Search Results for author: Nicola Tonellotto

Found 26 papers, 14 papers with code

A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems

no code implementations21 Jun 2024 Florin Cuconasu, Giovanni Trappolini, Nicola Tonellotto, Fabrizio Silvestri

Retrieval Augmented Generation (RAG) represents a significant advancement in artificial intelligence combining a retrieval phase with a generative phase, with the latter typically being powered by large language models (LLMs).

Graph Neural Re-Ranking via Corpus Graph

no code implementations17 Jun 2024 Andrea Giuseppe Di Francesco, Christian Giannetti, Nicola Tonellotto, Fabrizio Silvestri

Re-ranking systems aim to reorder an initial list of documents to satisfy better the information needs associated with a user-provided query.

Re-Ranking

Generating Query Recommendations via LLMs

no code implementations30 May 2024 Andrea Bacciu, Enrico Palumbo, Andreas Damianou, Nicola Tonellotto, Fabrizio Silvestri

We then improved our system by proposing a version that exploits query logs called Retriever-Augmented GQR (RA-GQR).

Recommendation Systems

Faster Learned Sparse Retrieval with Block-Max Pruning

1 code implementation2 May 2024 Antonio Mallia, Torten Suel, Nicola Tonellotto

Learned sparse retrieval systems aim to combine the effectiveness of contextualized language models with the scalability of conventional data structures such as inverted indexes.

Retrieval

A Reproducibility Study of PLAID

no code implementations23 Apr 2024 Sean MacAvaney, Nicola Tonellotto

The PLAID (Performance-optimized Late Interaction Driver) algorithm for ColBERTv2 uses clustered term representations to retrieve and progressively prune documents for final (exact) document scoring.

Re-Ranking Retrieval

Two-Step SPLADE: Simple, Efficient and Effective Approximation of SPLADE

no code implementations20 Apr 2024 Carlos Lassance, Hervé Dejean, Stéphane Clinchant, Nicola Tonellotto

Learned sparse models such as SPLADE have successfully shown how to incorporate the benefits of state-of-the-art neural information retrieval models into the classical inverted index data structure.

Information Retrieval

DESIRE-ME: Domain-Enhanced Supervised Information REtrieval using Mixture-of-Experts

1 code implementation20 Mar 2024 Pranav Kasela, Gabriella Pasi, Raffaele Perego, Nicola Tonellotto

Open-domain question answering requires retrieval systems able to cope with the diverse and varied nature of questions, providing accurate answers across a broad spectrum of query types and topics.

Information Retrieval Open-Domain Question Answering +1

The Power of Noise: Redefining Retrieval for RAG Systems

1 code implementation26 Jan 2024 Florin Cuconasu, Giovanni Trappolini, Federico Siciliano, Simone Filice, Cesare Campagnano, Yoelle Maarek, Nicola Tonellotto, Fabrizio Silvestri

Retrieval-Augmented Generation (RAG) has recently emerged as a method to extend beyond the pre-trained knowledge of Large Language Models by augmenting the original prompt with relevant passages or documents retrieved by an Information Retrieval (IR) system.

Information Retrieval Retrieval +1

RRAML: Reinforced Retrieval Augmented Machine Learning

no code implementations24 Jul 2023 Andrea Bacciu, Florin Cuconasu, Federico Siciliano, Fabrizio Silvestri, Nicola Tonellotto, Giovanni Trappolini

The emergence of large language models (LLMs) has revolutionized machine learning and related fields, showcasing remarkable abilities in comprehending, generating, and manipulating human language.

Retrieval

A Federated Channel Modeling System using Generative Neural Networks

no code implementations30 May 2023 Saira Bano, Pietro Cassarà, Nicola Tonellotto, Alberto Gotta

The paper proposes a data-driven approach to air-to-ground channel estimation in a millimeter-wave wireless network on an unmanned aerial vehicle.

Federated Learning Generative Adversarial Network

Integrating Item Relevance in Training Loss for Sequential Recommender Systems

no code implementations18 May 2023 Andrea Bacciu, Federico Siciliano, Nicola Tonellotto, Fabrizio Silvestri

Sequential Recommender Systems (SRSs) are a popular type of recommender system that learns from a user's history to predict the next item they are likely to interact with.

Recommendation Systems

A Static Pruning Study on Sparse Neural Retrievers

no code implementations25 Apr 2023 Carlos Lassance, Simon Lupart, Hervé Dejean, Stéphane Clinchant, Nicola Tonellotto

Sparse neural retrievers, such as DeepImpact, uniCOIL and SPLADE, have been introduced recently as an efficient and effective way to perform retrieval with inverted indexes.

Document Ranking Retrieval

Caching Historical Embeddings in Conversational Search

no code implementations25 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.

Conversational Search Document Embedding +1

Adaptive Re-Ranking with a Corpus Graph

1 code implementation18 Aug 2022 Sean MacAvaney, Nicola Tonellotto, Craig Macdonald

Search systems often employ a re-ranking pipeline, wherein documents (or passages) from an initial pool of candidates are assigned new ranking scores.

Passage Ranking Re-Ranking +1

Lecture Notes on Neural Information Retrieval

no code implementations27 Jul 2022 Nicola Tonellotto

These lecture notes focus on the recent advancements in neural information retrieval, with particular emphasis on the systems and models exploiting transformer networks.

Information Retrieval Retrieval

Faster Learned Sparse Retrieval with Guided Traversal

1 code implementation24 Apr 2022 Antonio Mallia, Joel Mackenzie, Torsten Suel, Nicola Tonellotto

Neural information retrieval architectures based on transformers such as BERT are able to significantly improve system effectiveness over traditional sparse models such as BM25.

Information Retrieval Retrieval

On Approximate Nearest Neighbour Selection for Multi-Stage Dense Retrieval

1 code implementation25 Aug 2021 Craig Macdonald, Nicola Tonellotto

In this work, we investigate the use of ANN scores for ranking the candidate documents, in order to decrease the number of candidate documents being fully scored.

Passage Ranking Retrieval

Query Embedding Pruning for Dense Retrieval

1 code implementation23 Aug 2021 Nicola Tonellotto, Craig Macdonald

Recent advances in dense retrieval techniques have offered the promise of being able not just to re-rank documents using contextualised language models such as BERT, but also to use such models to identify documents from the collection in the first place.

Passage Ranking Retrieval

On Single and Multiple Representations in Dense Passage Retrieval

1 code implementation13 Aug 2021 Craig Macdonald, Nicola Tonellotto, Iadh Ounis

The advent of contextualised language models has brought gains in search effectiveness, not just when applied for re-ranking the output of classical weighting models such as BM25, but also when used directly for passage indexing and retrieval, a technique which is called dense retrieval.

Passage Retrieval Re-Ranking +1

Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval

3 code implementations21 Jun 2021 Xiao Wang, Craig Macdonald, Nicola Tonellotto, Iadh Ounis

In particular, based on the pseudo-relevant set of documents identified using a first-pass dense retrieval, we extract representative feedback embeddings (using KMeans clustering) -- while ensuring that these embeddings discriminate among passages (based on IDF) -- which are then added to the query representation.

Information Retrieval Passage Ranking +2

Learning Passage Impacts for Inverted Indexes

1 code implementation24 Apr 2021 Antonio Mallia, Omar Khattab, Nicola Tonellotto, Torsten Suel

Neural information retrieval systems typically use a cascading pipeline, in which a first-stage model retrieves a candidate set of documents and one or more subsequent stages re-rank this set using contextualized language models such as BERT.

Information Retrieval Language Modelling +2

Declarative Experimentation in Information Retrieval using PyTerrier

9 code implementations28 Jul 2020 Craig Macdonald, Nicola Tonellotto

The advent of deep machine learning platforms such as Tensorflow and Pytorch, developed in expressive high-level languages such as Python, have allowed more expressive representations of deep neural network architectures.

Information Retrieval Retrieval

Expansion via Prediction of Importance with Contextualization

1 code implementation29 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.

Language Modelling Passage Ranking +2

Training Curricula for Open Domain Answer Re-Ranking

1 code implementation29 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.

Re-Ranking

Topical Result Caching in Web Search Engines

no code implementations9 Jan 2020 Ida Mele, Nicola Tonellotto, Ophir Frieder, Raffaele Perego

The results of queries characterized by a topic are kept in the fraction of the cache dedicated to it.

Information Retrieval Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.