While research on scientific claim verification has led to the development of powerful systems that appear to approach human performance, these approaches have yet to be tested in a realistic setting against large corpora of scientific literature. Moving to this open-domain evaluation setting, however, poses unique challenges; in particular, it is infeasible to exhaustively annotate all evidence documents. In this work, we present SciFact-Open, a new test collection designed to evaluate the performance of scientific claim verification systems on a corpus of 500K research abstracts. Drawing upon pooling techniques from information retrieval, we collect evidence for scientific claims by pooling and annotating the top predictions of four state-of-the-art scientific claim verification models. We find that systems developed on smaller corpora struggle to generalize to SciFact-Open, exhibiting performance drops of at least 15 F1. In addition, analysis of the evidence in SciFact-Open reveals interesting phenomena likely to appear when claim verification systems are deployed in practice, e.g., cases where the evidence supports only a special case of the claim. Our dataset is available at https://github.com/dwadden/scifact-open.
Automated scientific fact checking is difficult due to the complexity of scientific language and a lack of significant amounts of training data, as annotation requires domain expertise. To address this challenge, we propose scientific claim generation, the task of generating one or more atomic and verifiable claims from scientific sentences, and demonstrate its usefulness in zero-shot fact checking for biomedical claims. We propose CLAIMGEN-BART, a new supervised method for generating claims supported by the literature, as well as KBIN, a novel method for generating claim negations. Additionally, we adapt an existing unsupervised entity-centric method of claim generation to biomedical claims, which we call CLAIMGEN-ENTITY. Experiments on zero-shot fact checking demonstrate that both CLAIMGEN-ENTITY and CLAIMGEN-BART, coupled with KBIN, achieve up to 90% performance of fully supervised models trained on manually annotated claims and evidence. A rigorous evaluation study demonstrates significant improvement in generated claim and negation quality over existing baselines
When seeking information not covered in patient-friendly documents, like medical pamphlets, healthcare consumers may turn to the research literature. Reading medical papers, however, can be a challenging experience. To improve access to medical papers, we introduce a novel interactive interface-Paper Plain-with four features powered by natural language processing: definitions of unfamiliar terms, in-situ plain language section summaries, a collection of key questions that guide readers to answering passages, and plain language summaries of the answering passages. We evaluate Paper Plain, finding that participants who use Paper Plain have an easier time reading and understanding research papers without a loss in paper comprehension compared to those who use a typical PDF reader. Altogether, the study results suggest that guiding readers to relevant passages and providing plain language summaries, or "gists," alongside the original paper content can make reading medical papers easier and give readers more confidence to approach these papers.
We introduce the LongChecker system for scientific claim verification. Given a scientific claim and an evidence-containing research abstract, LongChecker predicts a veracity label and identifies supporting rationales in a multitask fashion based on a shared encoding of the claim and abstract. We perform experiments on the SciFact dataset, and find that LongChecker achieves state-of-the-art performance. We conduct analysis to understand the source of this improvement, and find that identifying the relationship between a claim and a rationale reporting a scientific finding often requires understanding the context in which the rationale appears. By making labeling decisions based on all available context, LongChecker achieves better performance on cases requiring this type of understanding. In addition, we show that LongChecker is able to leverage weakly-supervised in-domain data to facilitate few-shot domain adaptation for scientific claim verification.
Predictive models for medical outcomes hold great promise for enhancing clinical decision-making. These models are trained on rich patient data such as clinical notes, aggregating many patient signals into an outcome prediction. However, AI-based clinical models have typically been developed in isolation from the prominent paradigm of Evidence Based Medicine (EBM), in which medical decisions are based on explicit evidence from existing literature. In this work, we introduce techniques to help bridge this gap between EBM and AI-based clinical models, and show that these methods can improve predictive accuracy. We propose a novel system that automatically retrieves patient-specific literature based on intensive care (ICU) patient information, aggregates relevant papers and fuses them with internal admission notes to form outcome predictions. Our model is able to substantially boost predictive accuracy on three challenging tasks in comparison to strong recent baselines; for in-hospital mortality, we are able to boost top-10% precision by a large margin of over 25%.
Classifying the core textual components of a scientific paper-title, author, body text, etc.-is a critical first step in automated scientific document understanding. Previous work has shown how using elementary layout information, i.e., each token's 2D position on the page, leads to more accurate classification. We introduce new methods for incorporating VIsual LAyout (VILA) structures, e.g., the grouping of page texts into text lines or text blocks, into language models to further improve performance. We show that the I-VILA approach, which simply adds special tokens denoting the boundaries of layout structures into model inputs, can lead to 1.9% Macro F1 improvements for token classification. Moreover, we design a hierarchical model, H-VILA, that encodes the text based on layout structures and record an up-to 47% inference time reduction with less than 1.5% Macro F1 loss for the text classification models. Experiments are conducted on a newly curated evaluation suite, S2-VLUE, with a novel metric measuring classification uniformity within visual groups and a new dataset of gold annotations covering papers from 19 scientific disciplines. Pre-trained weights, benchmark datasets, and source code will be available at https://github.com/allenai/VILA.
We present an overview of the TREC-COVID Challenge, an information retrieval (IR) shared task to evaluate search on scientific literature related to COVID-19. The goals of TREC-COVID include the construction of a pandemic search test collection and the evaluation of IR methods for COVID-19. The challenge was conducted over five rounds from April to July, 2020, with participation from 92 unique teams and 556 individual submissions. A total of 50 topics (sets of related queries) were used in the evaluation, starting at 30 topics for Round 1 and adding 5 new topics per round to target emerging topics at that state of the still-emerging pandemic. This paper provides a comprehensive overview of the structure and results of TREC-COVID. Specifically, the paper provides details on the background, task structure, topic structure, corpus, participation, pooling, assessment, judgments, results, top-performing systems, lessons learned, and benchmark datasets.
To assess the effectiveness of any medical intervention, researchers must conduct a time-intensive and highly manual literature review. NLP systems can help to automate or assist in parts of this expensive process. In support of this goal, we release MS^2 (Multi-Document Summarization of Medical Studies), a dataset of over 470k documents and 20k summaries derived from the scientific literature. This dataset facilitates the development of systems that can assess and aggregate contradictory evidence across multiple studies, and is the first large-scale, publicly available multi-document summarization dataset in the biomedical domain. We experiment with a summarization system based on BART, with promising early results. We formulate our summarization inputs and targets in both free text and structured forms and modify a recently proposed metric to assess the quality of our system's generated summaries. Data and models are available at https://github.com/allenai/ms2
Understanding the relationship between figures and text is key to scientific document understanding. Medical figures in particular are quite complex, often consisting of several subfigures (75% of figures in our dataset), with detailed text describing their content. Previous work studying figures in scientific papers focused on classifying figure content rather than understanding how images relate to the text. To address challenges in figure retrieval and figure-to-text alignment, we introduce MedICaT, a dataset of medical images in context. MedICaT consists of 217K images from 131K open access biomedical papers, and includes captions, inline references for 74% of figures, and manually annotated subfigures and subcaptions for a subset of figures. Using MedICaT, we introduce the task of subfigure to subcaption alignment in compound figures and demonstrate the utility of inline references in image-text matching. Our data and code can be accessed at https://github.com/allenai/medicat.