MSˆ2: Multi-Document Summarization of Medical Studies

@inproceedings{DeYoung2021MS2MS,
  title={MSˆ2: Multi-Document Summarization of Medical Studies},
  author={Jay DeYoung and Iz Beltagy and Madeleine van Zuylen and Bailey Kuehl and Lucy Lu Wang},
  booktitle={EMNLP},
  year={2021}
}
To assess the effectiveness of any medical intervention, researchers must conduct a time-intensive and manual literature review. NLP systems can help to automate or assist in parts of this expensive process. In support of this goal, we release MSˆ2 (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… 
Predicting Intervention Approval in Clinical Trials through Multi-Document Summarization
TLDR
This study proposes a new method to predict the effectiveness of an intervention in a clinical trial which relies on generating an informative summary from multiple documents available in the literature about the intervention under study.
Discriminative Marginalized Probabilistic Neural Method for Multi-Document Summarization of Medical Literature
TLDR
A novel discriminative marginalized probabilistic method (DAMEN) trained to discriminate critical information from a cluster of topic-related medical documents and generate a multi-document summary via token probability marginalization is proposed.
The patient is more dead than alive: exploring the current state of the multi-document summarisation of the biomedical literature
TLDR
A new approach to human evaluation is proposed and several challenges that must be overcome are identified to develop effective biomedical MDS systems.
Automated tabulation of clinical trial results: A joint entity and relation extraction approach with transformer-based language representations
TLDR
This paper investigates automating evidence table generation by decomposing the problem across two language processing tasks: named entity recognition, which identifies key entities within text, such as drug names, and relation extraction, which maps their relationships for separating them into ordered tuples.
Generating Scientific Claims for Zero-Shot Scientific Fact Checking
TLDR
This work proposes scientific claim generation, the task of generating one or more atomic and verifiable claims from scientific sentences, and demonstrates its usefulness in zero-shot fact checking for biomedical claims, and proposes CLAIMGEN-BART, a new supervised method for generating claims supported by the literature, as well as KBIN, a novel methods for generating claim negations.
Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text
TLDR
This paper surveys the issues with human and automatic model evaluations and with commonly used datasets in NLG that have been pointed out over the past 20 years and lays out a long-term vision for NLG evaluation and proposes concrete steps to improve their evaluation processes.
Semi-Supervised Exaggeration Detection of Health Science Press Releases
TLDR
MT-PET, a multi-task version of Pattern Exploiting Training (PET), which leverages knowledge from complementary cloze-style QA tasks to improve few-shot learning and it is demonstrated that MT-PET outperforms PET and supervised learning both when data is limited, as well as when there is an abundance of data for the main task.
Literature-Augmented Clinical Outcome Prediction
TLDR
The BEEP approach boosts predictive performance on three important clinical tasks in compari-son to strong recent LM baselines, increasing F1 by up to 5 points and precision@Top-K by a large margin of over 25%.
Cross-Domain Multi-Task Learning for Sequential Sentence Classification in Research Papers
TLDR
A novel uniform deep learning architecture and multi-task learning for cross-domain sequential sentence classification in scientific texts and an approach to semi-automatically identify semantically related classes from different annotation schemes is suggested.
...
1
2
...

References

SHOWING 1-10 OF 97 REFERENCES
Understanding Clinical Trial Reports: Extracting Medical Entities and Their Relations
TLDR
This work considers the end-to-end task of extracting treatments and outcomes from full-text articles describing clinical trials and inferring the reported results for the former with respect to the latter, and proposes a new method motivated by how trial results are typically presented that outperforms these purely data-driven baselines.
PICO Element Detection in Medical Text via Long Short-Term Memory Neural Networks
TLDR
A Long Short-Term Memory (LSTM) neural network based model is presented to automatically detect PICO elements and achieves state-of-the-art results on PICO element classification compared to several strong baseline models.
Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model
TLDR
This work introduces Multi-News, the first large-scale MDS news dataset, and proposes an end-to-end model which incorporates a traditional extractive summarization model with a standard SDS model and achieves competitive results on MDS datasets.
Overview of the MEDIQA 2019 Shared Task on Textual Inference, Question Entailment and Question Answering
TLDR
The shared task is motivated by a need to develop relevant methods, techniques and gold standards for inference and entailment in the medical domain, and their application to improve domain specific information retrieval and question answering systems.
A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal
TLDR
This work presents a new dataset for MDS that is large both in the total number of document clusters and in the size of individual clusters, and provides a quantitative analysis of the dataset and empirical results for several state-of-the-art MDS techniques.
Clinical Information Retrieval using Document and PICO Structure
TLDR
A method that extends the language modeling approach to incorporate both document structure and PICO query formulation and an analysis of the distribution of PICO elements in medical abstracts that motivates the use of a location-based weighting strategy are presented.
Leveraging Graph to Improve Abstractive Multi-Document Summarization
TLDR
A neural abstractive multi-document summarization (MDS) model which can leverage well-known graph representations of documents, to more effectively process multiple input documents and produce abstractive summaries is developed.
Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models
TLDR
The method (Relevance Sensitive Attention for QFS) is compared to extractive baselines and with various ways to combine abstractive models on the DUC QFS datasets and with solid improvements on ROUGE performance.
A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature
TLDR
A corpus of 5,000 richly annotated abstracts of medical articles describing clinical randomized controlled trials is presented and a set of challenging NLP tasks that would aid searching of the medical literature and the practice of evidence-based medicine are outlined.
Assessing the state of the art in biomedical relation extraction: overview of the BioCreative V chemical-disease relation (CDR) task
TLDR
This task was found to be successful in engaging the text-mining research community, producing a large annotated corpus and improving the results of automatic disease recognition and CDR extraction.
...
1
2
3
4
5
...