Search Results - "Soldaini, Luca"

Learning to reformulate long queries for clinical decision support by Soldaini, Luca, Yates, Andrew, Goharian, Nazli

“…The large volume of biomedical literature poses a serious problem for medical professionals, who are often struggling to keep current with it. At the same…”
Get full text

Enhancing web search in the medical domain via query clarification by Soldaini, Luca, Yates, Andrew, Yom-Tov, Elad, Frieder, Ophir, Goharian, Nazli

“…The majority of Internet users search for medical information online; however, many do not have an adequate medical vocabulary. Users might have difficulties…”
Get full text

Overcoming low-utility facets for complex answer retrieval by MacAvaney, Sean, Yates, Andrew, Cohan, Arman, Soldaini, Luca, Hui, Kai, Goharian, Nazli, Frieder, Ophir

“…Many questions cannot be answered simply; their answers must include numerous nuanced details and context. Complex Answer Retrieval (CAR) is the retrieval of…”
Get full text

The Knowledge and Language Gap in Medical Information Seeking by Soldaini, Luca

“…Interest in medical information retrieval has risen significantly in the last few years. The Internet has become a primary source for consumers looking for…”
Get full text

One-Shot Labeling for Automatic Relevance Estimation by MacAvaney, Sean, Soldaini, Luca

“…Dealing with unjudged documents ("holes") in relevance assessments is a perennial problem when evaluating search systems with offline experiments. Holes can…”
Get full text

The Cascade Transformer: an Application for Efficient Answer Sentence Selection by Soldaini, Luca, Moschitti, Alessandro

“…Large transformer-based language models have been shown to be very effective in many classification tasks. However, their computational complexity prevents…”
Get full text

RouterRetriever: Exploring the Benefits of Routing over Multiple Expert Embedding Models by Lee, Hyunji, Soldaini, Luca, Cohan, Arman, Seo, Minjoon, Lo, Kyle

“…Information retrieval methods often rely on a single embedding model trained on large, general-domain datasets like MSMARCO. While this approach can produce a…”
Get full text

Back to Basics: A Simple Recipe for Improving Out-of-Domain Retrieval in Dense Encoders by Lee, Hyunji, Soldaini, Luca, Cohan, Arman, Seo, Minjoon, Lo, Kyle

“…Prevailing research practice today often relies on training dense retrievers on existing large datasets such as MSMARCO and then experimenting with ways to…”
Get full text

A Question Answering Framework for Decontextualizing User-facing Snippets from Scientific Documents by Newman, Benjamin, Soldaini, Luca, Fok, Raymond, Cohan, Arman, Lo, Kyle

“…Many real-world applications (e.g., note taking, search) require extracting a sentence or paragraph from a document and showing that snippet to a human outside…”
Get full text

Mathfish: Evaluating Language Model Math Reasoning via Grounding in Educational Curricula by Lucy, Li, August, Tal, Wang, Rose E, Soldaini, Luca, Allison, Courtney, Lo, Kyle

“…To ensure that math curriculum is grade-appropriate and aligns with critical skills or concepts in accordance with educational standards, pedagogical experts…”
Get full text

Self-Directed Synthetic Dialogues and Revisions Technical Report by Lambert, Nathan, Schoelkopf, Hailey, Gokaslan, Aaron, Soldaini, Luca, Pyatkin, Valentina, Castricato, Louis

“…Synthetic data has become an important tool in the fine-tuning of language models to follow instructions and solve complex problems. Nevertheless, the majority…”
Get full text

Modeling Context in Answer Sentence Selection Systems on a Latency Budget by Han, Rujun, Soldaini, Luca, Moschitti, Alessandro

“…Answer Sentence Selection (AS2) is an efficient approach for the design of open-domain Question Answering (QA) systems. In order to achieve low latency,…”
Get full text

Overview of the TREC 2023 NeuCLIR Track by Lawrie, Dawn, MacAvaney, Sean, Mayfield, James, McNamee, Paul, Oard, Douglas W, Soldaini, Luca, Yang, Eugene

“…The principal goal of the TREC Neural Cross-Language Information Retrieval (NeuCLIR) track is to study the impact of neural approaches to cross-language…”
Get full text

KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions by Xu, Fangyuan, Lo, Kyle, Soldaini, Luca, Kuehl, Bailey, Choi, Eunsol, Wadden, David

“…Large language models (LLMs) adapted to follow user instructions are now widely deployed as conversational agents. In this work, we examine one increasingly…”
Get full text

Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection by Di Liello, Luca, Garg, Siddhant, Soldaini, Luca, Moschitti, Alessandro

“…An important task for designing QA systems is answer sentence selection (AS2): selecting the sentence containing (or constituting) the answer to a question…”
Get full text

Paragraph-based Transformer Pre-training for Multi-Sentence Inference by Di Liello, Luca, Garg, Siddhant, Soldaini, Luca, Moschitti, Alessandro

“…Inference tasks such as answer sentence selection (AS2) or fact verification are typically solved by fine-tuning transformer-based models as individual…”
Get full text

AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters by Lucy, Li, Gururangan, Suchin, Soldaini, Luca, Strubell, Emma, Bamman, David, Klein, Lauren F, Dodge, Jesse

“…Large language models' (LLMs) abilities are drawn from their pretraining data, and model development begins with data curation. However, decisions around what…”
Get full text

Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems by Matsubara, Yoshitomo, Soldaini, Luca, Lind, Eric, Moschitti, Alessandro

“…Findings of the Association for Computational Linguistics: EMNLP 2022 Large transformer models can highly improve Answer Sentence Selection (AS2) tasks, but…”
Get full text

The Surveillance AI Pipeline by Kalluri, Pratyusha Ria, Agnew, William, Cheng, Myra, Owens, Kentrell, Soldaini, Luca, Birhane, Abeba

“…A rapidly growing number of voices argue that AI research, and computer vision in particular, is powering mass surveillance. Yet the direct path from computer…”
Get full text

When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasets by Weller, Orion, Lo, Kyle, Wadden, David, Lawrie, Dawn, Van Durme, Benjamin, Cohan, Arman, Soldaini, Luca

“…Using large language models (LMs) for query or document expansion can improve generalization in information retrieval. However, it is unknown whether these…”
Get full text