no code implementations • 20 May 2024 • Sebastian Bruch, Aditya Krishnan, Franco Maria Nardini
Clustering-based nearest neighbor search is a simple yet effective method in which data points are partitioned into geometric shards to form an index, and only a few shards are searched during query processing to find an approximate set of top-$k$ vectors.
1 code implementation • 29 Apr 2024 • Sebastian Bruch, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini
In this work, we propose a novel organization of the inverted index that enables fast yet effective approximate retrieval over learned sparse embeddings.
1 code implementation • 17 Apr 2024 • Thomas Vecchiato, Claudio Lucchese, Franco Maria Nardini, Sebastian Bruch
Its objective is to return a set of $k$ data points that are closest to a query point, with its accuracy measured by the proportion of exact nearest neighbors captured in the returned set.
1 code implementation • 3 Apr 2024 • Franco Maria Nardini, Cosimo Rulli, Rossano Venturini
This paper proposes ``Efficient Multi-Vector dense retrieval with Bit vectors'' (EMVB), a novel framework for efficient query processing in multi-vector dense retrieval.
no code implementations • 16 Sep 2023 • Sebastian Bruch, Franco Maria Nardini, Amir Ingber, Edo Liberty
Maximum inner product search (MIPS) over dense and sparse vectors have progressed independently in a bifurcated literature for decades; the latter is better known as top-$k$ retrieval in Information Retrieval.
no code implementations • 21 Jun 2023 • Vincenzo Paparella, Vito Walter Anelli, Franco Maria Nardini, Raffaele Perego, Tommaso Di Noia
To our knowledge, there are no well-recognized strategies to decide which point should be selected on the frontier.
no code implementations • 15 Jun 2023 • Franco Maria Nardini, Cosimo Rulli, Salvatore Trani, Rossano Venturini
Quantization and pruning are two effective Deep Neural Networks model compression methods.
no code implementations • 15 May 2023 • Sebastian Bruch, Claudio Lucchese, Franco Maria Nardini
We believe that by understanding the fundamentals underpinning these algorithmic and data structure solutions for containing the contentious relationship between efficiency and effectiveness, one can better identify future directions and more efficiently determine the merits of ideas.
no code implementations • 25 Jan 2023 • Sebastian Bruch, Franco Maria Nardini, Amir Ingber, Edo Liberty
To achieve optimal memory footprint and query latency, they rely on the near stationarity of documents and on laws governing natural languages.
no code implementations • 25 Nov 2022 • Ophir Frieder, Ida Mele, Cristina Ioana Muntean, Franco Maria Nardini, Raffaele Perego, Nicola Tonellotto
Our achieved high cache hit rates significantly improve the responsiveness of conversational systems while likewise reducing the number of queries managed on the search back-end.
1 code implementation • 1 Jun 2022 • Claudio Lucchese, Franco Maria Nardini, Salvatore Orlando, Raffaele Perego, Alberto Veneri
Interpretable Learning to Rank (LtR) is an emerging field within the research area of explainable AI, aiming at developing intelligible and accurate predictive models.
1 code implementation • 26 Nov 2021 • Lorenzo Beretta, Franco Maria Nardini, Roberto Trani, Rossano Venturini
In this paper, we address the problem of finding a champion of the tournament, also known as Copeland winner, which is a player that wins the highest number of matches.
1 code implementation • 6 May 2021 • Francesco Busolin, Claudio Lucchese, Franco Maria Nardini, Salvatore Orlando, Raffaele Perego, Salvatore Trani
Modern search engine ranking pipelines are commonly based on large machine-learned ensembles of regression trees.
no code implementations • 17 Nov 2020 • Lorenzo Valerio, Franco Maria Nardini, Andrea Passarella, Raffaele Perego
Results show that DynHP compresses a NN up to $10$ times without significant performance drops (up to $3. 5\%$ additional error w. r. t.
no code implementations • 30 Apr 2020 • Claudio Lucchese, Franco Maria Nardini, Salvatore Orlando, Raffaele Perego, Salvatore Trani
In this paper, we investigate the novel problem of \textit{query-level early exiting}, aimed at deciding the profitability of early stopping the traversal of the ranking ensemble for all the candidate documents to be scored for a query, by simply returning a ranking based on the additive scores computed by a limited portion of the ensemble.
1 code implementation • 29 Apr 2020 • Sean MacAvaney, Franco Maria Nardini, Raffaele Perego, Nicola Tonellotto, Nazli Goharian, Ophir Frieder
Deep pretrained transformer networks are effective at various ranking tasks, such as question answering and ad-hoc document ranking.
1 code implementation • 29 Apr 2020 • Sean MacAvaney, Franco Maria Nardini, Raffaele Perego, Nicola Tonellotto, Nazli Goharian, Ophir Frieder
We also observe that the performance is additive with the current leading first-stage retrieval methods, further narrowing the gap between inexpensive and cost-prohibitive passage ranking approaches.
1 code implementation • 29 Apr 2020 • Sean MacAvaney, Franco Maria Nardini, Raffaele Perego, Nicola Tonellotto, Nazli Goharian, Ophir Frieder
We show that the proposed heuristics can be used to build a training curriculum that down-weights difficult samples early in the training process.