Canada

In this paper, we elaborate on our approach for the shared task 1A issued by BioNLP Workshop 2023 titled “Problem List Summarization.” With an increase in the digitization of health records, a need arises for quick and precise summarization of large amounts of records. With the help of summarization, medical professionals can sieve through multiple records in a short span of time without overlooking any crucial point. We use abstractive text summarization for this task and experiment with multiple state-of-the-art models like Pegasus, BART, and T5, along with various pre-processing and data augmentation techniques to generate summaries from patients&#39; progress notes. For this task, the metric used was the ROUGE-L score. From our experiments, we conclude that Pegasus is the best-performing model on the dataset, achieving a ROUGE-L F1 score of 0.2744 on the test dataset (3rd rank on the leaderboard)

ACL 2023

Team Converge at ProbSum 2023: Abstractive Text Summarization of Patient Progress Notes

biomedical text summarization

abstractive text summarization

text summarization

summarization

transformers

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
 The conference will be held in Toronto, Canada, July 9-14, 2023. 
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience. 
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

In this paper, we elaborate on our approach for the shared task 1A issued by BioNLP Workshop 2023 titled “Problem List Summarization.” With an increase in the digitization of health records, a need arises for quick and precise summarization of large amounts of records. With the help of summarization, medical professionals can sieve through multiple records in a short span of time without overlooking any crucial point. We use abstractive text summarization for this task and experiment with multiple state-of-the-art models like Pegasus, BART, and T5, along with various pre-processing and data augmentation techniques to generate summaries from patients' progress notes. For this task, the metric used was the ROUGE-L score. From our experiments, we conclude that Pegasus is the best-performing model on the dataset, achieving a ROUGE-L F1 score of 0.2744 on the test dataset (3rd rank on the leaderboard)

workshop paper

HeGeL: A Novel Dataset for Geo-Location from Hebrew Text

In this paper, we present the interim results of a transformer-based annotation pipeline for Ancient and Medieval Greek. As the texts in the Database of Byzantine Book Epigrams have not been normalised, they pose more challenges for manual and automatic annotation than Ancient Greek, normalised texts do. As a result, the existing annotation tools perform poorly. We compiled three data sets for the development of an automatic annotation tool and carried out an inter-annotator agreement study, with a promising agreement score. The experimental results show that our part-of-speech tagger yields accuracy scores that are almost 50 percentage points higher than the widely used rule-based system Morpheus. In addition, error analysis revealed problems related to phenomena also occurring in current social media language.

Medieval Social Media: Manual and Automatic Annotation of Byzantine Greek Marginal Writing

In this work, we consider the challenge of summarizing patients' medical progress notes in a limited data setting. For the Problem List Summarization (shared task 1A) at the BioNLP Workshop 2023, we demonstrate that Clinical-T5 fine-tuned to 765 medical clinic notes outperforms other extractive, abstractive and zero-shot baselines, yielding reasonable baseline systems for medical note summarization. Further, we introduce Hierarchical Ensemble of Summarization Models (HESM), consisting of token-level ensembles of diverse fine-tuned Clinical-T5 models, followed by Minimum Bayes Risk (MBR) decoding. Our HESM approach lead to a considerable summarization performance boost, and when evaluated on held-out challenge data achieved a ROUGE-L of 32.77, which was the best-performing system at the top of the shared task leaderboard.

CUED at ProbSum 2023: Hierarchical Ensemble of Summarization Models

This paper presents our system at the Radiology Report Summarization Shared Task-1B of the 22nd BioNLP Workshop 2023. Inspired by the work of the BioBART model, we continuously pre-trained a general domain BART model with biomedical data to adapt it to this specific domain. In the pre-training phase, several pre-training tasks are aggregated to inject linguistic knowledge and increase the abstractivity of the generated summaries. We present the results of our models, and also, we have carried out an additional study on the lengths of the generated summaries, which has provided us with interesting information.

ELiRF-VRAIN at BioNLP Task 1B: Radiology Report Summarization

This paper presents our contribution to the RadSum23 shared task organized as part of the BioNLP 2023. We compared state-of-the-art generative language models in generating high-quality summaries from radiology reports. A two-stage fine-tuning approach was introduced for utilizing knowledge learnt from different datasets. We evaluated the performance of our method using a variety of metrics. Our results revealed the potentials of different models in summarizing radiology reports and demonstrated the effectiveness of the two-stage fine-tuning approach. We also discussed the limitations and future directions of our work, highlighting the need for better understanding the architecture design's effect and optimal way of fine-tuning accordingly in automatic clinical summarizations.

