TOPSIG : Topology Preserving Document Signatures

Performance comparisons between File Signatures and Inverted Files for text retrieval have previously shown several significant shortcomings of file signatures relative to inverted files. The inverted file approach underpins most state-of-the-art search engine algorithms, such as Language and Probabilistic models. It has been widely accepted that traditional file signatures are inferior alternatives to inverted files. This paper describes TopSig, a new approach to the construction of file signatures. Many advances in semantic hashing and dimensionality reduction have been made in recent times, but these were not so far linked to general purpose, signature file based, search engines. This paper introduces a different signature file approach that builds upon and extends these recent advances. We are able to demonstrate significant improvements in the performance of signature file based indexing and retrieval, performance that is comparable to that of state of the art inverted file based systems, including Language models and BM25. These findings suggest that file signatures offer a viable alternative to inverted files in suitable settings and positions the file signatures model in the class of Vector Space retrieval models.

Pairwise similarity of TopSig document signatures

This paper analyses the pairwise distances of signatures produced by the TopSig retrieval model on two document collections. The distribution of the distances are compared to purely random signatures. It explains why TopSig is only competitive with state of the art retrieval models at early precision. Only the local neighbourhood of the signatures is interpretable. We suggest this is a common property of vector space models.

Efficient top-k retrieval with signatures

This paper describes a new method of indexing and searching large binary signature collections to efficiently find similar signatures, addressing the scalability problem in signature search. Signatures offer efficient computation with acceptable measure of similarity in numerous applications. However, performing a complete search with a given search argument (a signature) requires a Hamming distance calculation against every signature in the collection. This quickly becomes excessive when dealing with large collections, presenting issues of scalability that limit their applicability. Our method efficiently finds similar signatures in very large collections, trading memory use and precision for greatly improved search speed. Experimental results demonstrate that our approach is capable of finding a set of nearest signatures to a given search argument with a high degree of speed and fidelity.

Scalable document hashing and retrieval

This thesis studies document signatures, which are small representations of documents and other objects that can be stored compactly and compared for similarity. This research finds that document signatures can be effectively and efficiently used to both search and understand relationships between documents in large collections, scalable enough to search a billion documents in a fraction of a second. Deliverables arising from the research include an investigation of the representational capacity of document signatures, the publication of an open-source signature search platform and an approach for scaling signature retrieval to operate efficiently on collections containing hundreds of millions of documents.

Locality-sensitive hashing for protein classification

Determination of sequence similarity is a central issue in computational biology, a problem addressed primarily through BLAST, an alignment based heuristic which has underpinned much of the analysis and annotation of the genomic era. Despite their success, alignment-based approaches scale poorly with increasing data set size, and are not robust under structural sequence rearrangements. Successive waves of innovation in sequencing technologies – so-called Next Generation Sequencing (NGS) approaches – have led to an explosion in data availability, challenging existing methods and motivating novel approaches to sequence representation and similarity scoring, including adaptation of existing methods from other domains such as information retrieval. In this work, we investigate locality-sensitive hashing of sequences through binary document signatures, applying the method to a bacterial protein classification task. Here, the goal is to predict the gene family to which a given query protein belongs. Experiments carried out on a pair of small but biologically realistic datasets (the full protein repertoires of families of Chlamydia and Staphylococcus aureus genomes respectively) show that a measure of similarity obtained by locality sensitive hashing gives highly accurate results while offering a number of avenues which will lead to substantial performance improvements over BLAST..

Parallel streaming signature EM-tree: A clustering algorithm for web scale applications

The proliferation of the web presents an unsolved problem of automatically analyzing billions of pages of natural language. We introduce a scalable algorithm that clusters hundreds of millions of web pages into hundreds of thousands of clusters. It does this on a single mid-range machine using efficient algorithms and compressed document representations. It is applied to two web-scale crawls covering tens of terabytes. ClueWeb09 and ClueWeb12 contain 500 and 733 million web pages and were clustered into 500,000 to 700,000 clusters. To the best of our knowledge, such fine grained clustering has not been previously demonstrated. Previous approaches clustered a sample that limits the maximum number of discoverable clusters. The proposed EM-tree algorithm uses the entire collection in clustering and produces several orders of magnitude more clusters than the existing algorithms. Fine grained clustering is necessary for meaningful clustering in massive collections where the number of distinct topics grows linearly with collection size. These fine-grained clusters show an improved cluster quality when assessed with two novel evaluations using ad hoc search relevance judgments and spam classifications for external validation. These evaluations solve the problem of assessing the quality of clusters where categorical labeling is unavailable and unfeasible.

Document clustering algorithms, representations and evaluation for information retrieval

This thesis presents new methods for classification and thematic grouping of billions of web pages, at scales previously not achievable. This process is also known as document clustering, where similar documents are automatically associated with clusters that represent various distinct topic. These automatically discovered topics are in turn used to improve search engine performance by only searching the topics that are deemed relevant to particular user queries.