TILDE: Term independent likelihood moDEl for passage re-ranking
Deep language models (deep LMs) are increasingly being used for full text retrieval or
within cascade retrieval pipelines as later-stage re-rankers. A problem with using deep LMs …
within cascade retrieval pipelines as later-stage re-rankers. A problem with using deep LMs …
Deep query likelihood model for information retrieval
The query likelihood model (QLM) for information retrieval has been thoroughly investigated
and utilised. At the basis of this method is the representation of queries and documents as …
and utilised. At the basis of this method is the representation of queries and documents as …
Bootstrapped nDCG Estimation in the Presence of Unjudged Documents
Retrieval studies often reuse TREC collections after the corresponding tracks have passed.
Yet, a fair evaluation of new systems that retrieve documents outside the original judgment …
Yet, a fair evaluation of new systems that retrieve documents outside the original judgment …
When measurement misleads: The limits of batch assessment of retrieval systems
J Zobel - ACM SIGIR Forum, 2023 - dl.acm.org
The discipline of information retrieval (IR) has a long history of examination of how best to
measure performance. In particular, there is an extensive literature on the practice of …
measure performance. In particular, there is an extensive literature on the practice of …
Analyzing Adversarial Attacks on Sequence-to-Sequence Relevance Models
Modern sequence-to-sequence relevance models like monoT5 can effectively capture
complex textual interactions between queries and documents through cross-encoding …
complex textual interactions between queries and documents through cross-encoding …
The Impact of Judgment Variability on the Consistency of Offline Effectiveness Measures
Measurement of the effectiveness of search engines is often based on use of relevance
judgments. It is well known that judgments can be inconsistent between judges, leading to …
judgments. It is well known that judgments can be inconsistent between judges, leading to …
SCAI-QReCC shared task on conversational question answering
Search-Oriented Conversational AI (SCAI) is an established venue that regularly puts a
spotlight upon the recent work advancing the field of conversational search. SCAI'21 was …
spotlight upon the recent work advancing the field of conversational search. SCAI'21 was …
[PDF][PDF] Team openwebsearch at CLEF 2024: QuantumCLEF
We describe the OpenWebSearch group's participation in the CLEF 2024 QuantumClef IR
Feature Selection track. Our submitted runs focus on the observation that the importance of …
Feature Selection track. Our submitted runs focus on the observation that the importance of …
How Train–Test Leakage Affects Zero-Shot Retrieval
Neural retrieval models are often trained on (subsets of) the millions of queries of the MS
MARCO/ORCAS datasets and then tested on the 250 Robust04 queries or other TREC …
MARCO/ORCAS datasets and then tested on the 250 Robust04 queries or other TREC …
Evaluating the predictivity of IR experiments
Experimental evaluation is regarded as a critical element of any research activity in
Information Retrieval, and is typically used to support assertions of the form" Technique A …
Information Retrieval, and is typically used to support assertions of the form" Technique A …