Martin Theobald

Top-k query evaluation with probabilistic guarantees

Top-k queries based on ranking elements of multidimensional datasets are a fundamental building block for many kinds of information discovery. The best known general-purpose algorithm for evaluating top-k queries is Fagins threshold algorithm (TA). Since the users goal behind top-k queries is to identify one or a few relevant and novel data items, it is intriguing to use approximate variants of TA to reduce run-time costs. This paper introduces a family of approximate top-k algorithms based on probabilistic arguments. When scanning index lists of the underlying multidimensional data space in descending order of local scores, various forms of convolution and derived bounds are employed to predict when it is safe, with high probability, to drop candidate items and to prune the index scans. The precision and the efficiency of the developed methods are experimentally evaluated based on a large Web corpus and a structured data collection.

Databases with uncertainty and lineage

This paper introduces uldbs, an extension of relational databases with simple yet expressive constructs for representing and manipulating both lineage and uncertainty. Uncertain data and data lineage are two important areas of data management that have been considered extensively in isolation, however many applications require the features in tandem. Fundamentally, lineage enables simple and consistent representation of uncertain data, it correlates uncertainty in query results with uncertainty in the input data, and query processing with lineage and uncertainty together presents computational benefits over treating them separately. We show that the uldb representation is complete, and that it permits straightforward implementation of many relational operations. We define two notions of uldb minimality—data-minimal and lineage-minimal—and study minimization of uldb representations under both notions. With lineage, derived relations are no longer self-contained: their uncertainty depends on uncertainty in the base data. We provide an algorithm for the new operation of extracting a database subset in the presence of interconnected uncertainty. We also show how uldbs enable a new approach to query processing in probabilistic databases. Finally, we describe the current state of the Trio system, our implementation of uldbs under development at Stanford.

Entity resolution with iterative blocking

Entity Resolution (ER) is the problem of identifying which records in a database refer to the same real-world entity. An exhaustive ER process involves computing the similarities between pairs of records, which can be very expensive for large datasets. Various blocking techniques can be used to enhance the performance of ER by dividing the records into blocks in multiple ways and only comparing records within the same block. However, most blocking techniques process blocks separately and do not exploit the results of other blocks. In this paper, we propose an iterative blocking framework where the ER results of blocks are reflected to subsequently processed blocks. Blocks are now iteratively processed until no block contains any more matching records. Compared to simple blocking, iterative blocking may achieve higher accuracy because reflecting the ER results of blocks to other blocks may generate additional record matches. Iterative blocking may also be more efficient because processing a block now saves the processing time for other blocks. We implement a scalable iterative blocking system and demonstrate that iterative blocking can be more accurate and efficient than blocking for large datasets.

Scalable knowledge harvesting with high precision and high recall

Harvesting relational facts from Web sources has received great attention for automatically constructing large knowledge bases. Stateof-the-art approaches combine pattern-based gathering of fact candidates with constraint-based reasoning. However, they still face major challenges regarding the trade-offs between precision, recall, and scalability. Techniques that scale well are susceptible to noisy patterns that degrade precision, while techniques that employ deep reasoning for high precision cannot cope with Web-scale data. This paper presents a scalable system, called PROSPERA, for high-quality knowledge harvesting. We propose a new notion of ngram-itemsets for richer patterns, and use MaxSat-based constraint reasoning on both the quality of patterns and the validity of fact candidates.We compute pattern-occurrence statistics for two benefits: they serve to prune the hypotheses space and to derive informative weights of clauses for the reasoner. The paper shows how to incorporate these building blocks into a scalable architecture that can parallelize all phases on a Hadoop-based distributed platform. Our experiments with the ClueWeb09 corpus include comparisons to the recent ReadTheWeb experiment. We substantially outperform these prior results in terms of recall, with the same precision, while having low run-times.

From information to knowledge: harvesting entities and relationships from web sources

There are major trends to advance the functionality of search engines to a more expressive semantic level. This is enabled by the advent of knowledge-sharing communities such as Wikipedia and the progress in automatically extracting entities and relationships from semistructured as well as natural-language Web sources. Recent endeavors of this kind include DBpedia, EntityCube, KnowItAll, ReadTheWeb, and our own YAGO-NAGA project (and others). The goal is to automatically construct and maintain a comprehensive knowledge base of facts about named entities, their semantic classes, and their mutual relations as well as temporal contexts, with high precision and high recall. This tutorial discusses state-of-the-art methods, research opportunities, and open challenges along this avenue of knowledge harvesting.

