Canada

A common metric for evaluating Automatic Speech Recognition (ASR) is Word Error Rate (WER) which solely takes into account dis- crepancies at the word-level. Although use- ful, WER is not guaranteed to correlate well with human judgment or performance on down- stream tasks that use ASR. Meaningful assess- ment of ASR mistakes becomes even more im- portant in high-stake scenarios such as health- care. We propose 2 general measures to evaluate the severity of mistakes made by ASR systems, one based on sentiment analysis and another based on text embeddings. We evaluate these measures on simulated patient-doctor conversations using 5 ASR systems. Results show that these measures capture characteristics of ASR errors that WER does not. Furthermore, we train an ASR system incorporating severity and demonstrate the potential for using severity not only in the evaluation, but in the development of ASR. Advantages and limitations of this methodology are analyzed and discussed.

ACL 2023

Evaluating and Improving Automatic Speech Recognition using Severity

severity

evaluation

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

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.

Fact-checking of health-related claims has become necessary in this digital age, where any information posted online is easily available to everyone. The most effective way to verify such claims is by using evidences obtained from reliable sources of medical knowledge, such as PubMed. Recent advances in the field of NLP have helped automate such fact-checking tasks. In this work, we propose a domain-specific BERT-based model using a transfer learning approach for the task of predicting the veracity of claim-evidence pairs for the verification of health-related facts. We also improvise on a method to combine multiple evidences retrieved for a single claim, taking into consideration conflicting evidences as well. We also show how our model can be exploited when labelled data is available and how back-translation can be used to augment data when there is data scarcity.

Multiple Evidence Combination for Fact-Checking of Health-Related Information

As opposed to general English, many concepts in biomedical terminology have been designed in recent history by biomedical professionals with the goal of being precise and concise. This is often achieved by concatenating meaningful biomedical morphemes to create new semantic units. Nevertheless, most modern biomedical language models (LMs) are pre-trained using standard domain-specific tokenizers derived from large scale biomedical corpus statistics without explicitly leveraging the agglutinating nature of biomedical language. In this work, we first find that standard open-domain and biomedical tokenizers are largely unable to segment biomedical terms into meaningful components. Therefore, we hypothesize that using a tokenizer which segments biomedical terminology more accurately would enable biomedical LMs to improve their performance on downstream biomedical NLP tasks, especially ones which involve biomedical terms directly such as named entity recognition (NER) and entity linking. Surprisingly, we find that pre-training a biomedical LM using a more accurate biomedical tokenizer does not improve the entity representation quality of a language model as measured by several intrinsic and extrinsic measures such as masked language modeling prediction (MLM) accuracy as well as NER and entity linking performance. These quantitative findings, along with a case study which explores entity representation quality more directly, suggest that the biomedical pre-training process is quite robust to instances of sub-optimal tokenization.

Biomedical Language Models are Robust to Sub-optimal Tokenization

We systematically investigate lightweight strategies to adapt large language models (LLMs) for the task of radiology report summarization (RRS). Specifically, we focus on domain adaptation via pretraining (on natural language, biomedical text, or clinical text) and via discrete prompting or parameter-efficient fine-tuning. Our results consistently achieve best performance by maximally adapting to the task via pretraining on clinical text and fine-tuning on RRS examples. Importantly, this method fine-tunes a mere 0.32% of parameters throughout the model, in contrast to end-to-end fine-tuning (100% of parameters). Additionally, we study the effect of in-context examples and out-of-distribution (OOD) training before concluding with a radiologist reader study and qualitative analysis. Our findings highlight the importance of domain adaptation in RRS and provide valuable insights toward developing effective natural language processing solutions for clinical tasks.

RadAdapt: Radiology Report Summarization via Lightweight Domain Adaptation of Large Language Models

Automatically rating the quality of published
research is a critical step in medical evidence
synthesis. While several methods have been
proposed, their algorithmic fairness has been
overlooked, even though significant risks may
result when such systems are deployed in
biomedical contexts. In this work, we study
the fairness of two systems with respect to two
sensitive attributes: participant sex and med-
ical area. In some cases, we find important
inequalities, leading us to apply various debi-
asing methods. Upon examining the interplay
of predictive performance and fairness, as well
as medically-critical selective classification ca-
pabilities and calibration performance, we find
that it is possible to improve fairness through
debiasing, but often at a cost to other perfor-
mance measures.

Promoting Fairness in Classification of Quality of Medical Evidence

We consider the task of automatically extracting various overlapping frames, i.e, structured entities composed of multiple labels and mentions, from long clinical breast radiology documents. 
While many methods exist for related topics such as event extraction, slot filling, or discontinuous entity recognition, a challenge in our study resides in the fact that clinical reports typically contain overlapping frames that span multiple sentences or paragraphs.
We propose a new method that addresses these difficulties and evaluate it on a new annotated corpus.
Despite the small number of documents, we show that the hybridization between knowledge injection and a learning-based system allows us to quickly obtain proper results.
We will also introduce the concept of scope relations and show that it both improves the performance of our system, and provides a visual explanation of the predictions.


An end-to-end neural model based on cliques and scopes for frame extraction in long breast radiology reports

In this presentation, we will talk about optimal approaches to pre-train biomedical language models and evaluate their performance on the Named Entity Recognition task. Moreover, we will present our proposed method of contextualized weight distillation used to introduce domain-specific vocabulary in the continued pre-training of language models. We will also discuss how using Curriculum learning when pre-training the BIOptimus model helped us to guide the model's learning process more smoothly and introduce the biomedical language model to a broader scope of language experience.

BIOptimus: Pre-training an Optimal Biomedical Language Model with Curriculum Learning for Named Entity Recognition

Fine-tuning biomedical pre-trained language models (BioPLMs) such as BioBERT has become a common practice dominating leaderboards across various natural language processing tasks. Despite their success and wide adoption, prevailing fine-tuning approaches for named entity recognition (NER) naively train BioPLMs on targeted datasets without considering class distributions. This is problematic especially when dealing with imbalanced biomedical gold-standard datasets for NER in which most biomedical entities are underrepresented. In this talk, we discuss our work on addressing the class imbalance problem and propose a weighted loss trainer (WeLT), as a cost-sensitive fine-tuning approach based on new re-scaled class weights for the task of biomedical NER.


WeLT: Improving Biomedical Fine-tuned Pre-trained Language Models with Cost-sensitive Learning

This paper presents the results of the shared task on Lay Summarisation of Biomedical Research Articles (BioLaySumm), hosted at the BioNLP Workshop at ACL 2023. The goal of this shared task is to develop abstractive summarisation models capable of generating ``lay summaries'' (i.e., summaries that are comprehensible to non-technical audiences) in both a controllable and non-controllable setting. There are two subtasks: 1) Lay Summarisation, where the goal is for participants to build models for lay summary generation only, given the full article text and the corresponding abstract as input; and 2) Readability-controlled Summarisation, where the goal is for participants to train models to generate both the technical abstract and the lay summary, given an article’s main text as input. In addition to overall results, we report on the setup and insights from the BioLaySumm shared task, which attracted a total of 20 participating teams across both subtasks.

BioLaySumm 2023 Shared Task: Lay Summarisation of Biomedical Research Articles

This paper proposes a new document classification method that incorporates the representations of a literature graph created from bibliographic and entity information.
Recently, document classification performance has been significantly improved with large pre-trained language models; however, there still remain documents that are difficult to classify. External information, such as bibliographic information, citation links, descriptions of entities, and medical taxonomies, has been considered one of the keys to dealing with such documents in document classification. 
Although several document classification methods using external information have been proposed, they only consider limited relationships, e.g., word co-occurrence and citation relationships. However, there are multiple types of external information.
To overcome the limitation of the conventional use of external information, we propose a document classification model that simultaneously considers bibliographic and entity information to deeply model the relationships among documents using the representations of the literature graph.
The experimental results show that our proposed method outperforms existing methods on two document classification datasets in the biomedical domain with the help of the literature graph. Our source code is publicly available at https://github.com/tticoin/BDCL-LitGraph.

Biomedical Document Classification with Literature Graph Representations of Bibliographies and Entities

Radiology report summarization is a growing area of research. Given the Findings and/or Background sections of a radiology report, the goal is to generate a summary (called an Im- pression section) that highlights the key ob- servations and conclusions of the radiology study. Recent efforts have released systems that achieve promising performance as mea- sured by widely used summarization metrics such as BLEU and ROUGE. However, the research area of radiology report summariza- tion currently faces two important limitations. First, most of the results are reported on private datasets. This limitation prevents the ability to reproduce results and fairly compare different systems and solutions. Secondly, to the best of our knowledge, most research is carried out on chest X-rays. To palliate these two limitations, we propose a radiology report summarization (RadSum) challenge on i) a new dataset of eleven different modalities and anatomies pairs based on the MIMIC-III database ii) a multimodal report summarization dataset based on MIMIC-CXR enhanced with a brand-new test-set from Stanford Hospital. In total, we received 112 submissions across 11 teams.

Downloads

Next from ACL 2023

Multiple Evidence Combination for Fact-Checking of Health-Related Information

Similar lecture

ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction

.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

Multiple Evidence Combination for Fact-Checking of Health-Related Information

Similar lecture

ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction

Downloads