Canada

Accurate human-annotated data for real-world use cases can be scarce and expensive to obtain. In the clinical domain, obtaining such data is even
more difficult due to privacy concerns which not only restrict open access to quality data but also require that the annotation be done by domain experts. In this paper, we propose a novel framework - InterDAPT - that leverages Intermediate Domain Finetuning to allow language models to adapt to narrow domains with small, noisy datasets. By making use of peripherally-related, unlabeled datasets, this framework circumvents domain-specific data scarcity issues. Our results show that this weakly
supervised framework provides performance improvements in downstream clinical named entity recognition tasks.

ACL 2023

Intermediate Domain Finetuning for Weakly Supervised Domain-adaptive Clinical NER

weak supervision

clinical nlp

domain adaptation

workshop paper

### 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.

Biomedical event extraction can be divided into three main subtasks; (1) biomedical event trigger detection, (2) biomedical argument identification and (3) event construction. This work focuses in the two first subtasks. For the first subtask we analyze a set of transformer language models that are commonly used in the biomedical domain to evaluate and compare their capacity for event trigger detection. We fine-tune the models using seven manually annotated corpora to assess their performance in different biomedical subdomains. SciBERT emerged as the highest performing model, presenting a slight improvement compared to baseline models. Then, for the second subtask we construct a knowledge graph (KG) from the biomedical corpora and integrate its KG embeddings to SciBERT to enrich its semantic information. We demonstrate that adding the KG embeddings to the model improves the argument identification performance by around 20 \%, and by around 15 \% compared to two baseline models. Our results suggest that fine-tuning a transformer model that is pretrained from scratch with biomedical and general data allows to detect event triggers and identify arguments covering different biomedical subdomains, and therefore improving its generalization. Furthermore, the integration of KG embeddings into the model can significantly improve the performance of biomedical event argument identification, outperforming the results of baseline models.

How Much do Knowledge Graphs Impact Transformer Models for Extracting Biomedical Events?

Recently, several methods have tackled the relation extraction task with QA and have shown successful results. However, the effectiveness of existing methods in specific domains, such as the biomedical domain, is yet to be verified. When there are multiple entity pairs that share an entity in a sentence, a QA-based relation extraction model that outputs only one single answer to a given question may not extract desired relations. In addition, these methods employ QA models that are not tuned for relation extraction. To address these issues, we first extend and apply a span QA-based relation extraction method to the drug-protein relation extraction by creating question templates and incorporating entity type markers. We further propose a binary QA-based method that directly uses the entity information available in the relation extraction task. The experimental results on the DrugProt dataset show that our QA-based methods, especially the proposed binary QA method, are effective for drug-protein relation extraction.

Biomedical Relation Extraction with Entity Type Markers and Relation-specific Question Agnswerin

Social media platforms have enabled individuals suffering from mental illnesses to share their lived experiences and find the online support necessary to cope. However, many users fail to receive genuine clinical support, thus exacerbating their symptoms. Screening users based on what they post online can aid providers in administering targeted healthcare and minimize false positives. Pre-trained Language Models (LMs) can assess users' social media data and classify them in terms of their mental health risk. We propose a Question-Answering (QA) approach to assess mental health risk using the Unified-QA model on two large mental health datasets. To protect user data, we extend Unified-QA by anonymizing the model training process using differential privacy. Our results demonstrate the effectiveness of modeling risk assessment as a QA task, specifically for mental health use cases. Furthermore, the model's performance decreases by less than 1% with the inclusion of differential privacy. The proposed system's performance is indicative of a promising research direction that will lead to the development of privacy-aware diagnostic systems.

Privacy Aware Question-Answering System for Online Mental Health Risk Assessment

This paper describes the submission of the TALP-UPC team to the Problem List Summarization task from the BioNLP 2023 workshop. This task consists of automatically extracting a list of health issues from the e-health medical record of a given patient. Our submission combines additional steps of data annotation with finetuning of BERT pre-trained language models. Our experiments focus on the impact of finetuning on different datasets as well as the addition of data augmentation techniques to delay overfitting.

TALP-UPC at ProbSum 2023: Fine-tuning and Data Augmentation Strategies for NER

Medical progress notes play a crucial role in documenting a patient's hospital journey, including his or her condition, treatment plan, and any updates for healthcare providers. Automatic summarisation of a patient's problems in the form of a ``problem list'' can aid stakeholders in understanding a patient's condition, reducing workload and cognitive bias. BioNLP 2023 Shared Task 1A focuses on generating a list of diagnoses and problems from the provider's progress notes during hospitalisation. In this paper, we introduce our proposed approach to this task, which integrates two complementary components . One component employs large language models (LLMs) for data augmentation; the other is an abstractive summarisation LLM with a novel pre-training objective for generating the patients' problems summarised as a list. Our approach was ranked second among all submissions to the shared task. The performance of our model on the development and test datasets shows that our approach is more robust on unknown data, with an improvement of up to 3.1 points over the same size of the larger model.

Team:PULSAR at ProbSum 2023:PULSAR: Pre-training with Extracted Healthcare Terms for Summarising Patients' Problems and Data Augmentation with Black-box Large Language Models

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)

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

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.

Downloads

Next from ACL 2023

How Much do Knowledge Graphs Impact Transformer Models for Extracting Biomedical Events?

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL 2023

How Much do Knowledge Graphs Impact Transformer Models for Extracting Biomedical Events?

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads