Canada

Most medical dialogue systems assume that patients have clear goals (seeking a diagnosis, medicine querying, etc.) before medical consultation. However, in many real situations, due to the lack of medical knowledge, it is usually difficult for patients to determine clear goals with all necessary slots. In this paper, we identify this challenge as how to construct medical consultation dialogue systems to help patients clarify their goals. For further study, we create a novel human-to-human mixed-type medical consultation dialogue corpus, termed MidMed, covering four dialogue types: task-oriented dialogue for diagnosis, recommendation, QA, and chitchat. MidMed covers four departments (otorhinolaryngology, ophthalmology, skin, and digestive system), with 8,309 dialogues. Furthermore, we build benchmarking baselines on MidMed and propose an instruction-guiding medical dialogue generation framework, termed InsMed, to handle mixed-type dialogues. Experimental results show the effectiveness of InsMed.

&lt;iframe src=&quot;https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/bcde157d-4877-440c-a6de-e3c779203626&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

MidMed: Towards Mixed-Type Dialogues for Medical Consultation

intruction

medical consultation

mix-type

## 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."<br>

*Message from the General Chair, Dirk Hovy*





<br>

EMNLP 2025

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

Most medical dialogue systems assume that patients have clear goals (seeking a diagnosis, medicine querying, etc.) before medical consultation. However, in many real situations, due to the lack of medical knowledge, it is usually difficult for patients to determine clear goals with all necessary slots. In this paper, we identify this challenge as how to construct medical consultation dialogue systems to help patients clarify their goals. For further study, we create a novel human-to-human mixed-type medical consultation dialogue corpus, termed MidMed, covering four dialogue types: task-oriented dialogue for diagnosis, recommendation, QA, and chitchat. MidMed covers four departments (otorhinolaryngology, ophthalmology, skin, and digestive system), with 8,309 dialogues. Furthermore, we build benchmarking baselines on MidMed and propose an instruction-guiding medical dialogue generation framework, termed InsMed, to handle mixed-type dialogues. Experimental results show the effectiveness of InsMed.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/bcde157d-4877-440c-a6de-e3c779203626" width="300" height="400"></iframe>

poster

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
<br>The conference will be held in Toronto, Canada, July 9-14, 2023.<br><br>
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.<br>
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)**
<br><br><br><br>

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.

Data annotation is the process of labeling data that could be used to train machine learning models. Having high-quality annotation is crucial, as it allows the model to learn the relationship between the input data and the desired output. Large-scale language models, such as GPT-3, ChatGPT, and GPT-4, developed by OpenAI, have demonstrated impressive zero- and few-shot performance on a wide range of NLP tasks. It is therefore natural to wonder whether they can be used to effectively annotate data for NLP tasks. In this paper, we mainly evaluate the performance of GPT-3 as a data annotator by comparing it with traditional data annotation methods and analyzing its output on a range of tasks. We also provide the comparison among GPT-3, ChatGPT, and GPT-4 on certain tasks. Through this analysis, we aim to provide insight into the potential of large language models as general-purpose data annotators in NLP.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/81db3829-8d5e-4334-a41a-344d8c1aa25f" width="300" height="400"></iframe>

Is GPT-3 a Good Data Annotator?

The goal of multimodal abstractive summarization (MAS) is to produce a concise summary given the multimodal data (text and vision). Existing studies on MAS mainly focus on how to effectively use the extracted visual features, having achieved impressive success on the high-resource English dataset. However, less attention has been paid to the quality of the visual features to the summary, which may limit the model performance, especially in the low- and zero-resource scenarios. In this paper, we propose to improve the summary quality through summary-oriented visual features. To this end, we devise two auxiliary tasks including vision to summary task and masked image modeling task. Together with the main summarization task, we optimize the MAS model via the training objectives of all these tasks. By these means, the MAS model can be enhanced by capturing the summary-oriented visual features, thereby yielding more accurate summaries. Experiments on 44 languages, covering mid-high-, low-, and zero-resource scenarios, verify the effectiveness and superiority of the proposed approach, which achieves state-of-the-art performance under all scenarios. Additionally, we will contribute a large-scale multilingual multimodal abstractive summarization (MM-Sum) dataset to the research community.

<iframe src="https://app.sli.do/event/iHwnn5G9xYwcAmSbeKA4Au/embed/polls/2e562cdf-a6c4-4c13-a83a-265c509e56fb" width="300" height="400"></iframe>

Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization

Pre-trained language models (PLMs) demonstrate excellent abilities to understand texts in the generic domain while struggling in a specific domain. Although continued pre-training on a large domain-specific corpus is effective, it is costly to tune all the parameters on the domain. In this paper, we investigate whether we can adapt PLMs both effectively and efficiently by only tuning a few parameters. Specifically, we decouple the feed-forward networks (FFNs) of the Transformer architecture into two parts: the original pre-trained FFNs to maintain the old-domain knowledge and our novel domain-specific adapters to inject domain-specific knowledge in parallel.Then we adopt a mixture-of-adapters gate to fuse the knowledge from different domain adapters dynamically. Our proposed Mixture-of-Domain-Adapters (MixDA) employs a two-stage adapter-tuning strategy that leverages both unlabeled data and labeled data to help the domain adaptation: $i$) domain-specific adapter on unlabeled data; followed by $ii$) the task-specific adapter on labeled data. MixDA can be seamlessly plugged into the pretraining-finetuning paradigm and our experiments demonstrate that MixDA achieves superior performance on in-domain tasks~(GLUE), out-of-domain tasks~(ChemProt, RCT, IMDB, Amazon), and knowledge-intensive tasks~(KILT).Further analyses demonstrate the reliability, scalability, and efficiency of our method.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/5f5aafa3-609e-432a-b361-1d214a097e7f" width="300" height="400"></iframe>

Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models' Memories

End-to-end Speech Translation (E2E ST) aims to directly translate source speech into target text. Existing ST methods perform poorly when only extremely small speech-text data are available for training. We observe that an ST model's performance closely correlates with its embedding similarity between speech and source transcript. In this paper, we propose Word-Aligned COntrastive learning (WACO), a simple and effective method for extremely low-resource speech-to-text translation. Our key idea is bridging word-level representations for both speech and text modalities via contrastive learning. We evaluate WACO and other methods on the MuST-C dataset, a widely used ST benchmark, and on a low-resource direction Maltese-English from IWSLT 2023. Our experiments demonstrate that WACO outperforms the best baseline by 9+ BLEU points with only 1-hour parallel ST data. Code is available at https://github.com/owaski/WACO.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/effa15c2-6c99-4400-aeba-59d8f30f792f" width="300" height="400"></iframe>

WACO: Word-Aligned Contrastive Learning for Speech Translation

Knowledge distillation (KD) is a promising technique for model compression in neural machine translation. However, where the knowledge hides in KD is still not clear, which may hinder the development of KD. In this work, we first unravel this mystery from an empirical perspective and show that the knowledge comes from the top-1 predictions of teachers, which also helps us build a potential connection between word- and sequence-level KD. Further, we point out two inherent issues in vanilla word-level KD based on this finding. Firstly, the current objective of KD spreads its focus to whole distributions to learn the knowledge, yet lacks special treatment on the most crucial top-1 information. Secondly, the knowledge is largely covered by the golden information due to the fact that most top-1 predictions of teachers overlap with ground-truth tokens, which further restricts the potential of KD. To address these issues, we propose a new method named Top-1 Information Enhanced Knowledge Distillation (TIE-KD). Specifically, we design a hierarchical ranking loss to enforce the learning of the top-1 information from the teacher. Additionally, we develop an iterative KD procedure to infuse more additional knowledge by distilling on the data without ground-truth targets. Experiments on WMT'14 English-German, WMT'14 English-French and WMT'16 English-Romanian demonstrate that our method can respectively boost Transformer$_{base}$ students by +1.04, +0.60 and +1.11 BLEU scores and significantly outperforms the vanilla word-level KD baseline. Besides, our method shows higher generalizability on different teacher-student capacity gaps than existing KD techniques.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/c6229f25-b24d-4253-9a31-352a517575b9" width="300" height="400"></iframe>

Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation

Most research on stylized image captioning aims to generate style-specific captions using unpaired text, and has achieved impressive performance for simple styles like positive and negative. However, unlike previous single-sentence captions whose style is mostly embodied in distinctive words or phrases, real-world styles are likely to be implied at the syntactic and discourse levels. In this work, we introduce a new task of Stylized Visual Storytelling (SVST), which aims to describe a photo stream with stylized stories that are more expressive and attractive. We propose a multitasking memory-augmented framework called StyleVSG, which is jointly trained on factual visual storytelling data and unpaired style corpus, achieving a trade-off between style accuracy and visual relevance. Particularly for unpaired stylized text, StyleVSG learns to reconstruct the stylistic story from roughly parallel visual inputs mined with the CLIP model, avoiding problems caused by random mapping in previous methods. Furthermore, a memory module is designed to preserve the consistency and coherence of generated stories. Experiments show that our method can generate attractive and coherent stories with different styles such as fairy tale, romance, and humor. The overall performance of our StyleVSG surpasses state-of-the-art methods on both automatic and human evaluation metrics.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/a47de1ef-70e2-43a4-8876-4cc687f69f97" width="300" height="400"></iframe>

Attractive Storyteller: Stylized Visual Storytelling with Unpaired Text

Incomplete utterance rewriting (IUR) aims to restore the incomplete utterance with sufficient context information for comprehension. This paper introduces a simple yet efficient IUR method. Different from prior studies, we first employ only one-layer \textbf{M}LP architecture to mine latent semantic information between joint utterances for \textbf{IUR} task (\textbf{MIUR}). After that, we conduct a joint feature matrix to predict the token type and thus restore the incomplete utterance. The well-designed network and simple architecture make our method significantly superior to existing methods in terms of quality and inference speed\footnote{Our code is available at \url{https://github.com/IMU-MachineLearningSXD/MIUR}}.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/87ae8789-b2cd-48bf-af71-6bb0da1d7778" width="300" height="400"></iframe>

How Well Apply Simple MLP to Incomplete Utterance Rewriting?

In this work, we empirically show that updating pretrained LMs (350M, 1.3B, 2.7B) with just a few steps of Gradient Ascent Post-training (GAP) on random, unlabeled text corpora enhances its zero-shot generalization capabilities across diverse NLP tasks. Specifically, we show that GAP can allow LMs to become comparable to 2-3x times larger LMs across 12 different NLP tasks. We also show that applying GAP on out-of-distribution corpora leads to the most reliable performance improvements. Our findings indicate that GAP can be a promising method for improving the generalization capability of LMs without any task-specific fine-tuning.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/1d3b3eec-1e62-4d8c-bcd0-5b55053cb3f8" width="300" height="400"></iframe>

Gradient Ascent Post-training Enhances Language Model Generalization

Fine-tuning pre-trained language models for multiple tasks can be expensive in terms of storage.Parameter-efficient transfer learning (PETL) methods have been proposed to address this issue, but they still require a significant number of parameters when being applied to broader ranges of tasks.To achieve even greater storage reduction, we propose ProPETL, a novel method that enables efficient sharing of a single prototype PETL network (e.g. adapter, LoRA, and prefix-tuning) across layers and tasks. We learn binary masks to select different sub-networks from the prototype network and apply them as PETL modules into different layers. We find that the binary masks can determine crucial structural information from the network, which is often ignored in previous studies. Our work can also be seen as a type of pruning method, where we find that overparameterization also exists in the seemingly small PETL modules. We evaluate ProPETL on various downstream tasks and show that it can outperform other PETL methods with around 10% parameters required by the latter.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/f8908807-fb16-4072-a3ec-b998a479dc25" width="300" height="400"></iframe>

One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning

Semi-supervised learning has been an important approach to address challenges in extracting entities and relations from limited data. However, current semi-supervised works handle the two tasks (i.e., Named Entity Recognition and Relation Extraction) separately and ignore the cross-correlation of entity and relation instances as well as the existence of similar instances across unlabeled data. To alleviate the issues, we propose Jointprop, a Heterogeneous Graph-based Propagation framework for joint semi-supervised entity and relation extraction, which captures the global structure information between individual tasks and exploits interactions within unlabeled data. Specifically, we construct a unified span-based heterogeneous graph from entity and relation candidates and propagate class labels based on confidence scores. We then employ a propagation learning scheme to leverage the affinities between labelled and unlabeled samples.Experiments on benchmark datasets show that our framework outperforms the state-of-the-art semi-supervised approaches on NER and RE tasks. We show that the joint semi-supervised learning of the two tasks benefits from their codependency and validates the importance of utilizing the shared information between unlabeled data.

<iframe src="https://app.sli.do/event/jQes3hFZo3TYjGXEHm6w95/embed/polls/01d7e760-a00e-4989-b136-93ec671cf20b" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

Is GPT-3 a Good Data Annotator?

Similar lecture

Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation