United Arab Emirates

Model compression by way of parameter pruning, quantization, or distillation has recently gained popularity as an approach for reducing the computational requirements of modern deep neural network models for NLP. Inspired by prior works suggesting a connection between simpler, more generalizable models and those that lie within wider loss basins, we hypothesize that optimizing for flat minima should lead to simpler parameterizations and thus more compressible models. We propose to combine sharpness-aware minimization (SAM) with various task-specific model compression methods, including iterative magnitude pruning (IMP), structured pruning with a distillation objective, and post-training dynamic quantization. Empirically, we show that optimizing for flatter minima consistently leads to greater compressibility of parameters compared to vanilla Adam when fine-tuning BERT models, with little to no loss in accuracy on the GLUE text classification and SQuAD question answering benchmarks. Moreover, SAM finds superior winning tickets during IMP that 1) are amenable to vanilla Adam optimization, and 2) transfer more effectively across tasks.

EMNLP 2022

Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models

iterative magnitude pruning

lottery ticket

flat minima

sharpness aware minimization

train flat

structured pruning

lottery ticket hypothesis

compression

quantization

distillation

pruning

## 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.

 *Message from Noah A. Smith, University of Washington and Allen Institute for AI, Seattle, Washington, USA* 
***EMNLP 2022 General Chair***
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/9eec7d4a287ee18c278b08229290aa83.png)](https://drive.google.com/file/d/1OlPv6QBeo62VVTughj2jkiLeyHd1WnUt/view)
 
[![](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

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.

findings / work in progress

Knowledge Distillation (KD) is a commonly used technique for improving the generalization of compact Pre-trained Language Models (PLMs) on downstream tasks. However, such methods impose the additional burden of training a separate teacher model for every new dataset.
Alternatively, one may directly work on the improvement of the optimization procedure of the compact model towards better generalization. Recent works observe that the flatness of the local minimum correlates well with better generalization.
In this work, we adapt Stochastic Weight Averaging (SWA), a method encouraging convergence to a flatter minimum, to fine-tuning PLMs. We conduct extensive experiments on various NLP tasks (text classification, question answering, and generation) and different model architectures and demonstrate that our adaptation improves the generalization without extra computation cost. Moreover, we observe that this simple optimization technique is able to outperform the state-of-the-art KD methods for compact models.

Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging

Language models pre-trained on large self-supervised corpora, followed by task-specific fine-tuning has become the dominant paradigm in NLP. These pre-training datasets often have a one-to-many structure---e.g. in dialogue there are many valid responses for a given context. However, only some of these responses will be desirable in our downstream task. This raises the question of how we should train the model such that it can emulate the desirable behaviours, but not the undesirable ones. Current approaches train in a one-to-one setup---only a single target response is given for a single dialogue context---leading to models only learning to predict the average response, while ignoring the full range of possible responses. Using text-based games as a testbed, our approach, PASA, uses discrete latent variables to capture the range of different behaviours represented in our larger pre-training dataset. We then use knowledge distillation to distil the posterior probability distribution into a student model. This probability distribution is far richer than learning from only the hard targets of the dataset, and thus allows the student model to benefit from the richer range of actions the teacher model has learned. Results show up to 49\% empirical improvement over the previous state-of-the-art model on the Jericho Walkthroughs dataset.

Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games

A growing body of research has demonstrated the inability of NLP models to generalize compositionally and has tried to alleviate it through specialized architectures, training schemes, and data augmentation, among other approaches. In this work, we study a different approach: training on instances with diverse structures. We propose a model-agnostic algorithm for subsampling such sets of instances from a labeled instance pool with structured outputs. Evaluating on both compositional template splits and traditional IID splits of 5 semantic parsing datasets of varying complexity, we show that structurally diverse training using our algorithm leads to comparable or better generalization than prior algorithms in 9 out of 10 dataset-split type pairs. In general, we find structural diversity to consistently improve sample efficiency compared to random train sets. Moreover, we show that structurally diverse sampling yields comprehensive test sets that are a lot more challenging than IID test sets. Finally, we provide two explanations for improved generalization from diverse train sets: 1) improved coverage of output substructures, and 2) a reduction in spurious correlations between these substructures.

Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive Evaluation

Word embedding aims to learn the dense representation of words and has become a regular input preparation in many NLP tasks. Due to the data and computation intensive nature of learning embeddings from scratch, a more affordable way is to borrow the pretrained embedding available in public and fine-tune the embedding through a domain specific downstream dataset. A privacy concern can arise if a malicious owner of the pretrained embedding gets access to the fine-tuned embedding and tries to infer the critical information from the downstream datasets. In this study, we propose a novel embedding inversion framework called Invernet that materializes the privacy concern by inferring the context distribution in the downstream dataset, which can lead to key information breach. With extensive experimental studies on two real-world news datasets: Antonio Gulli's News and New York Times, we validate the feasibility of proposed privacy attack and demonstrate the effectiveness of Invernet on inferring downstream datasets based on multiple word embedding methods.

Invernet: An Inversion Attack Framework to Infer Fine-Tuning Datasets through Word Embeddings

How can we protect the intellectual property of trained NLP models? Modern NLP models are prone to stealing by querying and distilling from their publicly exposed APIs. However, existing protection methods such as watermarking only work for images but are not applicable to text. We propose Distillation-Resistant Watermarking (DRW), a novel technique to protect NLP models from being stolen via distillation. DRW protects a model by injecting watermarks into the victim's prediction probability corresponding to a secret key and is able to detect such a key by probing a suspect model. We prove that a protected model still retains the original accuracy within a certain bound. We evaluate DRW on a diverse set of NLP tasks including text classification, part-of-speech tagging, and named entity recognition. Experiments show that DRW protects the original model and detects stealing suspects at 100% mean average precision for all four tasks while the prior method fails on two.

