![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Chapter and Conference Paper
Towards Automated End-to-End Health Misinformation Free Search with a Large Language Model
In the information age, health misinformation remains a notable challenge to public welfare. Integral to addressing this issue is the development of search systems adept at identifying and filtering out mislea...
-
Chapter and Conference Paper
PyGaggle: A Gaggle of Resources for Open-Domain Question Answering
Text retrieval using dense–sparse hybrids has been gaining popularity because of their effectiveness. Improvements to both sparse and dense models have also been noted, in the context of open-domain question a...
-
Chapter and Conference Paper
Answer Retrieval for Math Questions Using Structural and Dense Retrieval
Answer retrieval for math questions is a challenging task due to the complex and structured nature of mathematical expressions. In this paper, we combine a structure retriever and a domain-adapted ColBERT retr...
-
Chapter and Conference Paper
Pre-processing Matters! Improved Wikipedia Corpora for Open-Domain Question Answering
One of the contributions of the landmark Dense Passage Retriever (DPR) work is the curation of a corpus of passages generated from Wikipedia articles that have been segmented into non-overlap** passages of 1...
-
Chapter and Conference Paper
Squeezing Water from a Stone: A Bag of Tricks for Further Improving Cross-Encoder Effectiveness for Reranking
While much recent work has demonstrated that hard negative mining can be used to train better bi-encoder models, few have considered it in the context of cross-encoders, which are key ingredients in modern re...
-
Chapter and Conference Paper
Another Look at DPR: Reproduction of Training and Replication of Retrieval
Text retrieval using learned dense representations has recently emerged as a promising alternative to “traditional” text retrieval using sparse bag-of-words representations. One foundational work that has garn...
-
Chapter and Conference Paper
Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback: A Reproducibility Study
Pseudo-Relevance Feedback (PRF) utilises the relevance signals from the top-k passages from the first round of retrieval to perform a second round of retrieval aiming to improve search effectiveness. A recent res...
-
Chapter and Conference Paper
Comparing Score Aggregation Approaches for Document Retrieval with Pretrained Transformers
While BERT has been shown to be effective for passage retrieval, its maximum input length limitation poses a challenge when applying the model to document retrieval. In this work, we reproduce three passage sc...
-
Chapter and Conference Paper
From MAXSCORE to Block-Max Wand: The Story of How Lucene Significantly Improved Query Evaluation Performance
The latest major release of Lucene (version 8) in March 2019 incorporates block-max indexes and exploits the block-max variant of Wand for query evaluation, which are innovations that originated from academia. Th...
-
Chapter and Conference Paper
Which BM25 Do You Mean? A Large-Scale Reproducibility Study of Scoring Variants
When researchers speak of BM25, it is not entirely clear which variant they mean, since many tweaks to Robertson et al.’s original formulation have been proposed. When practitioners speak of BM25, they most li...
-
Chapter and Conference Paper
Reproducibility is a Process, Not an Achievement: The Replicability of IR Reproducibility Experiments
This paper espouses a view of reproducibility in the computational sciences as a process and not just a point-in-time “achievement”. As a concrete case study, we revisit the Open-Source IR Reproducibility Challen...
-
Chapter and Conference Paper
Simple Techniques for Cross-Collection Relevance Feedback
We tackle the problem of transferring relevance judgments across document collections for specific information needs by reproducing and generalizing the work of Grossman and Cormack from the TREC 2017 Common C...
-
Chapter and Conference Paper
Reproducing and Generalizing Semantic Term Matching in Axiomatic Information Retrieval
In the framework of axiomatic information retrieval, the semantic term matching technique proposed by Fang and Zhai in SIGIR 2006 has been shown to be effective in addressing the vocabulary mismatch problem, w...
-
Chapter and Conference Paper
Compressing and Decoding Term Statistics Time Series
There is growing recognition that temporality plays an important role in information retrieval, particularly for timestamped document collections such as tweets. This paper examines the problem of compressing ...
-
Chapter and Conference Paper
Toward Reproducible Baselines: The Open-Source IR Reproducibility Challenge
The Open-Source IR Reproducibility Challenge brought together developers of open-source search engines to provide reproducible baselines of their systems in a common environment on Amazon EC2. The product is a...
-
Chapter and Conference Paper
Reproducible Experiments on Lexical and Temporal Feedback for Tweet Search
“Evaluation as a service” (EaaS) is a new methodology for community-wide evaluations where an API provides the only point of access to the collection for completing the evaluation task. Two important advantage...
-
Chapter and Conference Paper
The Impact of Future Term Statistics in Real-Time Tweet Search
In the real-time tweet search task operationalized in the TREC Microblog evaluations, a topic consists of a query Q and a time t, modeling the task where the user wishes to see the most recent but relevant tweets...
-
Chapter and Conference Paper
Column Stores as an IR Prototy** Tool
We make the suggestion that instead of implementing custom index structures and query evaluation algorithms, IR researchers should simply store document representations in a column-oriented relational database...
-
Chapter and Conference Paper
10 Bit 1.5b/Stage Pipeline ADC Design for Video Application
This paper proposes a design of a 10-bit fully differential pipeline analog-to-digital converter (ADC). The main component of this ADC is the sample and hold (S/H) circuit and eight stages of 1.5 bit sub-ADC a...
-
Chapter and Conference Paper
Training Efficient Tree-Based Models for Document Ranking
Gradient-boosted regression trees (GBRTs) have proven to be an effective solution to the learning-to-rank problem. This work proposes and evaluates techniques for training GBRTs that have efficient runtime charac...