Difference between revisions of "BioNLP Workshop"
| Line 50: | Line 50: | ||
===Shared Tasks=== | ===Shared Tasks=== | ||
| − | <b>Clinical Text generation</b> | + | <b>1. Clinical Text generation</b> |
| − | Radiology Report Generation An important medical application of natural language generation (NLG) is to build assistive systems that take X-ray images of a patient and generate a textual report describing clinical observations in the images. This is a clinically important task, offering the potential to reduce radiologists’ repetitive work and generally improve clinical communication. This shared task is using the first large-scale collection of RRG datasets based on MIMIC-CXR, CheXpert, PadChest and CANDID-PTX. Participants will need to generate findings and impression from chest x-rays and will be evaluated on a common leaderboard with recent proposed metrics such as F1-Radgraph and RadCliQ. This shared task aims to benchmark recent progress using common data splits and evaluation implementations. | + | * Task 1: Radiology Report Generation <br/> |
| + | An important medical application of natural language generation (NLG) is to build assistive systems that take X-ray images of a patient and generate a textual report describing clinical observations in the images. This is a clinically important task, offering the potential to reduce radiologists’ repetitive work and generally improve clinical communication. This shared task is using the first large-scale collection of RRG datasets based on MIMIC-CXR, CheXpert, PadChest and CANDID-PTX. Participants will need to generate findings and impression from chest x-rays and will be evaluated on a common leaderboard with recent proposed metrics such as F1-Radgraph and RadCliQ. This shared task aims to benchmark recent progress using common data splits and evaluation implementations. | ||
| + | See details at https://stanford-aimi.github.io/RRG24/ | ||
| − | The <b>BioLaySumm</b> shared task surrounds the abstractive summarization of biomedical articles, with an emphasis on catering to non-expert audiences through the generation of summaries that are more readable, containing more background information and less technical terminology (i.e., a “lay summary”). | + | * Task 2: Discharge Me! |
| + | |||
| + | The primary objective of this task is to reduce the time and effort clinicians spend on writing detailed notes in the electronic health record (EHR). Clinicians play a crucial role in documenting patient progress in discharge summaries, but the creation of concise yet comprehensive hospital course summaries and discharge instructions often demands a significant amount of time, especially since these sections cannot be readily copied from prior notes. This can lead to clinician burnout and operational inefficiencies within hospital workflows. By streamlining the generation of these sections, we can not only enhance the accuracy and completeness of clinical documentation but also significantly reduce the time clinicians spend on administrative tasks, ultimately improving patient care quality. | ||
| + | |||
| + | See details at https://stanford-aimi.github.io/discharge-me/ | ||
| + | |||
| + | <b>2. BioLaySumm</b> | ||
| + | |||
| + | This shared task surrounds the abstractive summarization of biomedical articles, with an emphasis on catering to non-expert audiences through the generation of summaries that are more readable, containing more background information and less technical terminology (i.e., a “lay summary”). | ||
This is the 2nd iteration of BioLaySumm, following the success of the 1st edition of the task at BioNLP 2023 which attracted 56 submissions across 20 different teams. In this edition, we aim to build on last year’s task by introducing a new test set, updating our evaluation protocol, and encouraging participants to explore novel approaches that will help to further advance the state-of-the-art for Lay Summarization. | This is the 2nd iteration of BioLaySumm, following the success of the 1st edition of the task at BioNLP 2023 which attracted 56 submissions across 20 different teams. In this edition, we aim to build on last year’s task by introducing a new test set, updating our evaluation protocol, and encouraging participants to explore novel approaches that will help to further advance the state-of-the-art for Lay Summarization. | ||
| + | See details at https://biolaysumm.org/ | ||
===Organizers=== | ===Organizers=== | ||
Revision as of 19:53, 8 February 2024
BIONLP 2024 and Shared Tasks @ ACL 2024
The 23rd BioNLP workshop associated with the ACL SIGBIOMED special interest group is co-located with ACL 2024
IMPORTANT DATES
TENTATIVE
- Paper submission deadline: May 17 (Friday), 2024
- Notification of acceptance: June 17 (Monday), 2024
- Camera-ready paper due: July 1 (Monday), 2024
- Workshop: August 16, 2024, Location: LOTUS SUITE 12
SUBMISSION INSTRUCTIONS
Two types of submissions are invited: full (long) papers and short papers.