Distillation-Resistant Watermarking for Model Protection in NLP

While counterfactual data augmentation offers a promising step towards robust generalization in natural language processing, producing a set of counterfactuals that offer valuable inductive bias for models remains a challenge. Most existing approaches for producing counterfactuals, manual or automated, rely on small perturbations via minimal edits, resulting in simplistic changes. We introduce NeuroCounterfactuals, designed as loose counterfactuals, allowing for larger edits which result in naturalistic generations containing linguistic diversity, while still bearing similarity to the original document. Our novel generative approach bridges the benefits of constrained decoding, with those of language model adaptation for sentiment steering. Training data augmentation with our generations results in both in-domain and out-of-domain improvements for sentiment classification, outperforming even manually curated counterfactuals, under select settings. We further present detailed analyses to show the advantages of NeuroCounterfactuals over approaches involving simple, minimal edits.

NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation

Transformer-based pre-trained models are known to encode societal biases not only in their contextual representations, but also in downstream predictions when fine-tuned on task-specific data.
We present D-Bias, an approach that selectively eliminates stereotypical associations (e.g, co-occurrence statistics) at fine-tuning, such that the model doesn't learn to excessively rely on those signals.
D-Bias attenuates biases from both identity words and frequently co-occurring proxies, which we select using pointwise mutual information.
We apply D-Bias to a) occupation classification, and b) toxicity classification and find that our approach substantially reduces downstream biases (e.g. by > 60% in toxicity classification, for identities that are most frequently flagged as toxic on online platforms).
In addition, we show that D-Bias dramatically improves upon scrubbing, i.e., removing only the identity words in question.
We also demonstrate that D-Bias easily extends to multiple identities, and achieves competitive performance with two recently proposed debiasing approaches: R-LACE and INLP.

Don't Just Clean It, Proxy Clean It: Mitigating Bias by Proxy in Pre-Trained Models

Natural language inference (NLI) is critical in many domains requiring complex decision-making, such as the biomedical domain. We introduce a novel semi-supervised procedure that bootstraps biomedical NLI datasets from positive entailment examples present in abstracts of biomedical publications. We focus on challenging texts where the hypothesis includes mechanistic information such as biochemical interactions between two entities. A key contribution of this work is automating the creation of negative examples that are informative without being simplistic. We generate a range of negative examples using nine strategies that manipulate the structure of the underlying mechanisms both with rules, e.g., flip the roles of the entities in the interaction, and, more importantly, by imposing the perturbed conditions as logical constraints in a neuro-logical decoding system \cite{lu-etal-2021-neurologic}.
We use this procedure to create a novel dataset for NLI in the biomedical domain, called \dataset. The accuracy of neural classifiers on this dataset is in the mid 70s F1, which indicates that this NLI task remains to be solved. Critically, we observe that the performance on the different classes of negative examples varies widely, from 97\% F1 on the simple negative examples that change the role of the entities in the hypothesis, to barely better than chance on the negative examples generated using neuro-logic decoding.

BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples

Conversations on social media tend to go off-topic and turn into different and sometimes toxic exchanges. Previous work focuses on analysing textual dialogues that have derailed into toxic content, but the range of derailment types is much broader, including spam or bot content, tangential comments, etc. In addition, existing work disregards conversations that involve visual information (i.e. images or videos), which are prevalent on most platforms. In this paper, we take a broader view of conversation derailment and propose a new challenge: detecting derailment based on the "change of conversation topic", where the topic is defined by an initial post containing both a text and an image. For that, we (i) create the first Multimodal Conversation Derailment (MCD) dataset, and (ii) introduce a new multimodal conversational architecture (MMConv) that utilises visual and conversational contexts to classify comments for derailment. Experiments show that MMConv substantially outperforms previous text-based approaches to detect conversation derailment, as well as general multimodal classifiers. MMConv is also more robust to textual noise, since it relies on richer contextual information.

Multimodal Conversation Modelling for Topic Derailment Detection

Construction of human-curated annotated datasets for abstractive text summarization (ATS) is very time-consuming and expensive because creating each instance requires a human annotator to read a long document and compose a shorter summary that would preserve the key information relayed by the original document. Active Learning (AL) is a technique developed to reduce the amount of annotation required to achieve a certain level of machine learning model performance. In information extraction and text classification, AL can reduce the amount of labor up to multiple times. Despite its potential for aiding expensive annotation, as far as we know, there were no effective AL query strategies for ATS. This stems from the fact that many AL strategies rely on uncertainty estimation, while as we show in our work, uncertain instances are usually noisy, and selecting them can degrade the model performance compared to passive annotation. We address this problem by proposing the first effective query strategy for AL in ATS based on diversity principles. We show that given a certain annotation budget, using our strategy in AL annotation helps to improve the model performance in terms of ROUGE and consistency scores. Additionally, we analyze the effect of self-learning and show that it can additionally increase the performance of the model.

Downloads

Next from EMNLP 2022

Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging

Similar lecture

Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models

.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 EMNLP 2022

Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging

Similar lecture

Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models

Downloads