84 results for "Lin, Jimmy"
Showing 1–20 · 0.40 seconds · RSS
-
Journal Article Full text
PageRank without hyperlinks: Reranking with PubMed related article networks for biomedical text retrieval
Abstract Background Graph analysis algorithms such as PageRank and HITS have been successful in Web environments because they are able to extract important inter-document relationships from manually-created hyperlinks. We consider the application of these techniques to biomedical text retrieval. In…
Also available at: PubMed Central
-
Journal Article Full text
Is searching full text more effective than searching abstracts?
Abstract Background With the growing availability of full-text articles online, scientists and other consumers of the life sciences literature now have the ability to go beyond searching bibliographic records (title, abstract, metadata) to directly access full-text content. Motivated by this…
Also available at: PubMed Central
-
Preprint Full text
Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search Agents
Deep research agents rely on iterative retrieval and reasoning to answer complex queries, but scaling test-time computation raises significant efficiency concerns. We study how to allocate reasoning budget in deep search pipelines, focusing on the role of listwise reranking. Using the…
-
Preprint Full text
A Systematic Study of Pseudo-Relevance Feedback with LLMs
Pseudo-relevance feedback (PRF) methods built on large language models (LLMs) can be organized along two key design dimensions: the feedback source, which is where the feedback text is derived from and the feedback model, which is how the given feedback text is used to refine the query…
-
Journal Article Full text
Whole-genome Trees Based on the Occurrence of Folds and Orthologs: Implications for Comparing Genomes on Different Levels
We built whole-genome trees based on the presence or absence of particular molecular features, either orthologs or folds, in the genomes of a number of recently sequenced microorganisms. To put these genomic trees into perspective, we compared them to the traditional ribosomal phylogeny and also to…
-
Journal Article Full text
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 Challenge from 2015 and attempt to replicate those experiments: four years later, are those…
-
Journal Article Full text
PubMed related articles: a probabilistic topic-based model for content similarity
Abstract Background We present a probabilistic topic-based model for content similarity called pmra that underlies the related article search feature in PubMed. Whether or not a document is about a particular topic is computed from term frequencies, modeled as Poisson distributions. Unlike previous…
Also available at: PubMed Central
-
Journal Article Full text
Modeling Actions of PubMed Users with N-Gram Language Models
Transaction logs from online search engines are valuable for two reasons: First, they provide insight into human information-seeking behavior. Second, log data can be used to train user models, which can then be applied to improve retrieval systems. This article presents a study of logs from…
-
Journal Article Full text
Semantic Clustering of Answers to Clinical Questions
Access to clinical evidence is a critical component of the practice of evidence-based medicine. Advanced retrieval systems can supplement precompiled secondary sources to assist physicians in making sound clinical decisions. This study explores one particular issue related to the design of such…
-
Journal Article Full text
“Bag of Words” is not enough for Strength of Evidence Classification
Incorporation of evidence from clinical research requires critical appraisal of its quality. Information retrieval systems can facilitate physicians’ judgments by automatically labeling retrieved citations with their strength of evidence categories. Preliminary results of such a text classification…
-
Preprint Full text
Illusions of Relevance: Arbitrary Content Injection Attacks Deceive Retrievers, Rerankers, and LLM Judges
This work considers a black-box threat model in which adversaries attempt to propagate arbitrary non-relevant content in search. We show that retrievers, rerankers, and LLM relevance judges are all highly vulnerable to attacks that enable arbitrary content to be promoted to the top of search…
-
Preprint Full text
NanoKnow: How to Know What Your Language Model Knows
How do large language models (LLMs) know what they know? Answering this question has been difficult because pre-training data is often a "black box" - unknown or inaccessible. The recent release of nanochat - a family of small LLMs with fully open pre-training data - addresses this as it provides a…
-
Journal Article Full text
Evaluation of PICO as a Knowledge Representation for Clinical Questions
The paradigm of evidence-based medicine (EBM) recommends that physicians formulate clinical questions in terms of the problem/population, intervention, comparison, and outcome. Together, these elements comprise a PICO frame. Although this framework was developed to facilitate the formulation of…
-
Journal Article Full text
Characterization of Binding Sites of Eukaryotic Transcription Factors
To explore the nature of eukaryotic transcription factor (TF) binding sites and determine how they differ from surrounding DNA sequences, we examined four features associated with DNA binding sites: G+C content, pattern complexity, palindromic structure, and Markov sequence ordering. Our analysis…
-
Journal Article Full text
Understanding protein phosphorylation on a systems level
Protein kinase phosphorylation is central to the regulation and control of protein and cellular function. Over the past decade, the development of many high-throughput approaches has revolutionized the understanding of protein phosphorylation and allowed rapid and unbiased surveys of…
-
Journal Article Full text
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. This paper shares the story of how this came to be, which provides an interesting case…
-
Journal Article Full text
Ovarian Clear Cell Carcinoma: An Endometriosis-Associated Cancer with Therapeutic Challenges
Ovarian clear cell carcinoma (OCCC) is a histological subtype of epithelial ovarian cancer with distinct pathological features, molecular profiles, and biological functions. OCCC has high incidence rates in East Asia compared to the Western hemisphere and Europe and is associated with…