Dolf Trieschnigg

MeSH Up

MOTIVATION Controlled vocabularies such as the Medical Subject Headings (MeSH) thesaurus and the Gene Ontology (GO) provide an efficient way of accessing and organizing biomedical information by reducing the ambiguity inherent to free-text data. Different methods of automating the assignment of MeSH concepts have been proposed to replace manual annotation, but they are either limited to a small subset of MeSH or have only been compared with a limited number of other systems. RESULTS We compare the performance of six MeSH classification systems [MetaMap, EAGL, a language and a vector space model-based approach, a K-Nearest Neighbor (KNN) approach and MTI] in terms of reproducing and complementing manual MeSH annotations. A KNN system clearly outperforms the other published approaches and scales well with large amounts of text using the full MeSH thesaurus. Our measurements demonstrate to what extent manual MeSH annotations can be reproduced and how they can be complemented by automatic annotations. We also show that a statistically significant improvement can be obtained in information retrieval (IR) when the text of a users query is automatically annotated with MeSH concepts, compared to using the original textual query alone. CONCLUSIONS The annotation of biomedical texts using controlled vocabularies such as MeSH can be automated to improve text-only IR. Furthermore, the automatic MeSH annotation system we propose is highly scalable and it generates improvements in IR comparable with those observed for manual annotations.

WikiTranslate: query translation for cross-lingual information retrieval using only Wikipedia

This paper presents WikiTranslate, a system which performs query translation for cross-lingual information retrieval (CLIR) using only Wikipedia to obtain translations. Queries are mapped to Wikipedia concepts and the corresponding translations of these concepts in the target language are used to create the final query. WikiTranslate is evaluated by searching with topics formulated in Dutch, French and Spanish in an English data collection. The system achieved a performance of 67% compared to the monolingual baseline.

Federated search in the wild: the combined power of over a hundred search engines

Federated search has the potential of improving web search: the user becomes less dependent on a single search provider and parts of the deep web become available through a unified interface, leading to a wider variety in the retrieved search results. However, a publicly available dataset for federated search reflecting an actual web environment has been absent. As a result, it has been difficult to assess whether proposed systems are suitable for the web setting. We introduce a new test collection containing the results from more than a hundred actual search engines, ranging from large general web search engines such as Google and Bing to small domain-specific engines. We discuss the design and analyze the effect of several sampling methods. For a set of test queries, we collected relevance judgements for the top 10 results of each search engine. The dataset is publicly available and is useful for researchers interested in resource selection for web search collections, result merging and size estimation of uncooperative resources.

Conceptual language models for domain-specific retrieval

Over the years, various meta-languages have been used to manually enrich documents with conceptual knowledge of some kind. Examples include keyword assignment to citations or, more recently, tags to websites. In this paper we propose generative concept models as an extension to query modeling within the language modeling framework, which leverages these conceptual annotations to improve retrieval. By means of relevance feedback the original query is translated into a conceptual representation, which is subsequently used to update the query model. Extensive experimental work on five test collections in two domains shows that our approach gives significant improvements in terms of recall, initial precision and mean average precision with respect to a baseline without relevance feedback. On one test collection, it is also able to outperform a text-based pseudo-relevance feedback approach based on relevance models. On the other test collections it performs similarly to relevance models. Overall, conceptual language models have the added advantage of offering query and browsing suggestions in the form of conceptual annotations. In addition, the internal structure of the meta-language can be exploited to add related terms. Our contributions are threefold. First, an extensive study is conducted on how to effectively translate a textual query into a conceptual representation. Second, we propose a method for updating a textual query model using the concepts in conceptual representation. Finally, we provide an extensive analysis of when and how this conceptual feedback improves retrieval.

Experts and Machines against Bullies: A Hybrid Approach to Detect Cyberbullies

Cyberbullying is becoming a major concern in online environments with troubling consequences. However, most of the technical studies have focused on the detection of cyberbullying through identifying harassing comments rather than preventing the incidents by detecting the bullies. In this work we study the automatic detection of bully users on YouTube. We compare three types of automatic detection: an expert system, supervised machine learning models, and a hybrid type combining the two. All these systems assign a score indicating the level of “bulliness” of online bullies. We demonstrate that the expert system outperforms the machine learning models. The hybrid classifier shows an even better performance.

Peer-to-Peer Information Retrieval: An Overview

Peer-to-peer technology is widely used for file sharing. In the past decade a number of prototype peer-to-peer information retrieval systems have been developed. Unfortunately, none of these has seen widespread real-world adoption and thus, in contrast with file sharing, information retrieval is still dominated by centralized solutions. In this article we provide an overview of the key challenges for peer-to-peer information retrieval and the work done so far. We want to stimulate and inspire further research to overcome these challenges. This will open the door to the development and large-scale deployment of real-world peer-to-peer information retrieval systems that rival existing centralized client-server solutions in terms of scalability, performance, user satisfaction, and freedom.

Proof of concept: concept-based biomedical information retrieval

In this thesis we investigate the possibility to integrate domain-specific knowledge into biomedical information retrieval (IR). Recent decades have shown a fast growing interest in biomedical research, reflected by an exponential growth in scientific literature. An important problem for biomedical IR is dealing with the complex and inconsistent terminology encountered in biomedical publications. Dealing with the terminology problem requires domain knowledge stored in terminological resources: controlled indexing vocabularies and thesauri. The integration of this knowledge is, however, far from trivial. The first research theme investigates heuristics for obtaining word-based representations from biomedical text for robust retrieval. We investigated the effect of choices in document preprocessing heuristics on retrieval effectiveness. Document preprocessing heuristics such as stop word removal, stemming, and breakpoint identification and normalization were shown to strongly affect retrieval performance. An effective combination of heuristics was identified to obtain a word-based representation from text for the remainder of this thesis. The second research theme deals with concept-based retrieval. We compared a word-based to a concept-based representation and determined to what extent a manual concept-based representation can be automatically obtained from text. Retrieval based on only concepts was demonstrated to be significantly less effective than word-based retrieval. This deteriorated performance could be explained by errors in the classification process, limitations of the concept vocabularies and limited exhaustiveness of the concept-based document representations. Retrieval based on a combination of word-based and automatically obtained concept-based query representations did significantly improve word-only retrieval. In the third and last research theme we propose a cross-lingual framework for monolingual biomedical IR. In this framework, the integration of a concept-based representation is viewed as a cross-lingual matching problem involving a word-based and concept-based representation language. This framework gives us the opportunity to adopt a large set of established crosslingual information retrieval methods and techniques for this domain. Experiments with basic term-to-term translation models demonstrate that this approach can significantly improve word-based retrieval. Directions for future work are using these concepts for communication between user and retrieval system, extending upon the translation models and extending CLIR-enhanced concept-based retrieval outside the biomedical domain. Available online from http://purl.utwente.nl/publications/72481.

The influence of basic tokenization on biomedical document retrieval

Tokenization is a fundamental preprocessing step in Information Retrieval systems in which text is turned into index terms. This paper quantifies and compares the influence of various simple tokenization techniques on document retrieval effectiveness in two domains: biomedicine and news. As expected, biomedical retrieval is more sensitive to small changes in the tokenization method. The tokenization strategy can make the difference between a mediocre and well performing IR system, especially in the biomedical domain.

Exploiting user disagreement for web search evaluation: an experimental approach

To express a more nuanced notion of relevance as compared to binary judgments, graded relevance levels can be used for the evaluation of search results. Especially in Web search, users strongly prefer top results over less relevant results, and yet they often disagree on which are the top results for a given information need. Whereas previous works have generally considered disagreement as a negative effect, this paper proposes a method to exploit this user disagreement by integrating it into the evaluation procedure. First, we present experiments that investigate the user disagreement. We argue that, with a high disagreement, lower relevance levels might need to be promoted more than in the case where there is global consensus on the top results. This is formalized by introducing the User Disagreement Model, resulting in a weighting of the relevance levels with a probabilistic interpretation. A validity analysis is given, and we explain how to integrate the model with well-established evaluation metrics. Finally, we discuss a specific application of the model, in the estimation of suitable weights for the combined relevance of Web search snippets and pages.

What Snippets Say About Pages in Federated Web Search

What is the likelihood that a Web page is considered relevant to a query, given the relevance assessment of the corresponding snippet? Using a new federated IR test collection that contains search results from over a hundred search engines on the internet, we are able to investigate such research questions from a global perspective. Our test collection covers the main Web search engines like Google, Yahoo!, and Bing, as well as a number of smaller search engines dedicated to multimedia, shopping, etc., and as such reflects a realistic Web environment. Using a large set of relevance assessments, we are able to investigate the connection between snippet quality and page relevance. The dataset is strongly inhomogeneous, and although the assessors’ consistency is shown to be satisfying, care is required when comparing resources. To this end, a number of probabilistic quantities, based on snippet and page relevance, are introduced and evaluated.