Canada

Many text classification tasks are inherently ambiguous, which results in automatic systems having a high risk of making mistakes, in spite of using advanced machine learning models. For example, toxicity detection in user-generated content is a subjective task, and notions of toxicity can be annotated according to a variety of definitions, that can be in conflict with one another. Instead of relying solely on automatic solutions, moderation of the most difficult and ambiguous cases can be delegated to human workers. Potential mistakes in automated classification can be identified by using uncertainty estimation (UE) techniques. Although UE is a rapidly growing field within natural language processing, we find that state-of-the-art UE methods estimate only epistemic uncertainty and show poor performance, or under-perform trivial methods for ambiguous tasks such as toxicity detection. We argue that in order to create robust uncertainty estimation methods for ambiguous tasks it is necessary to account also for aleatoric uncertainty. In this paper, we propose a new uncertainty estimation method that combines epistemic and aleatoric UE methods. We show that by using our hybrid method, we can outperform state-of-the-art UE methods for toxicity detection and other ambiguous text classification tasks.

&lt;iframe src=&quot;https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/f5b71a5a-158a-4fb5-86b0-60b76e3bc992&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Hybrid Uncertainty Quantification for Selective Text Classification in Ambiguous Tasks

toxicity detection

selective classification

uncertainty estimation

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair:<br>
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for  Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025.  ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am  deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.*<br>
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)<br><br><br>



To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Many text classification tasks are inherently ambiguous, which results in automatic systems having a high risk of making mistakes, in spite of using advanced machine learning models. For example, toxicity detection in user-generated content is a subjective task, and notions of toxicity can be annotated according to a variety of definitions, that can be in conflict with one another. Instead of relying solely on automatic solutions, moderation of the most difficult and ambiguous cases can be delegated to human workers. Potential mistakes in automated classification can be identified by using uncertainty estimation (UE) techniques. Although UE is a rapidly growing field within natural language processing, we find that state-of-the-art UE methods estimate only epistemic uncertainty and show poor performance, or under-perform trivial methods for ambiguous tasks such as toxicity detection. We argue that in order to create robust uncertainty estimation methods for ambiguous tasks it is necessary to account also for aleatoric uncertainty. In this paper, we propose a new uncertainty estimation method that combines epistemic and aleatoric UE methods. We show that by using our hybrid method, we can outperform state-of-the-art UE methods for toxicity detection and other ambiguous text classification tasks.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/f5b71a5a-158a-4fb5-86b0-60b76e3bc992" 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.

Semi-supervised text classification (SSTC) aims at text classification with few labeled data and massive unlabeled data. Recent works achieve this task by pseudo-labeling methods, with the belief that the unlabeled and labeled data have identical data distribution, and assign the unlabeled data with pseudo-labels as additional supervision. However, existing pseudo-labeling methods usually suffer from ambiguous categorical boundary issues when training the pseudo-labeling phase, and simply select pseudo-labels without considering the unbalanced categorical distribution of the unlabeled data, making it difficult to generate reliable pseudo-labels for each category. We propose a novel semi-supervised framework, namely ProtoS^2, with prototypical cluster separation (PCS) and prototypical-center data selection (CDS) technology to address the issue. Particularly, PCS exploits categorical prototypes to assimilate instance representations within the same category, thus emphasizing low-density separation for the pseudo-labeled data to alleviate ambiguous boundaries. Besides, CDS selects central pseudo-labeled data considering the categorical distribution, avoiding the model from biasing on dominant categories. Empirical studies and extensive analysis with four benchmarks demonstrate the effectiveness of the proposed model.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/e1bf4f1c-3929-4281-9bb5-974ea8847001" width="300" height="400"></iframe>

Prototype-Guided Pseudo Labeling for Semi-Supervised Text Classification

We study the problem of defying catastrophic forgetting when learning a series of language processing tasks. Compared with previous methods, we emphasize the importance of not caching history tasks' data, which makes the problem more challenging. Our proposed method applies the parameter isolation strategy. For each task, it allocates a small portion of private parameters and learns them with a shared pre-trained model. To load correct parameters at testing time, we introduce a simple yet effective non-parametric method. Experiments on continual language learning benchmarks show that our method is significantly better than all existing no-data-cache methods, and is comparable (or even better) than those using historical data.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/39f36c9e-1cb3-48d7-9c00-6e159c2ffd67" width="300" height="400"></iframe>

Rehearsal-free Continual Language Learning via Efficient Parameter Isolation

With recent advances in question-answering models, various datasets have been collected to improve and study the effectiveness of these models on scientific texts. Questions and answers in these datasets explore a scientific paper by seeking factual information from the paper's content. However, these datasets do not tackle the argumentative content of scientific papers, which is of huge importance in persuasiveness of a scientific discussion. We introduce ArgSciChat, a dataset of 41 argumentative dialogues between scientists on 20 NLP papers. The unique property of our dataset is that it includes both exploratory and argumentative questions and answers in a dialogue discourse on a scientific paper. Moreover, the size of ArgSciChat demonstrates the difficulties in collecting dialogues for specialized domains.Thus, our dataset is a challenging resource to evaluate dialogue agents in low-resource domains, in which collecting training data is costly. We annotate all sentences of dialogues in ArgSciChat and analyze them extensively. The results confirm that dialogues in ArgSciChat include exploratory and argumentative interactions. Furthermore, we use our dataset to fine-tune and evaluate a pre-trained document-grounded dialogue agent. The agent achieves a low performance on our dataset, motivating a need for dialogue agents with a capability to reason and argue about their answers. We publicly release ArgSciChat.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/561bdaa0-7312-435b-b062-3034aa8dadb6" width="300" height="400"></iframe>

A Dataset of Argumentative Dialogues on Scientific Papers

Many text generation applications require the generated text to be factually consistent with input information. Automatic evaluation of factual consistency is challenging. Previous work has developed various metrics that often depend on specific functions, such as natural language inference (NLI) or question answering (QA), trained on limited data. Those metrics thus can hardly assess diverse factual inconsistencies (e.g., contradictions, hallucinations) that occur in varying inputs/outputs (e.g., sentences, documents) from different tasks. In this paper, we propose AlignScore, a new holistic metric that applies to a variety of factual inconsistency scenarios as above. AlignScore is based on a general function of information alignment between two arbitrary text pieces. Crucially, we develop a unified training framework of the alignment function by integrating a large diversity of data sources, resulting in 4.7M training examples from 7 well-established tasks (NLI, QA, paraphrasing, fact verification, information retrieval, semantic similarity, and summarization). We conduct extensive experiments on large-scale benchmarks including 22 evaluation datasets, where 19 of the datasets were never seen in the alignment training. AlignScore achieves substantial improvement over a wide range of previous metrics. Moreover, AlignScore (355M parameters) matches or even outperforms metrics based on ChatGPT and GPT-4 that are orders of magnitude larger.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/fe840250-2380-456e-8162-093559555b6e" width="300" height="400"></iframe>

AlignScore: Evaluating Factual Consistency with A Unified Alignment Function

Massively multilingual language models have displayed strong performance in zero-shot (ZS-XLT) and few-shot (FS-XLT) cross-lingual transfer setups, where models fine-tuned on task data in a source language are transferred without any or with only a few annotated instances to the target language(s). However, current work typically overestimates model performance as fine-tuned models are frequently evaluated at model checkpoints that generalize best to validation instances in the target languages. This effectively violates the main assumptions of true' ZS-XLT and FS-XLT. Such XLT setups require robust methods that do not depend on labeled target language data for validation and model selection. In this work, aiming to improve the robustness of true' ZS-XLT and FS-XLT, we propose a simple and effective method that averages different checkpoints (i.e., model snapshots) during task fine-tuning. We conduct exhaustive ZS-XLT and FS-XLT experiments across higher-level semantic tasks (NLI, extractive QA) and lower-level token classification tasks (NER, POS). The results indicate that averaging model checkpoints yields systematic and consistent performance gains across diverse target languages in all tasks. Importantly, it simultaneously substantially desensitizes XLT to varying hyperparameter choices in the absence of target language validation. We also show that checkpoint averaging benefits performance when further combined with run averaging (i.e., averaging the parameters of models fine-tuned over independent runs).

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/41efc70f-02d2-46b7-a359-4167761532f1" width="300" height="400"></iframe>

Free Lunch: Robust Cross-Lingual Transfer via Model Checkpoint Averaging

Language models trained on large-scale corpora can generate remarkably fluent results in open-domain dialogue. However, for the persona-based dialogue generation task, consistency and coherence are also key factors, which are great challenges for language models. Existing works mainly focus on valuable data filtering, model structure modifying, or objective function designing, while their improvements are limited and hard to generalize to all types of pre-trained language models. However, we find that language models can produce consistent and coherent responses if we consider enough generations. Thus, the problems lay in large-scale response generation and target response selection. In this work, a simple but effective two-stage SimOAP strategy is proposed, i.e., over-sampling and post-evaluation. The over-sampling stage takes large-scale responses from existing trained models efficiently via off-the-shelf distilling and compressing methods, and the post-evaluation stage selects a good response based on multiple well-designed evaluation metrics from large-scale candidates. Experimental results show that the proposed plug-in SimOAP strategy improves the backbone models and outperforms the baseline strategies in both automatic and human evaluations.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/fa48f0dd-c139-4c3b-9da4-2ab720bf8dad" width="300" height="400"></iframe>

SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation

Despite the recent advances in dialogue state tracking (DST), the joint goal accuracy (JGA) of the existing methods on MultiWOZ 2.1 still remains merely 60%. In our preliminary error analysis, we find that beam search produces a pool of candidates that is likely to include the correct dialogue state. Motivated by this observation, we introduce a novel framework, called BREAK (Beam search and RE-rAnKing), that achieves outstanding performance on DST. BREAK performs DST in two stages: (i) generating k-best dialogue state candidates with beam search and (ii) re-ranking the candidates to select the correct dialogue state. This simple yet powerful framework shows state-of-the-art performance on all versions of MultiWOZ and M2M datasets. Most notably, we push the joint goal accuracy to 80-90% on MultiWOZ 2.1-2.4, which is an improvement of 23.6%, 26.3%, 21.7%, and 10.8% over the previous best-performing models, respectively. The data and code will be available at https://github.com/tony-won/DST-BREAK

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/13d609f2-7b20-4fad-9308-57f86f97087c" width="300" height="400"></iframe>

BREAK: Breaking the Dialogue State Tracking Barrier with Beam Search and Re-ranking

The World Health Organization (WHO) has significantly emphasized the need for mental health care. The social stigma associated with mental illness prevents individuals from addressing their issues and getting assistance. In such a scenario, the relevance of online counseling has increased dramatically. The feelings and attitudes that a client and a counselor express towards each other result in a higher or lower counseling experience. A counselor should be friendly and gain clients' trust to make them share their problems comfortably. Thus, it is essential for the counselor to adequately comprehend the client's emotions and ensure client's welfare, i.e. s/he should adapt and deal with the clients politely and empathetically to provide a pleasant, cordial and personalized experience. Motivated by this, in this work, we attempt to build a novel Polite and empAthetic counseLing conversational agent PAL to lay down the counseling support to substance addict and crime victims. To have client's emotion-based polite and empathetic responses, two counseling datasets laying down the counseling support to substance addicts and crime victims are annotated. These annotated datasets are used to build PAL in a reinforcement learning framework. A novel reward function is formulated to ensure correct politeness and empathy preferences as per client's emotions with naturalness and non-repetitiveness in responses. Thorough automatic and human evaluation showcase the usefulness and strength of the designed novel reward function. Our proposed system is scalable and can be easily modified with different modules of preference models as per need.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/f0afdd99-3d66-41af-a953-c542177a147b" width="300" height="400"></iframe>

PAL to Lend a Helping Hand: Towards Building an Emotion Adaptive Polite and Empathetic Counseling Conversational Agent

In recent years, there has been significant progress in developing pre-trained language models for NLP. However, these models often struggle when fine-tuned on small datasets. To address this issue, researchers have proposed various adaptation approaches. Prompt-based tuning is arguably the most common way, especially for larger models. Previous research shows that adding contrastive learning to prompt-based fine-tuning is effective as it helps the model generate embeddings that are more distinguishable between classes, and it can also be more sample-efficient as the model learns from positive and negative examples simultaneously. One of the most important components of contrastive learning is data augmentation, but unlike computer vision, effective data augmentation for NLP is still challenging. This paper proposes LM-CPPF, Contrastive Paraphrasing-guided Prompt-based Fine-tuning of Language Models, which leverages prompt-based few-shot paraphrasing using generative language models, especially large language models such as GPT-3 and OPT-175B, for data augmentation. Our experiments on multiple text classification benchmarks show that this augmentation method outperforms other methods, such as easy data augmentation, back translation, and multiple templates.

<iframe src="https://app.sli.do/event/532fnPQGAZvefKDC1fZsuL/embed/polls/caa91239-c9b7-44fe-aa4f-9b5022ad9486" width="300" height="400"></iframe>

LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning

Existing controllable dialogue generation work focuses on the single-attribute control and lacks generalization capability to out-of-distribution multiple attribute combinations. In this paper, we explore the compositional generalization for multi-attribute controllable dialogue generation where a model can learn from seen attribute values and generalize to unseen combinations. We propose a prompt-based disentangled controllable dialogue generation model, DCG. It learns attribute concept composition by generating attribute-oriented prompt vectors and uses a disentanglement loss to disentangle different attributes for better generalization. Besides, we design a unified reference-free evaluation framework for multiple attributes with different levels of granularities. Experiment results on two benchmarks prove the effectiveness of our method and the evaluation metric.

<iframe src="https://app.sli.do/event/1kgCXjyZMgdV89PsksaJsj/embed/polls/ad79f961-6868-4bed-a0da-9495d0f9d3a9" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

Prototype-Guided Pseudo Labeling for Semi-Supervised Text Classification

Similar lecture

Reconsidering LLM Uncertainty Estimation Methods in the Wild