Cosimo Rulli
YOU?
Author Swipe
View article: Effective Inference-Free Retrieval for Learned Sparse Representations
Effective Inference-Free Retrieval for Learned Sparse Representations Open
Learned Sparse Retrieval (LSR) is an effective IR approach that exploits pre-trained language models for encoding text into a learned bag of words. Several efforts in the literature have shown that sparsity is key to enabling a good trade-…
View article: Efficient Conversational Search via Topical Locality in Dense Retrieval
Efficient Conversational Search via Topical Locality in Dense Retrieval Open
Pre-trained language models have been widely exploited to learn dense representations of documents and queries for information retrieval. While previous efforts have primarily focused on improving effectiveness and user satisfaction, respo…
View article: Investigating the Scalability of Approximate Sparse Retrieval Algorithms to Massive Datasets
Investigating the Scalability of Approximate Sparse Retrieval Algorithms to Massive Datasets Open
Learned sparse text embeddings have gained popularity due to their effectiveness in top-k retrieval and inherent interpretability. Their distributional idiosyncrasies, however, have long hindered their use in real-world retrieval systems. …
View article: kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors Search
kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors Search Open
Approximate Nearest Neighbors (ANN) search is a crucial task in several applications like recommender systems and information retrieval. Current state-of-the-art ANN libraries, although being performance-oriented, often lack modularity and…
View article: ChatGPT Versus Modest Large Language Models: An Extensive Study on Benefits and Drawbacks for Conversational Search
ChatGPT Versus Modest Large Language Models: An Extensive Study on Benefits and Drawbacks for Conversational Search Open
Large Language Models (LLMs) are effective in modeling text syntactic and semantic content, making them a strong choice to perform conversational query rewriting. While previous approaches proposed NLP-based custom models, requiring signif…
View article: Pairing Clustered Inverted Indexes with κ-NN Graphs for Fast Approximate Retrieval over Learned Sparse Representations
Pairing Clustered Inverted Indexes with κ-NN Graphs for Fast Approximate Retrieval over Learned Sparse Representations Open
Learned sparse representations form an effective and interpretable class of embeddings for text retrieval. While exact top-k retrieval over such embeddings faces efficiency challenges, a recent algorithm called Seismic has enabled remarkab…
View article: Pairing Clustered Inverted Indexes with kNN Graphs for Fast Approximate Retrieval over Learned Sparse Representations
Pairing Clustered Inverted Indexes with kNN Graphs for Fast Approximate Retrieval over Learned Sparse Representations Open
Learned sparse representations form an effective and interpretable class of embeddings for text retrieval. While exact top-k retrieval over such embeddings faces efficiency challenges, a recent algorithm called Seismic has enabled remarkab…
View article: Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations
Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations Open
Learned sparse representations form an attractive class of contextual embeddings for text retrieval. That is so because they are effective models of relevance and are interpretable by design. Despite their apparent compatibility with inver…
View article: Efficient Multi-Vector Dense Retrieval Using Bit Vectors
Efficient Multi-Vector Dense Retrieval Using Bit Vectors Open
Dense retrieval techniques employ pre-trained large language models to build a high-dimensional representation of queries and passages. These representations compute the relevance of a passage w.r.t. to a query using efficient similarity m…
View article: PerconAI 2024: 3rd Workshop on Pervasive and Resource-Constrained Artificial Intelligence - Welcome and Committees
PerconAI 2024: 3rd Workshop on Pervasive and Resource-Constrained Artificial Intelligence - Welcome and Committees Open
The PeRConAI workshop aims at promoting the circulation of new ideas and research directions on pervasive and resource-constrained artificial intelligence, serving as a forum for practitioners and researchers working on the intersection be…
View article: Neural Network Compression using Binarization and Few Full-Precision Weights
Neural Network Compression using Binarization and Few Full-Precision Weights Open
Quantization and pruning are two effective Deep Neural Networks model compression methods. In this paper, we propose Automatic Prune Binarization (APB), a novel compression technique combining quantization with pruning. APB enhances the re…
View article: Distilled Neural Networks for Efficient Learning to Rank
Distilled Neural Networks for Efficient Learning to Rank Open
Recent studies in Learning to Rank have shown the possibility to effectively\ndistill a neural network from an ensemble of regression trees. This result\nleads neural networks to become a natural competitor of tree-based ensembles on\nthe …