Canada

Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM) systems achieve state-of-the-art results on semantic spoken language tasks by utilizing rich semantic representations from the LLM. These systems come at the cost of labeled audio transcriptions, which is expensive and time-consuming to obtain. We propose a task-agnostic unsupervised way of incorporating semantic information from LLMs into self-supervised speech encoders without labeled audio transcriptions. By introducing semantics, we improve existing speech encoder spoken language understanding performance by over 5% on intent classification, with modest gains in named entity resolution and slot filling, and spoken question answering FF1 score by over 2%. Our approach, which uses no ASR data, achieves similar performance as methods trained on over 100 hours of labeled audio transcripts, demonstrating the feasibility of unsupervised semantic augmentations to existing speech encoders.

&lt;iframe src=&quot;https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/f5665e49-0c86-4882-b9cb-c10375ab5cc3&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Introducing Semantics into Speech Encoders

spoken question answering

spoken language understanding

speech recognition

## 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.

Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM) systems achieve state-of-the-art results on semantic spoken language tasks by utilizing rich semantic representations from the LLM. These systems come at the cost of labeled audio transcriptions, which is expensive and time-consuming to obtain. We propose a task-agnostic unsupervised way of incorporating semantic information from LLMs into self-supervised speech encoders without labeled audio transcriptions. By introducing semantics, we improve existing speech encoder spoken language understanding performance by over 5% on intent classification, with modest gains in named entity resolution and slot filling, and spoken question answering FF1 score by over 2%. Our approach, which uses no ASR data, achieves similar performance as methods trained on over 100 hours of labeled audio transcripts, demonstrating the feasibility of unsupervised semantic augmentations to existing speech encoders.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/f5665e49-0c86-4882-b9cb-c10375ab5cc3" 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.

Out-of-distribution (OOD) detection is a critical task for reliable predictions over text. Fine-tuning with pre-trained language models has been a de facto procedure to derive OOD detectors with respect to in-distribution (ID) data. Despite its common use, the understanding of the role of fine-tuning and its necessity for OOD detection is largely unexplored. In this paper, we raise the question: is fine-tuning necessary for OOD detection? We present a study investigating the efficacy of directly leveraging pre-trained language models for OOD detection, without any model fine-tuning on the ID data. We compare the approach with several competitive fine-tuning objectives, and offer new insights under various types of distributional shifts. Extensive experiments demonstrate near-perfect OOD detection performance (with 0% FPR95 in many cases), strongly outperforming the fine-tuned counterpart.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/b763801d-5c5d-45fe-a5ae-41716a672423" width="300" height="400"></iframe>

Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection

Dense retrieval has shown promising results in various information retrieval tasks, and hybrid retrieval, combined with the strength of sparse retrieval, has also been actively studied. A key challenge in hybrid retrieval is to make sparse and dense complementary to each other. Existing models have focused on dense models to capture "residual" features neglected in the sparse models. Our key distinction is to show how this notion of residual complementarity is limited, and propose a new objective, denoted as RoC (Ratio of Complementarity), which captures a fuller notion of complementarity. We propose a two-level orthogonality designed to improve RoC, then show that the improved RoC of our model, in turn, improves the performance of hybrid retrieval. Our method outperforms all state-of-the-art methods on three representative IR benchmarks: MSMARCO-Passage, Natural Questions, and TREC Robust04, with statistical significance. Our finding is also consistent in various adversarial settings.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/2fa89745-8c0a-4fa1-9fa2-0e7349348b22" width="300" height="400"></iframe>

On Complementarity Objectives for Hybrid Retrieval

Transformer-based Language Models (LMs) have achieved impressive results on natural language understanding tasks, but they can also generate toxic text such as insults, threats, and profanity, limiting their real-world applications. To overcome this issue, a few text generation approaches aim to detoxify toxic texts using additional LMs or perturbations. However, previous methods require excessive memory, computations, and time which are serious bottlenecks in their real-world application. To address such limitations, we propose an effective yet efficient method for language detoxification using an attribute-discriminative latent space. Specifically, we project the latent space of an original Transformer LM onto a discriminative latent space that well-separates texts by their attributes using a projection block and an attribute discriminator. This allows the LM to control the text generation to be non-toxic with minimal memory and computation overhead. We validate our model, Attribute-Discriminative Language Model (ADLM) on detoxified language and dialogue generation tasks, on which our method significantly outperforms baselines both in performance and efficiency.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/212065c0-6a94-4ffd-a71b-adac4fba738a" width="300" height="400"></iframe>

Language Detoxification with Attribute-Discriminative Latent Space

The propensity of abstractive summarization models to make factual errors has been studied extensively, including design of metrics to detect factual errors and annotation of errors in current systems' outputs. However, the ever-evolving nature of summarization systems, metrics, and annotated benchmarks makes factuality evaluation a moving target, and drawing clear comparisons among metrics has become increasingly difficult. In this work, we aggregate factuality error annotations from nine existing datasets and stratify them according to the underlying summarization model. We compare performance of state-of-the-art factuality metrics, including recent ChatGPT-based metrics, on this stratified benchmark and show that their performance varies significantly across different types of summarization models. Critically, our analysis shows that much of the recent improvement in the factuality detection space has been on summaries from older (pre-Transformer) models instead of more relevant recent summarization models. We further perform a finer-grained analysis per error-type and find similar performance variance across error types for different factuality metrics. Our results show that no one metric is superior in all settings or for all error types, and we provide recommendations for best practices given these insights.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/ff2340f5-0b87-4485-8fa0-121a6dee7b97" width="300" height="400"></iframe>

Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors

The recent emergence of Neuro-Symbolic Agent (NeSA) approaches to natural language-based interactions calls for the investigation of model-based approaches. In contrast to model-free approaches, which existing NeSAs take, learning an explicit world model has an interesting potential especially in the explainability, which is one of the key selling points of NeSA. To learn useful world models, we leverage one of the recent neuro-symbolic architectures, Logical Neural Networks (LNN). Here, we describe a method that can learn neuro-symbolic world models on the TextWorld-Commonsense set of games.We then show how this can be improved further by taking inspiration from the concept of proprioception, but for conversation. This is done by enhancing the internal logic state with a memory of previous actions while also guiding future actions by augmenting the learned model with constraints based on this memory.This greatly improves the game-solving agents performance in a TextWorld setting, where the advantage over the baseline is an 85% average steps reduction and x2.3 average score.

<iframe src="https://app.sli.do/event/qQ87ZDnDYN6cfmCQWHFaok/embed/polls/66295ddb-4664-454e-b8f7-c5a3e72efa28" width="300" height="400"></iframe>

Learning Neuro-Symbolic World Models with Conversational Proprioception

We introduce ART, a new corpus-level autoencoding approach for training dense retrieval models that does not require any labeled training data. Dense retrieval is a central challenge for open-domain tasks, such as Open QA, where state-of-the-art methods typically require large supervised datasets with custom hard-negative mining and denoising of positive examples. ART, in contrast, only requires access to unpaired inputs and outputs (e.g. questions and potential answer passages). It uses a new passage retrieval autoencoding scheme, where (1) an input question is used to retrieve a set of evidence passages, and (2) the passages are then used to compute the probability of reconstructing the original question. Training for retrieval based on question reconstruction enables effective unsupervised learning of both passage and question encoders, which can be later incorporated into complete Open QA systems without any further finetuning. Extensive experiments demonstrate that ART obtains state-of-the-art results on multiple QA retrieval benchmarks with only generic initialization from a pretrained language model, removing the need for labeled data and task-specific losses.

Questions Are All You Need to Train a Dense Passage Retriever

Neural network models have been proposedto explain the grapheme-phoneme mappingprocess in humans for many alphabet languages.These models not only successfullylearned the correspondence of the letterstrings and their pronunciation, but alsocaptured human behavior in nonce wordnaming tasks. How would the neural modelsperform for a non-alphabet language (Chinese)unknown character task? How wellwould the model capture human behavior?In this study, we evaluate a set of transformermodels and compare their performanceswith human behaviors on unknownChinese character naming task. We foundthat the models and humans behaved verysimilarly that they have similar accuracy distributionfor each character and have a substantialoverlap in answers. In addition, themodels’ answers are highly correlated withhumans’ answers. These results suggestedthat the transformer models can well capturehuman’s character naming behavior.

Evaluating Transformer Models and Human Behaviors on Chinese Character Naming

Complementary to finding good general word embeddings, an important question for representation learning is to find dynamic word embeddings, e.g., across time or domain. Current methods do not offer a way to use or predict information on structure between sub-corpora, time or domain and dynamic embeddings can only be compared after post-alignment. We propose novel word embedding methods that provide general word representations for the whole corpus, domain-specific representations for each sub-corpus, sub-corpus structure, and embedding alignment simultaneously. We present an empirical evaluation on New York Times articles and two English Wikipedia datasets with articles on science and philosophy. Our method, called Word2Vec with Structure Prediction (W2VPred), provides better performance than baselines in terms of the general analogy tests, domain-specific analogy tests, and multiple specific word embedding evaluations as well as structure prediction performance when no structure is given a priori. As a use case in the field of Digital Humanities we demonstrate how to raise novel research questions for high literature from the German Text Archive.

Domain-Specific Word Embeddings with Structure Prediction

Discharge summaries are comprehensive medical records that encompass vital information about a patient's hospital stay. A crucial aspect of discharge summaries is the temporal information of treatments administered throughout the patient's illness. With an extensive volume of clinical documents, manually extracting and compiling a patient's medication list can be laborious, time-consuming, and susceptible to errors. The objective of this paper is to build upon the recent development on clinical NLP by temporally classifying treatments in clinical texts, specifically determining whether a treatment was administered between the time of admission and discharge from the hospital. State-of-the-art NLP methods including prompt-based learning on Generative Pre-trained Transformers (GPTs) models and fine-tuning on pre-trained language models (PLMs) such as BERT were employed to classify temporal relations between treatments and hospitalisation periods in discharge summaries. Fine-tuning with the BERT model achieved an F1 score of 92.45\% and a balanced accuracy of 77.56\%, while prompt learning using the T5 model and mixed templates resulted in an F1 score of 90.89\% and a balanced accuracy of 72.07\%. Our codes and data are available at \url{https://github.com/HECTA-UoM/MedTem}.

MedTem2.0: Prompt-based Temporal Classification of Treatment Events from Discharge Summaries

A buzzer quiz is a genre of quiz in which multiple players simultaneously listen to a quiz being read aloud and respond it by buzzing in as soon as they can predict the answer. Because incorrect answers often result in penalties, a buzzer-quiz answering system must not only predict the answer from only part of a question but also estimate the predicted answer's accuracy. In this paper, we introduce two types of buzzer-quiz answering systems: (1) a system that directly generates an answer from part of a question by using an autoregressive language model; and (2) a system that first reconstructs the entire question by using an autoregressive language model and then determines the answer according to the reconstructed question. We then propose a method to estimate the accuracy of the answers for each system by using the internal scores of each model.

Downloads

Next from ACL 2023

Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection

Similar lecture

Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders