Search Results for author:
Found 16 papers, 7 papers with code
Investigating the Scalability of Approximate Sparse Retrieval Algorithms to Massive Datasets
Learned sparse text embeddings have gained popularity due to their effectiveness in top-k retrieval and inherent interpretability.
Pairing Clustered Inverted Indexes with kNN Graphs for Fast Approximate Retrieval over Learned Sparse Representations
At query time, each inverted list associated with a query term is traversed one block at a time in an arbitrary order, with the inner product between the query and summaries determining if a block must be evaluated.
Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search
Clustering-based nearest neighbor search is an effective method in which points are partitioned into geometric shards to form an index, with only a few shards searched during query processing to find a set of top-$k$ vectors.
Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations
In this work, we propose a novel organization of the inverted index that enables fast yet effective approximate retrieval over learned sparse embeddings.
A Learning-to-Rank Formulation of Clustering-Based Approximate Nearest Neighbor Search
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.
Foundations of Vector Retrieval
Vectors are universal mathematical objects that can represent text, images, speech, or a mix of these data modalities.
Bridging Dense and Sparse Maximum Inner Product Search
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.
Efficient and Effective Tree-based and Neural Learning to Rank
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.
An Approximate Algorithm for Maximum Inner Product Search over Streaming Sparse Vectors
To achieve optimal memory footprint and query latency, they rely on the near stationarity of documents and on laws governing natural languages.
Yggdrasil Decision Forests: A Fast and Extensible Decision Forests Library
Yggdrasil Decision Forests is a library for the training, serving and interpretation of decision forest models, targeted both at research and production work, implemented in C++, and available in C++, command line interface, Python (under the name TensorFlow Decision Forests), JavaScript, Go, and Google Sheets (under the name Simple ML for Sheets).
An Analysis of Fusion Functions for Hybrid Retrieval
In particular, we examine fusion by a convex combination (CC) of lexical and semantic scores, as well as the Reciprocal Rank Fusion (RRF) method, and identify their advantages and potential pitfalls.
Modeling Text with Decision Forests using Categorical-Set Splits
We define a condition that is specific to categorical-set features -- defined as an unordered set of categorical variables -- and present an algorithm to learn it, thereby equipping decision forests with the ability to directly model text, albeit without preserving sequential order.
Learning Representations for Axis-Aligned Decision Forests through Input Perturbation
Axis-aligned decision forests have long been the leading class of machine learning algorithms for modeling tabular data.
An Alternative Cross Entropy Loss for Learning-to-Rank
Listwise learning-to-rank methods form a powerful class of ranking algorithms that are widely adopted in applications such as information retrieval.
TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank
We propose TensorFlow Ranking, the first open source library for solving large-scale ranking problems in a deep learning framework.
Learning Groupwise Multivariate Scoring Functions Using Deep Neural Networks
To overcome this limitation, we propose a new framework for multivariate scoring functions, in which the relevance score of a document is determined jointly by multiple documents in the list.
