Christina Lioma

A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion

Users may strive to formulate an adequate textual query for their information need. Search engines assist the users by presenting query suggestions. To preserve the original search intent, suggestions should be context-aware and account for the previous queries issued by the user. Achieving context awareness is challenging due to data sparsity. We present a novel hierarchical recurrent encoder-decoder architecture that makes possible to account for sequences of previous queries of arbitrary lengths. As a result, our suggestions are sensitive to the order of queries in the context while avoiding data sparsity. Additionally, our model can suggest for rare, or long-tail, queries. The produced suggestions are synthetic and are sampled one word at a time, using computationally cheap decoding techniques. This is in contrast to current synthetic suggestion models relying upon machine learning pipelines and hand-engineered feature sets. Results show that our model outperforms existing context-aware approaches in a next query prediction setting. In addition to query suggestion, our architecture is general enough to be used in a variety of other applications.

University of glasgow at WebCLEF 2005: experiments in per-field normalisation and language specific stemming

We participated in the WebCLEF 2005 monolingual task. In this task, a search system aims to retrieve relevant documents from a multilingual corpus of Web documents from Web sites of European governments. Both the documents and the queries are written in a wide range of European languages. A challenge in this setting is to detect the language of documents and topics, and to process them appropriately. We develop a language specific technique for applying the correct stemming approach, as well as for removing the correct stopwords from the queries. We represent documents using three fields, namely content, title, and anchor text of incoming hyperlinks. We use a technique called per-field normalisation, which extends the Divergence From Randomness (DFR) framework, to normalise the term frequencies, and to combine them across the three fields. We also employ the length of the URL path of Web documents. The ranking is based on combinations of both the language specific stemming, if applied, and the per-field normalisation. We use our Terrier platform for all our experiments. The overall performance of our techniques is outstanding, achieving the overall top four performing runs, as well as the top performing run without metadata in the monolingual task. The best run only uses per-field normalisation, without applying stemming.

FindZebra: A search engine for rare diseases

BACKGROUND The web has become a primary information resource about illnesses and treatments for both medical and non-medical users. Standard web search is by far the most common interface to this information. It is therefore of interest to find out how well web search engines work for diagnostic queries and what factors contribute to successes and failures. Among diseases, rare (or orphan) diseases represent an especially challenging and thus interesting class to diagnose as each is rare, diverse in symptoms and usually has scattered resources associated with it. METHODS We design an evaluation approach for web search engines for rare disease diagnosis which includes 56 real life diagnostic cases, performance measures, information resources and guidelines for customising Google Search to this task. In addition, we introduce FindZebra, a specialized (vertical) rare disease search engine. FindZebra is powered by open source search technology and uses curated freely available online medical information. RESULTS FindZebra outperforms Google Search in both default set-up and customised to the resources used by FindZebra. We extend FindZebra with specialized functionalities exploiting medical ontological information and UMLS medical concepts to demonstrate different ways of displaying the retrieved results to medical experts. CONCLUSIONS Our results indicate that a specialized search engine can improve the diagnostic quality without compromising the ease of use of the currently widely popular standard web search. The proposed evaluation approach can be valuable for future development and benchmarking. The FindZebra search engine is available at http://www.findzebra.com/.

A syntactically-based query reformulation technique for information retrieval

Whereas in language words of high frequency are generally associated with low content [Bookstein, A., & Swanson, D. (1974). Probabilistic models for automatic indexing. Journal of the American Society of Information Science, 25(5), 312-318; Damerau, F. J. (1965). An experiment in automatic indexing. American Documentation, 16, 283-289; Harter, S. P. (1974). A probabilistic approach to automatic keyword indexing. PhD thesis, University of Chicago; Sparck-Jones, K. (1972). A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation, 28, 11-21; Yu, C., & Salton, G. (1976). Precision weighting - an effective automatic indexing method. Journal of the Association for Computer Machinery (ACM), 23(1), 76-88], shallow syntactic fragments of high frequency generally correspond to lexical fragments of high content [Lioma, C., & Ounis, I. (2006). Examining the content load of part of speech blocks for information retrieval. In Proceedings of the international committee on computational linguistics and the association for computational linguistics (COLING/ACL 2006), Sydney, Australia]. We implement this finding to Information Retrieval, as follows. We present a novel automatic query reformulation technique, which is based on shallow syntactic evidence induced from various language samples, and used to enhance the performance of an Information Retrieval system. Firstly, we draw shallow syntactic evidence from language samples of varying size, and compare the effect of language sample size upon retrieval performance, when using our syntactically-based query reformulation (SQR) technique. Secondly, we compare SQR to a state-of-the-art probabilistic pseudo-relevance feedback technique. Additionally, we combine both techniques and evaluate their compatibility. We evaluate our proposed technique across two standard Text REtrieval Conference (TREC) English test collections, and three statistically different weighting models. Experimental results suggest that SQR markedly enhances retrieval performance, and is at least comparable to pseudo-relevance feedback. Notably, the combination of SQR and pseudo-relevance feedback further enhances retrieval performance considerably. These collective experimental results confirm the tenet that high frequency shallow syntactic fragments correspond to content-bearing lexical fragments.

Preliminary study into query translation for patent retrieval

Patent retrieval is a branch of Information Retrieval (IR) aiming to support patent professionals in retrieving patents that satisfy their information needs. Often, patent granting bodies require patents to be partially translated into one or more major foreign languages, so that language boundaries do not hinder their accessibility. This multilinguality of patent collections offers opportunities for improving patent retrieval. In this work we exploit these opportunities by applying query translation to patent retrieval. We expand monolingual patent queries with their translations, using both a domain-specific patent dictionary that we extract from the patent collection, and a general domain-free dictionary. Experimental evaluation on a standard CLEF-IP dataset shows that using either translation dictionary fetches similar results: query translation can help patent retrieval, but not always, and without great improvement compared to standard statistical monolingual query expansion (Rocchio). The improvement is greater when the source language is English, as opposed to French or German, a finding partly due to the effect of the complex French and German morphology upon translation accuracy, but also partly due to the prevalence of English in the collection. A thorough per-query analysis reveals that cases where standard query expansion fails (e.g. zero recall) can benefit from query translation.

Random walk term weighting for information retrieval

We present a way of estimating term weights for Information Retrieval (IR), using term co-occurrence as a measure of dependency between terms.We use the random walk graph-based ranking algorithm on a graph that encodes terms and co-occurrence dependencies in text, from which we derive term weights that represent a quantification of how a term contributes to its context. Evaluation on two TREC collections and 350 topics shows that the random walk-based term weights perform at least comparably to the traditional tf-idf term weighting, while they outperform it when the distance between co-occurring terms is between 6 and 30 terms.

Examining the Content Load of Part of Speech Blocks for Information Retrieval

We investigate the connection between part of speech (POS) distribution and content in language. We define POS blocks to be groups of parts of speech. We hypothesise that there exists a directly proportional relation between the frequency of POS blocks and their content salience. We also hypothesise that the class membership of the parts of speech within such blocks reflects the content load of the blocks, on the basis that open class parts of speech are more content-bearing than closed class parts of speech. We test these hypotheses in the context of Information Retrieval, by syntactically representing queries, and removing from them content-poor blocks, in line with the aforementioned hypotheses. For our first hypothesis, we induce POS distribution information from a corpus, and approximate the probability of occurrence of POS blocks as per two statistical estimators separately. For our second hypothesis, we use simple heuristics to estimate the content load within POS blocks. We use the Text REtrieval Conference (TREC) queries of 1999 and 2000 to retrieve documents from the WT2G and WT10G test collections, with five different retrieval strategies. Experimental outcomes confirm that our hypotheses hold in the context of Information Retrieval.

Rhetorical relations for information retrieval

Typically, every part in most coherent text has some plausible reason for its presence, some function that it performs to the overall semantics of the text. Rhetorical relations, e.g. contrast, cause, explanation, describe how the parts of a text are linked to each other. Knowledge about this so-called discourse structure has been applied successfully to several natural language processing tasks. This work studies the use of rhetorical relations for Information Retrieval (IR): Is there a correlation between certain rhetorical relations and retrieval performance? Can knowledge about a documents rhetorical relations be useful to IR? We present a language model modification that considers rhetorical relations when estimating the relevance of a document to a query. Empirical evaluation of different versions of our model on TREC settings shows that certain rhetorical relations can benefit retrieval effectiveness notably (>10% in mean average precision over a state-of-the-art baseline).

Power Law Distributions in Information Retrieval

Several properties of information retrieval (IR) data, such as query frequency or document length, are widely considered to be approximately distributed as a power law. This common assumption aims to focus on specific characteristics of the empirical probability distribution of such data (e.g., its scale-free nature or its long/fat tail). This assumption, however, may not be always true. Motivated by recent work in the statistical treatment of power law claims, we investigate two research questions: (i) To what extent do power law approximations hold for term frequency, document length, query frequency, query length, citation frequency, and syntactic unigram frequency? And (ii) what is the computational cost of replacing ad hoc power law approximations with more accurate distribution fitting? We study 23 TREC and 5 non-TREC datasets and compare the fit of power laws to 15 other standard probability distributions. We find that query frequency and 5 out of 24 term frequency distributions are best approximated by a power law. All remaining properties are better approximated by the Inverse Gaussian, Generalized Extreme Value, Negative Binomial, or Yule distribution. We also find the overhead of replacing power law approximations by more informed distribution fitting to be negligible, with potential gains to IR tasks like index compression or test collection generation for IR evaluation.

A subjective logic formalisation of the principle of polyrepresentation for information needs

Interactive Information Retrieval refers to the branch of Information Retrieval that considers the retrieval process with respect to a wide range of contexts, which may affect the users information seeking experience. The identification and representation of such contexts has been the object of the principle of Polyrepresentation, a theoretical framework for reasoning about different representations arising from interactive information retrieval in a given context. Although the principle of Polyrepresentation has received attention from many researchers, not much empirical work has been done based on it. One reason may be that it has not yet been formalised mathematically. In this paper we propose an up-to-date and flexible mathematical formalisation of the principle of Polyrepresentation for information needs. Specifically, we apply Subjective Logic to model different representations of information needs as beliefs marked by degrees of uncertainty. We combine such beliefs using different logical operators, and we discuss these combinations with respect to different retrieval scenarios and situations. A formal model is introduced and discussed, with illustrative applications to the modelling of information needs.