Submission site for the workshop https://softconf.com/acl2024/BioNLP2024
INVITED TALK
Titipat Achakulvisut. Biomedical and Data (Bio-Data) lab at Mahidol University
WORKSHOP OVERVIEW AND SCOPE
The BioNLP workshop, associated with the ACL SIGBIOMED special interest group, is an established primary venue for presenting research in language processing and language understanding for the biological and medical domains. The workshop has been running every year since 2002 and continues getting stronger. Many other emerging biomedical and clinical language processing workshops can afford to be more specialized because BioNLP truly encompasses the breadth of the domain and brings together researchers in bio- and clinical NLP from all over the world.
BioNLP 2024 will be particularly interested in transparency of the generative approaches and factuality of the generated text. Language processing that supports DEIA (Diversity, Equity, Inclusion and Accessibility) is still of utmost importance. The work on detection and mitigation of bias and misinformation continues to be of interest. Research in languages other than English, particularly, under-represented languages, and health disparities are always of interest to BioNLP. Other active areas of research include, but are not limited to:
- Tangible results of biomedical language processing applications;
- Entity identification and normalization (linking) for a broad range of semantic categories;
- Extraction of complex relations and events;
- Discourse analysis; Anaphora \& coreference resolution;
- Text mining \& Literature based discovery;
- Summarization;
- Text simplification;
- Question Answering;
- Resources and strategies for system testing and evaluation;
- Infrastructures and pre-trained language models for biomedical NLP;
- Processing and annotation platforms;
- Synthetic data generation \& data augmentation;
- Translating NLP research into practice;
- Getting reproducible results.
1. Clinical Text generation
- Task 1: Radiology Report Generation
An important medical application of natural language generation (NLG) is to build assistive systems that take X-ray images of a patient and generate a textual report describing clinical observations in the images. This is a clinically important task, offering the potential to reduce radiologists’ repetitive work and generally improve clinical communication. This shared task is using the first large-scale collection of RRG datasets based on MIMIC-CXR, CheXpert, PadChest and CANDID-PTX. Participants will need to generate findings and impression from chest x-rays and will be evaluated on a common leaderboard with recent proposed metrics such as F1-Radgraph and RadCliQ. This shared task aims to benchmark recent progress using common data splits and evaluation implementations.
See details at https://stanford-aimi.github.io/RRG24/
- Task 2: Discharge Me!
The primary objective of this task is to reduce the time and effort clinicians spend on writing detailed notes in the electronic health record (EHR). Clinicians play a crucial role in documenting patient progress in discharge summaries, but the creation of concise yet comprehensive hospital course summaries and discharge instructions often demands a significant amount of time, especially since these sections cannot be readily copied from prior notes. This can lead to clinician burnout and operational inefficiencies within hospital workflows. By streamlining the generation of these sections, we can not only enhance the accuracy and completeness of clinical documentation but also significantly reduce the time clinicians spend on administrative tasks, ultimately improving patient care quality.
See details at https://stanford-aimi.github.io/discharge-me/
2. BioLaySumm
This shared task surrounds the abstractive summarization of biomedical articles, with an emphasis on catering to non-expert audiences through the generation of summaries that are more readable, containing more background information and less technical terminology (i.e., a “lay summary”).
This is the 2nd iteration of BioLaySumm, following the success of the 1st edition of the task at BioNLP 2023 which attracted 56 submissions across 20 different teams. In this edition, we aim to build on last year’s task by introducing a new test set, updating our evaluation protocol, and encouraging participants to explore novel approaches that will help to further advance the state-of-the-art for Lay Summarization.
See details at https://biolaysumm.org/
Organizers
* Dina Demner-Fushman, US National Library of Medicine * Sophia Ananiadou, National Centre for Text Mining and University of Manchester, UK * Makoto Miwa, Toyota Technological Institute, Japan * Kirk Roberts, UTHealth, Houston, Texas * Jun-ichi Tsujii, National Institute of Advanced Industrial Science and Technology, Japan