowledge. In this paper, we tackle the Opinion Retrieval, Mining and Summarization task, by proposing a unified framework, composed of three crucial components (information retrieval, opinion mining and text summarization) that allow the retrieval, classification and summarization of subjective information. An extensive analysis is conducted, where different configurations of the framework are suggested and analyzed, in order to determine which is the best one, and under which conditions. The evaluation carried out and the results obtained show the appropriateness of the individual components, as well as the framework as a whole. By achieving an improvement over 10% compared to the state-of-the-art approaches in the context of blogs, we can conclude that subjective text can be efficiently dealt with by means of our proposed framework.

Using IR-n for information retrieval of Genomics Track

Nowadays there is a big amount of biomedical literature which uses complex nouns and acronyms of biological entities thus complicating the task of retrieval specific information. The Genomics Track works for this goal and this paper describes the approach we used to take part of this track of TREC 2007. As this is the first time we participate in this track, we configurated a new system consisting of the following diferenciated parts: preprocessing, passage generation, document retrieval and passage (with the answer) extraction. We want to call special attention to the textual retrieval system used, which was developed by the University of Alicante. Adapting the resources for the propouse, our system has obtained precision results over the mean and median average of the 66 official runs for the Document, Aspect and Passage2 MAP; and in the case of Passage MAP we get nearly the median and mean value. We want to emphasize we have obtained these results without incorporating specific information about the domain of the track. For the future, we would like to further develop our system in this direction.

Question answering and multi-search engines in geo-temporal information retrieval

In this paper we present a complete system for the treatment of both geographical and temporal dimensions in text and its application to information retrieval. This system has been evaluated in both the GeoTime task of the 8th and 9th NTCIR workshop in the years 2010 and 2011 respectively, making it possible to compare the system to contemporary approaches to the topic. In order to participate in this task we have added the temporal dimension to our GIR system. The system proposed here has a modular architecture in order to add or modify features. In the development of this system, we have followed a QA-based approach as well as multi-search engines to improve the system performance.

Polarimetric Response of Rice Fields at C-Band: Analysis and Phenology Retrieval

A set of ten RADARSAT-2 images acquired in fully polarimetric mode over a test site with rice fields in Seville, Spain, has been analyzed to extract the main features of the C-band radar backscatter as a function of rice phenology. After observing the evolutions versus phenology of different polarimetric observables and explaining their behavior in terms of scattering mechanisms present in the scene, a simple retrieval approach has been proposed. This algorithm is based on three polarimetric observables and provides estimates from a set of four relevant intervals of phenological stages. The validation against ground data, carried out at parcel level for a set of six stands and up to nine dates per stand, provides a 96% rate of coincidence. Moreover, an equivalent compact-pol retrieval algorithm has been also proposed and validated, providing the same performance at parcel level. In all cases, the inversion is carried out by exploiting a single satellite acquisition, without any other auxiliary information.

Application of Text Summarization techniques to the Geographical Information Retrieval task

Automatic Text Summarization has been shown to be useful for Natural Language Processing tasks such as Question Answering or Text Classification and other related fields of computer science such as Information Retrieval. Since Geographical Information Retrieval can be considered as an extension of the Information Retrieval field, the generation of summaries could be integrated into these systems by acting as an intermediate stage, with the purpose of reducing the document length. In this manner, the access time for information searching will be improved, while at the same time relevant documents will be also retrieved. Therefore, in this paper we propose the generation of two types of summaries (generic and geographical) applying several compression rates in order to evaluate their effectiveness in the Geographical Information Retrieval task. The evaluation has been carried out using GeoCLEF as evaluation framework and following an Information Retrieval perspective without considering the geo-reranking phase commonly used in these systems. Although single-document summarization has not performed well in general, the slight improvements obtained for some types of the proposed summaries, particularly for those based on geographical information, made us believe that the integration of Text Summarization with Geographical Information Retrieval may be beneficial, and consequently, the experimental set-up developed in this research work serves as a basis for further investigations in this field.

Noise-tolerance feasibility for restricted-domain Information Retrieval systems

Information Retrieval systems normally have to work with rather heterogeneous sources, such as Web sites or documents from Optical Character Recognition tools. The correct conversion of these sources into flat text files is not a trivial task since noise may easily be introduced as a result of spelling or typeset errors. Interestingly, this is not a great drawback when the size of the corpus is sufficiently large, since redundancy helps to overcome noise problems. However, noise becomes a serious problem in restricted-domain Information Retrieval specially when the corpus is small and has little or no redundancy. This paper devises an approach which adds noise-tolerance to Information Retrieval systems. A set of experiments carried out in the agricultural domain proves the effectiveness of the approach presented.

Retrieval of phenological stages of onion fields during the first year of growth by means of C-band polarimetric SAR measurements

The phenological stages of onion fields in the first year of growth are estimated using polarimetric observables and single-polarization intensity channels. Experiments are undertaken on a time series of RADARSAT-2 C-band full-polarimetric synthetic aperture radar (SAR) images collected in 2009 over the Barrax region, Spain, where ground truth information about onion growth stages is provided by the European Space Agency (ESA)-funded agricultural bio/geophysical retrieval from frequent repeat pass SAR and optical imaging (AgriSAR) field campaign conducted in that area. The experimental results demonstrate that polarimetric entropy or copolar coherence when used jointly with the cross-polarized intensity allows unambiguously distinguishing three phenological intervals.

Learning representations for Information Retrieval

La recherche d'informations s'intéresse, entre autres, à répondre à des questions comme: est-ce qu'un document est pertinent à une requête ? Est-ce que deux requêtes ou deux documents sont similaires ? Comment la similarité entre deux requêtes ou documents peut être utilisée pour améliorer l'estimation de la pertinence ? Pour donner réponse à ces questions, il est nécessaire d'associer chaque document et requête à des représentations interprétables par ordinateur. Une fois ces représentations estimées, la similarité peut correspondre, par exemple, à une distance ou une divergence qui opère dans l'espace de représentation. On admet généralement que la qualité d'une représentation a un impact direct sur l'erreur d'estimation par rapport à la vraie pertinence, jugée par un humain. Estimer de bonnes représentations des documents et des requêtes a longtemps été un problème central de la recherche d'informations. Le but de cette thèse est de proposer des nouvelles méthodes pour estimer les représentations des documents et des requêtes, la relation de pertinence entre eux et ainsi modestement avancer l'état de l'art du domaine. Nous présentons quatre articles publiés dans des conférences internationales et un article publié dans un forum d'évaluation. Les deux premiers articles concernent des méthodes qui créent l'espace de représentation selon une connaissance à priori sur les caractéristiques qui sont importantes pour la tâche à accomplir. Ceux-ci nous amènent à présenter un nouveau modèle de recherche d'informations qui diffère des modèles existants sur le plan théorique et de l'efficacité expérimentale. Les deux derniers articles marquent un changement fondamental dans l'approche de construction des représentations. Ils bénéficient notamment de l'intérêt de recherche dont les techniques d'apprentissage profond par réseaux de neurones, ou deep learning, ont fait récemment l'objet. Ces modèles d'apprentissage élicitent automatiquement les caractéristiques importantes pour la tâche demandée à partir d'une quantité importante de données. Nous nous intéressons à la modélisation des relations sémantiques entre documents et requêtes ainsi qu'entre deux ou plusieurs requêtes. Ces derniers articles marquent les premières applications de l'apprentissage de représentations par réseaux de neurones à la recherche d'informations. Les modèles proposés ont aussi produit une performance améliorée sur des collections de test standard. Nos travaux nous mènent à la conclusion générale suivante: la performance en recherche d'informations pourrait drastiquement être améliorée en se basant sur les approches d'apprentissage de représentations.