Exploiting Lineage for Confidence Computation in Uncertain and Probabilistic Databases

We study the problem of computing query results with confidence values in ULDBs: relational databases with uncertainty and lineage. ULDBs, which subsume probabilistic databases, offer an alternative decoupled method of computing confidence values: Instead of computing confidences during query processing, compute them afterwards based on lineage. This approach enables a wider space of query plans, and it permits selective computations when not all confidence values are needed. This paper develops a suite of algorithms and optimizations for a broad class of relational queries on ULDBs. We provide confidence computation algorithms for single data items, as well as efficient batch algorithms to compute confidences for an entire relation or database. All algorithms incorporate memoization to avoid redundant computations, and they have been implemented in the Trio prototype ULDB database system. Performance characteristics and scalability of the algorithms are demonstrated through experimental results over a large synthetic dataset.

KORE: keyphrase overlap relatedness for entity disambiguation

Measuring the semantic relatedness between two entities is the basis for numerous tasks in IR, NLP, and Web-based knowledge extraction. This paper focuses on disambiguating names in a Web or text document by jointly mapping all names onto semantically related entities registered in a knowledge base. To this end, we have developed a novel notion of semantic relatedness between two entities represented as sets of weighted (multi-word) keyphrases, with consideration of partially overlapping phrases. This measure improves the quality of prior link-based models, and also eliminates the need for (usually Wikipedia-centric) explicit interlinkage between entities. Thus, our method is more versatile and can cope with long-tail and newly emerging entities that have few or no links associated with them. For efficiency, we have developed approximation techniques based on min-hash sketches and locality-sensitive hashing. Our experiments on semantic relatedness and on named entity disambiguation demonstrate the superiority of our method compared to state-of-the-art baselines.

TopX: efficient and versatile top-k query processing for semistructured data

Recent IR extensions to XML query languages such as Xpath 1.0 Full-Text or the NEXI query language of the INEX benchmark series reflect the emerging interest in IR-style ranked retrieval over semistructured data. TopX is a top-k retrieval engine for text and semistructured data. It terminates query execution as soon as it can safely determine the k top-ranked result elements according to a monotonic score aggregation function with respect to a multidimensional query. It efficiently supports vague search on both content- and structure-oriented query conditions for dynamic query relaxation with controllable influence on the result ranking. The main contributions of this paper unfold into four main points: (1) fully implemented models and algorithms for ranked XML retrieval with XPath Full-Text functionality, (2) efficient and effective top-k query processing for semistructured data, (3) support for integrating thesauri and ontologies with statistically quantified relationships among concepts, leveraged for word-sense disambiguation and query expansion, and (4) a comprehensive description of the TopX system, with performance experiments on large-scale corpora like TREC Terabyte and INEX Wikipedia.

Efficient and self-tuning incremental query expansion for top-k query processing

We present a novel approach for efficient and self-tuning query expansion that is embedded into a top-k query processor with candidate pruning. Traditional query expansion methods select expansion terms whose thematic similarity to the original query terms is above some specified threshold, thus generating a disjunctive query with much higher dimensionality. This poses three major problems: 1) the need for hand-tuning the expansion threshold, 2) the potential topic dilution with overly aggressive expansion, and 3) the drastically increased execution cost of a high-dimensional query. The method developed in this paper addresses all three problems by dynamically and incrementally merging the inverted lists for the potential expansion terms with the lists for the original query terms. A priority queue is used for maintaining result candidates, the pruning of candidates is based on Fagins family of top-k algorithms, and optionally probabilistic estimators of candidate scores can be used for additional pruning. Experiments on the TREC collections for the 2004 Robust and Terabyte tracks demonstrate the increased efficiency, effectiveness, and scalability of our approach.

Efficient text proximity search

In addition to purely occurrence-based relevance models, term proximity has been frequently used to enhance retrieval quality of keyword-oriented retrieval systems. While there have been approaches on effective scoring functions that incorporate proximity, there has not been much work on algorithms or access methods for their efficient evaluation. This paper presents an efficient evaluation framework including a proximity scoring function integrated within a top-k query engine for text retrieval. We propose precomputed and materialized index structures that boost performance. The increased retrieval effectiveness and efficiency of our framework are demonstrated through extensive experiments on a very large text benchmark collection. In combination with static index pruning for the proximity lists, our algorithm achieves an improvement of two orders of magnitude compared to a term-based top-k evaluation, with a significantly improved result quality.