KnowLab at RadSum23: comparing pre-trained language models in radiology report summarization

Radiology report summarization aims to automatically provide concise summaries of radiology findings, reducing time and errors in manual summaries. However, current methods solely summarize the text, which overlooks critical details in the images. Unfortunately, directly using the images in a multimodal model is difficult. Multimodal models are susceptible to overfitting due to their increased capacity, and modalities tend to overfit and generalize at different rates. Thus, we propose a novel retrieval-based approach that uses image similarities to generate additional text features. We further employ few-shot with chain-of-thought and ensemble techniques to boost performance. Overall, our method achieves state-of-the-art performance in the F1RadGraph score, which measures the factual correctness of summaries. We rank second place in both MIMIC-CXR and MIMIC-III hidden tests among 11 teams, with F1RadGraph scores of 42.86 and 36.31.

UTSA-NLP at RadSum23: Multi-modal Retrieval-Based Chest X-Ray Report Summarization

In this paper, we tackle a lay summarization task that aims to produce lay summary
of biomedical articles. BioLaySumm in the BioNLP Workshop at ACL 2023
(Goldsack et al., 2023), has presented us with this lay summarization task for
biomedical articles. Our proposed models provide a three-step abstractive
approach for summarizing biomedical articles. Our methodology involves breaking
down the original document into distinct sections, generating candidate summaries
for each subsection, and then selecting the top-performing paragraph for each
section. We run ablation studies to establish that each step in our pipeline is critical
for improvement in the quality of the lay summary. This model achieved the second-
highest rank in terms of readability scores (Luo et al., 2022). Our work distinguishes
itself from previous studies by not only considering the content of the paper but
also its structure, resulting in more coherent and comprehensible lay summaries.
We hope that our model for generating lay summaries of biomedical articles will be
a useful resource for individuals across various domains, including academia, industry, and healthcare, who require rapid comprehension of key scientific research.

APTSumm at BioLaySumm Task 1: Biomedical Breakdown, Improving Readability by Relevancy Based Selection

This study describes the model design of the NCUEE-NLP system for BioLaySumm Task 2 at the BioNLP 2023 workshop. We separately fine-tune pretrained PRIMERA models to independently generate technical abstracts and lay summaries of biomedical articles. A total of seven evaluation metrics across three criteria were used to compare system performance. Our best submission was ranked first for relevance, second for readability, and fourth for factuality, tying first for overall performance.

NCUEE-NLP at BioLaySumm Task 2: Readability-Controlled Summarization of Biomedical Articles Using the PRIMERA Models

Lay summarization aims to simplify complex scientific information for non-expert audiences. This paper investigates the trade-off between readability and relevance in the lay summarization of long biomedical documents. We introduce a two-stage framework that attains the best readability metrics in the first subtask of BioLaySumm 2023, with 8.924 Flesch–Kincaid Grade Level and 9.188 Dale–Chall Readability Score. However, this comes at the cost of reduced relevance and factuality, emphasizing the inherent challenges of balancing readability and content preservation in lay summarization. The first stage generates summaries using a large language model, such as BART with LSG attention. The second stage uses a zero-shot sentence simplification method to improve the readability of the summaries. In the second subtask, a hybrid dataset is employed to train a model capable of generating both lay summaries and abstracts. This approach achieves the best readability score and shares the top overall rank with other leading methods. Our study underscores the importance of developing effective methods for creating accessible lay summaries while maintaining information integrity. Future work will integrate simplification and summary generation within a joint optimization framework that generates high-quality lay summaries that effectively communicate scientific content to a broader audience.

Pathology Dynamics at BioLaySumm: the trade-off between Readability, Relevance, and Factuality in Lay Summarization

ChatGPT is a large language model developed by OpenAI. Despite its impressive performance across various tasks, no prior work has investigated its capability in the biomedical domain yet. To this end, this paper aims to evaluate the zero-shot performance of ChatGPT on various benchmark biomedical tasks, such as relation extraction, document classification, question answering, and summarization. To the best of our knowledge, this is the first work that conducts an extensive evaluation of ChatGPT in the biomedical domain. Interestingly, we find based on our evaluation that in biomedical datasets that have smaller training sets, zero-shot ChatGPT even outperforms the state-of-the-art fine-tuned generative transformer models, such as BioGPT and BioBART. This suggests that ChatGPT’s pre-training on large text corpora makes it quite specialized even in the biomedical domain. Our findings demonstrate that ChatGPT has the potential to be a valuable tool for various biomedical tasks that lack large annotated data.

Downloads

Next from ACL 2023

HeGeL: A Novel Dataset for Geo-Location from Hebrew Text

Similar lecture

CUED at ProbSum 2023: Hierarchical Ensemble of Summarization Models