Antonio Mallia, Michal Siedlaczek and Torsten Suel. An Experimental Study of Index Compression and DAAT Query Processing Methods. In Proceedings of the 41st European Conference on Information Retrieval (ECIR). 2019

Abstract: In the last two decades, the IR community has seen numerous advances in top-k query processing and inverted index compression techniques. While newly proposed techniques are typically proposed against a few baselines, these evaluations are often very limited, and we feel that there is no clear overall picture on the best choices of algorithms and compression methods. In this paper, we attempt to address this issue by evaluating a number of state-of-the-art index compression methods and safe disjunctive DAAT query processing algorithms. Our goal is to understand how much index compression performance impacts overall query processing speeds, how the choice of query processing algorithm depends on the compression method used, and how performance is impacted by document reordering techniques and the number of results returned, keeping in mind that current search engines typically use sets of hundreds or thousands of candidates for further reranking.

Joel Mackenzie, Antonio Mallia, Matthias Petri, J. Shane Culpepper and Torsten Suel. Compressing Inverted Indexes with Recursive Graph Bisection: A Reproducibility Study. In Proceedings of the 41st European Conference on Information Retrieval (ECIR). 2019

Abstract: Document reordering is an important but often overlooked preprocessing stage in index construction. Reordering document identifiers in graphs and inverted indexes has been shown to reduce storage costs and improve processing efficiency in the resulting indexes. However, surprisingly few document reordering algorithms are publicly available despite their importance. A new reordering algorithm derived from recursive graph bisection was recently proposed by Dhulipala et al., and shown to be highly effective and efficient when compared against other state-of-the-art reordering strategies. In this work, we present a reproducibility study of this new algorithm. We describe both the implementation challenges faced, as well as the performance characteristics of our clean-room reimplementation. We show that we are able to successfully reproduce the core results of the original paper, and show that the algorithm generalizes to other collections and indexing frameworks. Furthermore, we make our implementation publicly available to help promote further research in this space.

Antonio Mallia, Elia Porciani. Faster BlockMax WAND with Longer Skipping. In Proceedings of the 41st European Conference on Information Retrieval (ECIR). 2019

Abstract: One of the major problems for modern search engines is to keep up with the tremendous growth in the size of the web and the number of queries submitted by users. The amount of data being generated today can only be processed and managed with specialized technologies. BlockMaxWAND and the more recent Variable BlockMaxWAND represent the most advanced query processing algorithms that make use of dynamic pruning techniques, which allow them to retrieve the top k most relevant documents for a given query without any effectiveness degradation of its ranking. In this paper, we describe a new technique for the BlockMaxWAND family of query processing algorithm, which improves block skipping in order to increase its efficiency. We show that our optimization is able to improve query processing speed on short queries by up to 37% with negligible additional space overhead.

Melanie Tosik, Antonio Mallia, Kedar Gangopadhyay. Debunking Fake News One Feature at a Time. CoRR abs/1808.02831. 2018

Abstract: Identifying the stance of a news article body with respect to a certain headline is the first step to automated fake news detection. In this paper, we introduce a 2-stage ensemble model to solve the stance detection task. By using only hand-crafted features as input to a gradient boosting classifier, we are able to achieve a score of 9161.5 out of 11651.25 (78.63%) on the official Fake News Challenge (Stage 1) dataset. We identify the most useful features for detecting fake news and discuss how sampling techniques can be used to improve recall accuracy on a highly imbalanced dataset.

Antonio Mallia, Giuseppe Ottaviano, Elia Porciani, Nicola Tonellotto, and Rossano Venturini. Faster BlockMax WAND with Variable-sized Blocks. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). 2017

Abstract: Query processing is one of the main bottlenecks in large-scale search engines. Retrieving the top k most relevant documents for a given query can be extremely expensive, as it involves scoring large amounts of documents. Several dynamic pruning techniques have been introduced in the literature to tackle this problem, such as BlockMaxWAND, which splits the inverted index into constant- sized blocks and stores the maximum document-term scores per block; this information can be used during query execution to safely skip low-score documents, producing many-fold speedups over exhaustive methods. We introduce a refinement for BlockMaxWAND that uses variable- sized blocks, rather than constant-sized. We set up the problem of deciding the block partitioning as an optimization problem which maximizes how accurately the block upper bounds represent the underlying scores, and describe an efficient algorithm to find an approximate solution, with provable approximation guarantees. rough an extensive experimental analysis we show that our method significantly outperforms the state of the art roughly by a factor 2×. We also introduce a compressed data structure to represent the additional block information, providing a compression ratio of roughly 50%, while incurring only a small speed degradation, no more than 10% with respect to its uncompressed counterpart.

Other activities