Search Results for author:
Found 14 papers, 11 papers with code
Caching Historical Embeddings in Conversational Search
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.
Adaptive Re-Ranking with a Corpus Graph
Search systems often employ a re-ranking pipeline, wherein documents (or passages) from an initial pool of candidates are assigned new ranking scores.
Lecture Notes on Neural Information Retrieval
These lecture notes focus on the recent advancements in neural information retrieval, with particular emphasis on the systems and models exploiting transformer networks.
Faster Learned Sparse Retrieval with Guided Traversal
Neural information retrieval architectures based on transformers such as BERT are able to significantly improve system effectiveness over traditional sparse models such as BM25.
On Approximate Nearest Neighbour Selection for Multi-Stage Dense Retrieval
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.
Query Embedding Pruning for Dense Retrieval
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.
On Single and Multiple Representations in Dense Passage Retrieval
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.
Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval
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.
Ranked #1 on
TREC 2019 Passage Ranking
on MSMARCO
Learning Passage Impacts for Inverted Indexes
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.
Declarative Experimentation in Information Retrieval using PyTerrier
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.
Expansion via Prediction of Importance with Contextualization
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.
Efficient Document Re-Ranking for Transformers by Precomputing Term Representations
Deep pretrained transformer networks are effective at various ranking tasks, such as question answering and ad-hoc document ranking.
Training Curricula for Open Domain Answer Re-Ranking
We show that the proposed heuristics can be used to build a training curriculum that down-weights difficult samples early in the training process.
Topical Result Caching in Web Search Engines
The results of queries characterized by a topic are kept in the fraction of the cache dedicated to it.
