An axiomatic approach to diagnosing neural IR models
Traditional retrieval models such as BM25 or language models have been engineered
based on search heuristics that later have been formalized into axioms. The axiomatic …
based on search heuristics that later have been formalized into axioms. The axiomatic …
Text indexing for long patterns: Anchors are all you need
L Ayad, G Loukidis, S Pissis - Proceedings of the VLDB Endowment …, 2023 - kclpure.kcl.ac.uk
In many real-world database systems, a large fraction of the data is represented by strings:
sequences of letters over some alphabet. This is because strings can easily encode data …
sequences of letters over some alphabet. This is because strings can easily encode data …
Learning relevant questions for conversational product search using deep reinforcement learning
A Montazeralghaem, J Allan - … Conference on Web Search and Data …, 2022 - dl.acm.org
We propose RelQuest, a conversational product search model based on reinforcement
learning to generate questions from product descriptions in each round of the conversation …
learning to generate questions from product descriptions in each round of the conversation …
An axiomatic approach to corpus-based cross-language information retrieval
A major challenge in cross-language information retrieval (CLIR) is the adoption of
translation knowledge in retrieval models, as it affects term weighting which is known to …
translation knowledge in retrieval models, as it affects term weighting which is known to …
Text Indexing for Long Patterns using Locally Consistent Anchors
LAK Ayad, G Loukides, SP Pissis - arXiv preprint arXiv:2407.11819, 2024 - arxiv.org
In many real-world database systems, a large fraction of the data is represented by strings:
sequences of letters over some alphabet. This is because strings can easily encode data …
sequences of letters over some alphabet. This is because strings can easily encode data …
BM25 beyond query-document similarity
The massive growth of information produced and shared online has made retrieving
relevant documents a difficult task. Query Expansion (QE) based on term co-occurrence …
relevant documents a difficult task. Query Expansion (QE) based on term co-occurrence …
Space-Efficient Indexes for Uncertain Strings
E Gabory, C Liu, G Loukides, SP Pissis… - arXiv preprint arXiv …, 2024 - arxiv.org
Strings in the real world are often encoded with some level of uncertainty. In the character-
level uncertainty model, an uncertain string $ X $ of length $ n $ on an alphabet $\Sigma $ is …
level uncertainty model, an uncertain string $ X $ of length $ n $ on an alphabet $\Sigma $ is …
Algorithmic Vibe in Information Retrieval
When information retrieval systems return a ranked list of results in response to a query, they
may be choosing from a large set of candidate results that are equally useful and relevant …
may be choosing from a large set of candidate results that are equally useful and relevant …
Theoretical analysis of interdependent constraints in pseudo-relevance feedback
Axiomatic analysis is a well-defined theoretical framework for analytical evaluation of
information retrieval models. The current studies in axiomatic analysis implicitly assume that …
information retrieval models. The current studies in axiomatic analysis implicitly assume that …
Pseudo-relevance feedback based on locally-built co-occurrence graphs
Abstract In Information Retrieval (IR), user queries are often too short, making the selection
of relevant documents hard. Pseudo-relevance feedback (PRF) is an effective method to …
of relevant documents hard. Pseudo-relevance feedback (PRF) is an effective method to …