Canada

Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions). While several defense techniques have been proposed, and adapted, to the discrete nature of text adversarial attacks, the benefits of general-purpose regularization methods such as label smoothing for language models, have not been studied. In this paper, we study the adversarial robustness provided by label smoothing strategies in foundational models for diverse NLP tasks in both in-domain and out-of-domain settings. Our experiments show that label smoothing significantly improves adversarial robustness in pre-trained models like BERT, against various popular attacks. We also analyze the relationship between prediction confidence and robustness, showing that label smoothing reduces over-confident errors on adversarial examples.

&lt;iframe src=&quot;https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/3eccbe55-0640-4a98-815c-28a8ac172267&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

In and Out-of-Domain Text Adversarial Robustness via Label Smoothing

machine learning

label smoothing

adversarial robustness

## Welcome to EMNLP 2022!
I am delighted to welcome you to EMNLP 2022!  I believe this conference has been complicated beyond any precedent.  Over the past year, it’s been thrilling to see the organization team approach each new puzzle with creativity and enthusiasm.  We hope that those participating in Abu Dhabi as well as those joining remotely will leave the conference feeling newly inspired by the program and newly connected to our ever-growing community.  Following EMNLP 2021 and major NLP conferences since, EMNLP 2022 is “hybrid,” serving both virtual and in-person participants.

Our key innovations for EMNLP 2022 include:

* EMNLP 2022 is “hybrid” in a second sense, as well:  we allowed both direct and rolling review paper submissions, building on the pilot experiment of EMNLP 2021, which considered a small number of ARR submissions. 
* Familiar from NAACL but new to EMNLP, we’ve added an industry track.
* During the conference, “portals” will link virtual poster sessions to in-person conference participants during poster sessions each day.
* The first ACL-family conference in the United Arab Emirates.

<br>*Message from Noah A. Smith, University of Washington and Allen Institute for AI, Seattle, Washington, USA*<br>
***EMNLP 2022 General Chair***
<br><br><br>
[![](https://assets.underline.io/uploads/markdown_image/1/image/9eec7d4a287ee18c278b08229290aa83.png)](https://drive.google.com/file/d/1OlPv6QBeo62VVTughj2jkiLeyHd1WnUt/view)
<br><br>
[![](https://assets.underline.io/uploads/markdown_image/1/image/a3db7a768409f05192210d98601edb25.png)](https://emnlp2022.rocket.chat/)



To access this site you need to register. Please register [here](https://2022.emnlp.org/registration/).

Register here

EMNLP 2022

Welcome!
EMNLP 2022 will take place in Abu Dhabi from December 7th to December 11th, 2022. And it will be held in hybrid mode, both online and offline.

Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions). While several defense techniques have been proposed, and adapted, to the discrete nature of text adversarial attacks, the benefits of general-purpose regularization methods such as label smoothing for language models, have not been studied. In this paper, we study the adversarial robustness provided by label smoothing strategies in foundational models for diverse NLP tasks in both in-domain and out-of-domain settings. Our experiments show that label smoothing significantly improves adversarial robustness in pre-trained models like BERT, against various popular attacks. We also analyze the relationship between prediction confidence and robustness, showing that label smoothing reduces over-confident errors on adversarial examples.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/3eccbe55-0640-4a98-815c-28a8ac172267" 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.

Capturing complex contextual dependencies plays a vital role in Emotion Recognition in Conversations (ERC). Previous studies have predominantly focused on speaker-aware context modeling, overlooking the discourse structure of the conversation. In this paper, we introduce Dual Graph ATtention networks (DualGATs) to concurrently consider the complementary aspects of discourse structure and speaker-aware context, aiming for more precise ERC. Specifically, we devise a Discourse-aware GAT (DisGAT) module to incorporate discourse structural information by analyzing the discourse dependencies between utterances. Additionally, we develop a Speaker-aware GAT (SpkGAT) module to incorporate speaker-aware contextual information by considering the speaker dependencies between utterances. Furthermore, we design an interaction module that facilitates the integration of the DisGAT and SpkGAT modules, enabling the effective interchange of relevant information between the two modules. We extensively evaluate our method on four datasets, and experimental results demonstrate that our proposed DualGATs surpass state-of-the-art baselines on the majority of the datasets.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/21c014e6-5b2c-440d-b2bd-c9e7fd2f41b4" width="300" height="400"></iframe>

DualGATs: Dual Graph Attention Networks for Emotion Recognition in Conversations

This paper presents Z-Code++, a new pre-trained language model optimized for abstractive text summarization. The model extends the state-of-the-art encoder-decoder model using three techniques. First, we use a two-phase pre-training to improve the model's performance on low-resource summarization tasks. The model is first pre-trained using text corpora for language understanding, then is continually pre-trained on summarization corpora for grounded text generation. Second, we replace self-attention layers in the encoder with disentangled attention layers, where each word is represented using two vectors that encode its content and position, respectively. Third, we use fusion-in-encoder, a simple yet effective method of encoding long sequences in a hierarchical manner. Z-Code++ createsa new state-of-the-art on 9 of 13 text summarization tasks across 5 languages. Our model is parameter-efficient in that it outperforms the 600x larger PaLM540B on XSum, and the finetuned 200x larger GPT3175B on SAMSum. In zero-shot and few-shot settings, our model substantially outperforms the competing models.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/7af117fe-d186-4492-9ba3-e65408478a3f" width="300" height="400"></iframe>

Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization

Compression techniques for deep learning have become increasingly popular, particularly in settings where latency and memory constraints are imposed. Several methods, such as pruning, distillation, and quantization, have been adopted for compressing models, each providing distinct advantages. However, existing literature demonstrates that compressing deep learning models could affect their fairness. Our analysis involves a comprehensive evaluation of pruned, distilled, and quantized language models, which we benchmark across a range of intrinsic and extrinsic metrics for measuring bias in text classification. We also investigate the impact of using multilingual models and evaluation measures. Our findings highlight the significance of considering both the pre-trained model and the chosen compression strategy in developing equitable language technologies. The results also indicate that compression strategies can have an adverse effect on fairness measures.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/368101ec-bfb8-4ea7-b4a9-f706269c9e22" width="300" height="400"></iframe>

A Comparative Study on the Impact of Model Compression Techniques on Fairness in Language Models

Despite the seeming success of contemporary grounded text generation systems, they often tend to generate factually inconsistent text with respect to their input.This phenomenon is emphasized in tasks like summarization, in which the generated summaries should be corroborated by their source article. In this work we leverage recent progress on textual entailment models to directly address this problem for abstractive summarization systems.We use reinforcement learning with reference-free, textual-entailment rewards to optimize for factual consistency and explore the ensuing trade-offs, as improved consistency may come at the cost of less informative or more extractive summaries.Our results, according to both automatic metrics and human evaluation, show that our method considerably improves the faithfulness, salience and conciseness of the generated summaries.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/420c9ebf-2e2b-445c-a982-44ec955b73f4" width="300" height="400"></iframe>

Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback

Video multimodal fusion aims to integrate multimodal signals in videos, such as visual, audio and text, to make a complementary prediction with multiple modalities contents.However, unlike other image-text multimodal tasks, video has longer multimodal sequences with more redundancy and noise in both visual and audio modalities.Prior denoising methods like forget gate are coarse in the granularity of noise filtering. They often suppress the redundant and noisy information at the risk of losing critical information.Therefore, we propose a denoising bottleneck fusion (DBF) model for fine-grained video multimodal fusion. On the one hand, we employ a bottleneck mechanism to filter out noise and redundancy with a restrained receptive field. On the other hand, we use a mutual information maximization module to regulate the filter-out module to preserve key information within different modalities.Our DBF model achieves significant improvement over current state-of-the-art baselines on multiple benchmarks covering multimodal sentiment analysis and multimodal summarization tasks. It proves that our model can effectively capture salient features from noisy and redundant video, audio, and text inputs.The code for this paper will be publicly available at https://github.com/WSXRHFG/DBF

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/e7d442a9-c84c-4f9f-aefa-712a784f59c9" width="300" height="400"></iframe>

Denoising Bottleneck with Mutual Information Maximization for Video Multimodal Fusion

The CoNLL-2003 English named entity recognition (NER) dataset has been widely used to train and evaluate NER models for almost 20 years. However, it is unclear how well models that are trained on this 20-year-old data and developed over a period of decades using the same test set will perform when applied on modern data. In this paper, we evaluate the generalization of over 20 different models trained on CoNLL-2003, and show that NER models have very different generalization. Surprisingly, we find no evidence of performance degradation in pre-trained Transformers, such as RoBERTa and T5, even when fine-tuned using decades-old data. We investigate why some models generalize well to new data while others do not, and attempt to disentangle the effects of temporal drift and overfitting due to test reuse. Our analysis suggests that most deterioration is due to temporal mismatch between the pre-training corpora and the downstream test sets. We found that four factors are important for good generalization: model architecture, number of parameters, time period of the pre-training corpus, in addition to the amount of fine-tuning data. We suggest current evaluation methods have, in some sense, underestimated progress on NER over the past 20 years, as NER models have not only improved on the original CoNLL-2003 test set, but improved even more on modern data. Our datasets can be found at https://github.com/ShuhengL/acl2023_conllpp.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/6d2839a3-82ef-435b-b8cb-41f8eccd6285" width="300" height="400"></iframe>

Do CoNLL-2003 Named Entity Taggers Still Work Well in 2023?

Natural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks -- malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. However, evaluations of these attacks ignore the property of imperceptibility or study it under limited settings. This entails that adversarial perturbations would not pass any human quality gate and do not represent real threats to human-checked NLP systems. To bypass this limitation and enable proper assessment (and later, improvement) of NLP model robustness, we have surveyed 378 human participants about the perceptibility of text adversarial examples produced by state-of-the-art methods. Our results underline that existing text attacks are impractical in real-world scenarios where humans are involved. This contrasts with previous smaller-scale human studies, which reported overly optimistic conclusions regarding attack success. Through our work, we hope to position human perceptibility as a first-class success criterion for text attacks, and provide guidance for research to build effective attack algorithms and, in turn, design appropriate defence mechanisms.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/c7e2e303-fe77-4d52-8a01-bc5fdf6b0630" width="300" height="400"></iframe>

How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks

Privacy concerns have attracted increasing attention in data-driven products due to the tendency of machine learning models to memorize sensitive training data. Generating synthetic versions of such data with a formal privacy guarantee, such as differential privacy (DP), provides a promising path to mitigating these privacy concerns, but previous approaches in this direction have typically failed to produce synthetic data of high quality. In this work, we show that a simple and practical recipe in the text domain is effective: simply fine-tuning a pretrained generative language model with DP enables the model to generate useful synthetic text with strong privacy protection. Through extensive empirical analyses on both benchmark and private customer data, we demonstrate that our method produces synthetic text that is competitive in terms of utility with its non-private counterpart, meanwhile providing strong protection against potential privacy leakages.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/e43ddc43-dc33-44b2-a0d8-8d21d4ca653f" width="300" height="400"></iframe>

Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe

Targeted syntactic evaluations of language models ask whether models show stable preferences for syntactically acceptable content over minimal-pair unacceptable inputs. Our best syntactic evaluation datasets, however, provide substantially less linguistic context than models receive during pretraining. This mismatch raises an important question: how robust are models' syntactic judgements across different contexts? In this paper, we vary the input contexts based on: length, the types of syntactic phenomena it contains, and whether or not there are grammatical violations. We find that model judgements are generally robust when placed in randomly sampled linguistic contexts, but are unstable when contexts match the test stimuli in syntactic structure. Among all tested models (GPT-2 and five variants of OPT), we find that model performance is affected when we provided contexts with matching syntactic structure: performance significantly improves when contexts are acceptable, and it significantly declines when they are unacceptable. This effect is amplified by the length of the context, except for unrelated inputs. We show that these changes in model performance are not explainable by acceptability-preserving syntactic perturbations. This sensitivity to highly specific syntactic features of the context can only be explained by the models' implicit in-context learning abilities.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/afea25f5-53ec-4661-ad8e-488bb63dfba3" width="300" height="400"></iframe>

Language model acceptability judgements are not always robust to context

This study presents a diverse set of freely available linguistic resources for Turkish natural language processing, including corpora, pretrained models and education material. Although Turkish is spoken by a sizeable population of over 80 million people, Turkish linguistic resources for natural language processing remain scarce. In this study, we provide corpora to allow practitioners to build their own applications and pretrained models that would assist industry researchers in creating quick prototypes. The provided corpora include named entity recognition datasets of diverse genres, including Wikipedia articles and supplement products customer reviews. In addition, crawling e-commerce and movie reviews websites, we compiled several sentiment analysis datasets of different genres. Our linguistic resources for Turkish also include pretrained spaCy language models. To the best of our knowledge, our models are the first spaCy models trained for the Turkish language. Finally, we provide various types of education material, such as video tutorials and code examples, that can support the interested audience on practicing Turkish NLP. The advantages of our linguistic resources are three-fold: they are freely available, they are first of their kind, and they are easy to use in a broad range of implementations. Along with a thorough description of the resource creation process, we also explain the position of our resources in the Turkish NLP world.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/c680138d-2fcc-45e6-b886-105cc3a162ae" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

DualGATs: Dual Graph Attention Networks for Emotion Recognition in Conversations

Similar lecture

Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation