Using domain-specific knowledge to improve information retrieval performance

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Molecular docking and geographical information systems as tools to assess the potential impact of veterinary medicines on non-target organisms and the environment

Veterinary medicines (VMs) from agricultural industry can enter the environment in a number of ways. This includes direct exposure through aquaculture, accidental spillage and disposal, and indirect entry by leaching from manure or runoff after treatment. Many compounds used in animal treatments have ecotoxic properties that may have chronic or sometimes lethal effects when they come into contact with non-target organisms. VMs enter the environment in mixtures, potentially having additive effects. Traditional ecotoxicology tests are used to determine the lethal and sometimes reproductive effects on freshwater and terrestrial organisms. However, organisms used in ecotoxicology tests can be unrepresentative of the populations that are likely to be exposed to the compound in the environment. Most often the tests are on single compound toxicity but mixture effects may be significant and should be included in ecotoxicology testing. This work investigates the use, measured environmental concentrations (MECs) and potential impact of sea lice treatments on salmon farms in Scotland. Alternative methods for ecotoxicology testing including mixture toxicity, and the use of in silico techniques to predict the chronic impact of VMs on different species of aquatic organisms were also investigated. The Scottish Environmental Protection Agency (SEPA) provided information on the use of five sea lice treatments from 2008-2011 on Scottish salmon farms. This information was combined with the recently available data on sediment MECs for the years 2009-2012 provided by SEPA using ArcGIS 10.1. In depth analysis of this data showed that from a total of 55 sites, 30 sites had a MEC higher than the maximum allowable concentration (MAC) as set out by SEPA for emamectin benzoate and 7 sites had a higher MEC than MAC for teflubenzuron. A number of sites that were up to 16 km away from the nearest salmon farm reported as using either emamectin benzoate or teflubenzuron measured positive for the two treatments. There was no relationship between current direction and the distribution of the sea lice treatments, nor was there any evidence for alternative sources of the compounds e.g. land treatments. The sites that had MECs higher than the MAC could pose a risk to non-target organisms and disrupt the species dynamics of the area. There was evidence that some marine protected sites might be at risk of exposure to these compounds. To complement this work, effects on acute mixture toxicity of the 5 sea lice treatments, plus one major metabolite 3-phenoxybenzoic acid (3PBA), were measured using an assay using the bioluminescent bacteria Aliivibrio fischeri. When exposed to the 5 sea lice treatments and 3PBA A. fischeri showed a response to 3PBA, emamectin benzoate and azamethiphos as well as combinations of the three. In order to establish any additive effect of the sea lice treatments, the efficacy of two mixture prediction equations, concentration addition (CA) and independent action ii(IA) were tested using the results from single compound dose response curves. In this instance IA was the more effective prediction method with a linear regression confidence interval of 82.6% compared with 22.6% of CA. In silico molecular docking was carried out to predict the chronic effects of 15 VMs (including the five used as sea lice control). Molecular docking has been proposed as an alternative screening method for the chronic effects of large animal treatments on non-target organisms. Oestrogen receptor alpha (ERα) of 7 non-target bony fish and the African clawed frog Xenopus laevis were modelled using SwissModel. These models were then ‘docked’ to oestradiol, the synthetic oestrogen ethinylestradiol, two known xenoestrogens dichlorodiphenyltrichloroethane (DDT) and bisphenol A (BPA), the antioestrogen breast cancer treatment tamoxifen and 15 VMs using Auto Dock 4. Based on the results of this work, four VMs were identified as being possible xenoestrogens or anti-oestrogens; these were cypermethrin, deltamethrin, fenbendazole and teflubenzuron. Further investigation, using in vitro assays, into these four VMs has been suggested as future work. A modified recombinant yeast oestrogen screen (YES) was attempted using the cDNA of the ERα of the zebrafish Danio rerio and the rainbow trout Oncorhynchus mykiss. Due to time and difficulties in cloning protocols this work was unable to be completed. Use of such in vitro assays would allow for further investigation of the highlighted VMs into their oestrogenic potential. In conclusion, VMs used as sea lice treatments, such as teflubenzuron and emamectin benzoate may be more persistent and have a wider range in the environment than previously thought. Mixtures of sea lice treatments have been found to persist together in the environment, and effects of these mixtures on the bacteria A. fischeri can be predicted using the IA equation. Finally, molecular docking may be a suitable tool to predict chronic endocrine disrupting effects and identify varying degrees of impact on the ERα of nine species of aquatic organisms.

How can geographical information systems and spatial analysis inform a response to prescription opioid misuse? a discussion in the context of existing literature

Vocabulary and language model adaptation using information retrieval

International audience

Query routing in cooperative semi-structured peer-to-peer information retrieval networks

Conventional web search engines are centralised in that a single entity crawls and indexes the documents selected for future retrieval, and the relevance models used to determine which documents are relevant to a given user query. As a result, these search engines suffer from several technical drawbacks such as handling scale, timeliness and reliability, in addition to ethical concerns such as commercial manipulation and information censorship. Alleviating the need to rely entirely on a single entity, Peer-to-Peer (P2P) Information Retrieval (IR) has been proposed as a solution, as it distributes the functional components of a web search engine – from crawling and indexing documents, to query processing – across the network of users (or, peers) who use the search engine. This strategy for constructing an IR system poses several efficiency and effectiveness challenges which have been identified in past work. Accordingly, this thesis makes several contributions towards advancing the state of the art in P2P-IR effectiveness by improving the query processing and relevance scoring aspects of a P2P web search. Federated search systems are a form of distributed information retrieval model that route the user’s information need, formulated as a query, to distributed resources and merge the retrieved result lists into a final list. P2P-IR networks are one form of federated search in routing queries and merging result among participating peers. The query is propagated through disseminated nodes to hit the peers that are most likely to contain relevant documents, then the retrieved result lists are merged at different points along the path from the relevant peers to the query initializer (or namely, customer). However, query routing in P2P-IR networks is considered as one of the major challenges and critical part in P2P-IR networks; as the relevant peers might be lost in low-quality peer selection while executing the query routing, and inevitably lead to less effective retrieval results. This motivates this thesis to study and propose query routing techniques to improve retrieval quality in such networks. Cluster-based semi-structured P2P-IR networks exploit the cluster hypothesis to organise the peers into similar semantic clusters where each such semantic cluster is managed by super-peers. In this thesis, I construct three semi-structured P2P-IR models and examine their retrieval effectiveness. I also leverage the cluster centroids at the super-peer level as content representations gathered from cooperative peers to propose a query routing approach called Inverted PeerCluster Index (IPI) that simulates the conventional inverted index of the centralised corpus to organise the statistics of peers’ terms. The results show a competitive retrieval quality in comparison to baseline approaches. Furthermore, I study the applicability of using the conventional Information Retrieval models as peer selection approaches where each peer can be considered as a big document of documents. The experimental evaluation shows comparative and significant results and explains that document retrieval methods are very effective for peer selection that brings back the analogy between documents and peers. Additionally, Learning to Rank (LtR) algorithms are exploited to build a learned classifier for peer ranking at the super-peer level. The experiments show significant results with state-of-the-art resource selection methods and competitive results to corresponding classification-based approaches. Finally, I propose reputation-based query routing approaches that exploit the idea of providing feedback on a specific item in the social community networks and manage it for future decision-making. The system monitors users’ behaviours when they click or download documents from the final ranked list as implicit feedback and mines the given information to build a reputation-based data structure. The data structure is used to score peers and then rank them for query routing. I conduct a set of experiments to cover various scenarios including noisy feedback information (i.e, providing positive feedback on non-relevant documents) to examine the robustness of reputation-based approaches. The empirical evaluation shows significant results in almost all measurement metrics with approximate improvement more than 56% compared to baseline approaches. Thus, based on the results, if one were to choose one technique, reputation-based approaches are clearly the natural choices which also can be deployed on any P2P network.

Sperimentazione di Deep Metric Loss per Self-Supervised Information Retrieval Systems su CORD19.

Dopo lo sviluppo dei primi casi di Covid-19 in Cina nell’autunno del 2019, ad inizio 2020 l’intero pianeta è precipitato in una pandemia globale che ha stravolto le nostre vite con conseguenze che non si vivevano dall’influenza spagnola. La grandissima quantità di paper scientifici in continua pubblicazione sul coronavirus e virus ad esso affini ha portato alla creazione di un unico dataset dinamico chiamato CORD19 e distribuito gratuitamente. Poter reperire informazioni utili in questa mole di dati ha ulteriormente acceso i riflettori sugli information retrieval systems, capaci di recuperare in maniera rapida ed efficace informazioni preziose rispetto a una domanda dell'utente detta query. Di particolare rilievo è stata la TREC-COVID Challenge, competizione per lo sviluppo di un sistema di IR addestrato e testato sul dataset CORD19. Il problema principale è dato dal fatto che la grande mole di documenti è totalmente non etichettata e risulta dunque impossibile addestrare modelli di reti neurali direttamente su di essi. Per aggirare il problema abbiamo messo a punto nuove soluzioni self-supervised, a cui abbiamo applicato lo stato dell'arte del deep metric learning e dell'NLP. Il deep metric learning, che sta avendo un enorme successo soprattuto nella computer vision, addestra il modello ad "avvicinare" tra loro immagini simili e "allontanare" immagini differenti. Dato che sia le immagini che il testo vengono rappresentati attraverso vettori di numeri reali (embeddings) si possano utilizzare le stesse tecniche per "avvicinare" tra loro elementi testuali pertinenti (e.g. una query e un paragrafo) e "allontanare" elementi non pertinenti. Abbiamo dunque addestrato un modello SciBERT con varie loss, che ad oggi rappresentano lo stato dell'arte del deep metric learning, in maniera completamente self-supervised direttamente e unicamente sul dataset CORD19, valutandolo poi sul set formale TREC-COVID attraverso un sistema di IR e ottenendo risultati interessanti.

Self-supervised information retrieval: a novel approach based on Deep Metric Learning and Neural Language Models

Most of the existing open-source search engines, utilize keyword or tf-idf based techniques to find relevant documents and web pages relative to an input query. Although these methods, with the help of a page rank or knowledge graphs, proved to be effective in some cases, they often fail to retrieve relevant instances for more complicated queries that would require a semantic understanding to be exploited. In this Thesis, a self-supervised information retrieval system based on transformers is employed to build a semantic search engine over the library of Gruppo Maggioli company. Semantic search or search with meaning can refer to an understanding of the query, instead of simply finding words matches and, in general, it represents knowledge in a way suitable for retrieval. We chose to investigate a new self-supervised strategy to handle the training of unlabeled data based on the creation of pairs of ’artificial’ queries and the respective positive passages. We claim that by removing the reliance on labeled data, we may use the large volume of unlabeled material on the web without being limited to languages or domains where labeled data is abundant.

Self-supervised Information Retrieval basato su deep metric learning

La tesi ha lo scopo di ricercare, esaminare ed implementare un sistema di Machine Learning, un Recommendation Systems per precisione, che permetta la racommandazione di documenti di natura giuridica, i quali sono già stati analizzati e categorizzati appropriatamente, in maniera ottimale, il cui scopo sarebbe quello di accompagnare un sistema già implementato di Information Retrieval, istanziato sopra una web application, che permette di ricercare i documenti giuridici appena menzionati.

Una aproximación basada en corpus para la detección del foco geográfico en el texto

El foco geográfico de un documento identifica el lugar o lugares en los que se centra el contenido del texto. En este trabajo se presenta una aproximación basada en corpus para la detección del foco geográfico en el texto. Frente a otras aproximaciones que se centran en el uso de información puramente geográfica para la detección del foco, nuestra propuesta emplea toda la información textual existente en los documentos del corpus de trabajo, partiendo de la hipótesis de que la aparición de determinados personajes, eventos, fechas e incluso términos comunes, pueden resultar fundamentales para esta tarea. Para validar nuestra hipótesis, se ha realizado un estudio sobre un corpus de noticias geolocalizadas que tuvieron lugar entre los años 2008 y 2011. Esta distribución temporal nos ha permitido, además, analizar la evolución del rendimiento del clasificador y de los términos más representativos de diferentes localidades a lo largo del tiempo.

Discovery and retrieval of Geographic data using Google

Dissertation submitted in partial fulfilment of the requirements for the Degree of Master of Science in Geospatial Technologies

Dual retrieval in conceptual information systems

Conceptual Information Systems provide a multi-dimensional conceptually structured view on data stored in relational databases. On restricting the expressiveness of the retrieval language, they allow the visualization of sets of realted queries in conceptual hierarchies, hence supporting the search of something one does not have a precise description, but only a vague idea of. Information Retrieval is considered as the process of finding specific objects (documents etc.) out of a large set of objects which fit to some description. In some data analysis and knowledge discovery applications, the dual task is of interest: The analyst needs to determine, for a subset of objects, a description for this subset. In this paper we discuss how Conceptual Information Systems can be extended to support also the second task.

Semantic-driven context-aware visual information indexing and retrieval: applied in the film post-production domain

A large volume of visual content is inaccessible until effective and efficient indexing and retrieval of such data is achieved. In this paper, we introduce the DREAM system, which is a knowledge-assisted semantic-driven context-aware visual information retrieval system applied in the film post production domain. We mainly focus on the automatic labelling and topic map related aspects of the framework. The use of the context- related collateral knowledge, represented by a novel probabilistic based visual keyword co-occurrence matrix, had been proven effective via the experiments conducted during system evaluation. The automatically generated semantic labels were fed into the Topic Map Engine which can automatically construct ontological networks using Topic Maps technology, which dramatically enhances the indexing and retrieval performance of the system towards an even higher semantic level.

New perspectives on the processing and release of public information

This article discusses issues related to the organization and reception of information in the context of services and public information systems driven by technology. It stems from the assumption that in a ""technologized"" society, the distance between users and information is almost always of cognitive and socio-cultural nature, a product of our effort to design communication. In this context, we favor the approach of the information sign, seeking to answer how a documentary message turns into information, i.e. a structure recognized as socially useful. Observing the structural, cognitive and communicative aspects of the documentary message, based on Documentary Linguistics, Terminology, as well as on Textual Linguistics, the policy of knowledge management and innovation of the Government of the State of Sao Paulo is analyzed, which authorizes the use of Web 2.0, also questioning to what extent this initiative represents innovation in the environment of libraries.

Decision support system with incomplete and domain incoherent information management

Many of the most common human functions such as temporal and non-monotonic reasoning have not yet been fully mapped in developed systems, even though some theoretical breakthroughs have already been accomplished. This is mainly due to the inherent computational complexity of the theoretical approaches. In the particular area of fault diagnosis in power systems however, some systems which tried to solve the problem, have been deployed using methodologies such as production rule based expert systems, neural networks, recognition of chronicles, fuzzy expert systems, etc. SPARSE (from the Portuguese acronym, which means expert system for incident analysis and restoration support) was one of the developed systems and, in the sequence of its development, came the need to cope with incomplete and/or incorrect information as well as the traditional problems for power systems fault diagnosis based on SCADA (supervisory control and data acquisition) information retrieval, namely real-time operation, huge amounts of information, etc. This paper presents an architecture for a decision support system, which can solve the presented problems, using a symbiosis of the event calculus and the default reasoning rule based system paradigms, insuring soft real-time operation with incomplete, incorrect or domain incoherent information handling ability. A prototype implementation of this system is already at work in the control centre of the Portuguese Transmission Network.

Forest cover monitoring in the Bara district (Nepal) with remote sensing and geographic information systems

Dissertation submitted in partial fulfilment of the requirements for the Degree of Master of Science in Geospatial Technologies