United Arab Emirates

Pre-trained language models have achieved remarkable successes in natural language processing tasks, coming at the cost of increasing model size. To address this issue, knowledge distillation (KD) has been widely applied to compress language models. However, typical KD approaches for language models have overlooked the difficulty of training examples, suffering from incorrect teacher prediction transfer and sub-efficient training. In this paper, we propose a novel KD framework, Tutor-KD, which improves the distillation effectiveness by controlling the difficulty of training examples during pre-training. We introduce a tutor network that generates samples that are easy for the teacher but difficult for the student, with training on a carefully designed policy gradient method. Experimental results show that Tutor-KD significantly and consistently outperforms the state-of-the-art KD methods with variously sized student models on the GLUE benchmark, demonstrating that the tutor can effectively generate training examples for the student.

EMNLP 2022

Tutoring Helps Students Learn Better: Improving Knowledge Distillation for BERT with Tutor Network

efficient learning

compression

language model

knowledge distillation

poster

## 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.

Instead of using a single ground truth for language processing tasks, several recent studies have examined how to represent and predict the labels of the set of annotators. However, often little or no information about annotators is known, or the set of annotators is small. In this work, we examine a corpus of social media posts about conflict from a set of 13k annotators and 210k judgements of social norms. We provide a novel experimental setup that applies personalization methods to the modeling of annotators and compare their effectiveness for predicting the perception of social norms. We further provide an analysis of performance across subsets of social situations that vary by the closeness of the relationship between parties in conflict, and assess where personalization helps the most.

Unifying Data Perspectivism and Personalization: An Application to Social Norms

Debiasing language models from unwanted behaviors in Natural Language Understanding (NLU) tasks is a topic with rapidly increasing interest in the NLP community. Spurious statistical correlations in the data allow models to perform shortcuts and avoid uncovering more advanced and desirable linguistic features.
A multitude of effective debiasing approaches has been proposed, but flexibility remains a major issue. For the most part, models must be retrained to find a new set of weights with debiased behavior.
We propose a new debiasing method in which we identify debiased pruning masks that can be applied to a finetuned model. This enables the selective and conditional application of debiasing behaviors.
We assume that bias is caused by a certain subset of weights in the network; our method is, in essence, a mask search to identify and remove biased weights.
Our masks show equivalent or superior performance to the standard counterparts, while offering important benefits.
Pruning masks can be stored with high efficiency in memory, and it becomes possible to switch among several debiasing behaviors (or revert back to the original biased model) at inference time. Finally, it opens the doors to further research on how biases are acquired by studying the generated masks. For example, we observed that the early layers and attention heads were pruned more aggressively, possibly hinting towards the location in which biases may be encoded.

Debiasing Masks: A New Framework for Shortcut Mitigation in NLU

Existing summarization datasets come with two main drawbacks: 
(1) They tend to focus on overly exposed domains, such as news articles or wiki-like texts, and 
(2) are primarily monolingual, with few multilingual datasets.
In this work, we propose a novel dataset, called EUR-Lex-Sum, based on manually curated document summaries of legal acts from the European Union law platform (EUR-Lex). Documents and their respective summaries exist as cross-lingual paragraph-aligned data in several of the 24 official European languages, enabling access to various cross-lingual and lower-resourced summarization setups. We obtain up to 1,500 document/summary pairs per language, including a subset of 375 cross-lingually aligned legal acts with texts available in *all* 24 languages. 
In this work, the data acquisition process is detailed and key characteristics of the resource are compared to existing summarization resources. In particular, we illustrate challenging sub-problems and open questions on the dataset that could help the facilitation of future research in the direction of domain-specific cross-lingual summarization.
Limited by the extreme length and language diversity of samples, we further conduct experiments with suitable extractive monolingual and cross-lingual baselines for future work. 
Code for the extraction as well as access to our data and baselines is available online at: [https://github.com/achouhan93/eur-lex-sum](https://github.com/achouhan93/eur-lex-sum).

EUR-Lex-Sum: A Multi- and Cross-lingual Dataset for Long-form Summarization in the Legal Domain

Massively multilingual models are promising for transfer learning across tasks and languages. However, existing methods are unable to fully leverage training data when it is available in different task-language combinations. To exploit such heterogeneous supervision, we propose Hyper-X, a single hypernetwork that unifies multi-task and multilingual learning with efficient adaptation. It generates weights for adapter modules conditioned on both tasks and language embeddings. By learning to combine task and language-specific knowledge, our model enables zero-shot transfer for unseen languages and task-language combinations. Our experiments on a diverse set of languages demonstrate that Hyper-X achieves the best or competitive gain when a mixture of multiple resources is available, while on par with strong baseline in the standard scenario. Hyper-X is also considerably more efficient in terms of parameters and resources compared to methods that train separate adapters. Finally, Hyper-X consistently produces strong results in few-shot scenarios for new languages, showing the versatility of our approach beyond zero-shot transfer.

Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer

Most Outside-Knowledge Visual Question Answering (OK-VQA) systems employ a two-stage framework that first retrieves external knowledge given the visual question and then predicts the answer based on the retrieved content. However, the retrieved knowledge is often inadequate. Retrievals are frequently too general and fail to cover specific knowledge needed to answer the question. Also, the naturally available supervision (whether the passage contains the correct answer) is weak and does not guarantee question relevancy. To address these issues, we propose an Entity-Focused Retrieval (EnFoRe) model that provides stronger supervision during training and recognizes question-relevant entities to help retrieve more specific knowledge. Experiments show that our EnFoRe model achieves superior retrieval performance on OK-VQA, the currently largest outside-knowledge VQA dataset. We also combine the retrieved knowledge with state-of-the-art VQA models, and achieve a new state-of-the-art performance on OK-VQA.

Entity-Focused Dense Passage Retrieval for Outside-Knowledge Visual Question Answering

In this paper, we look at the case of a Generic text-to-text NMT model that has to deal with data coming from various modalities, like speech, images, or noisy text extracted from the web. We propose a two-step method, based on composable adapters, to deal with this problem of Multimodal Robustness. In a first step, we separately learn domain adapters and modality specific adapters, to deal with noisy input coming from various sources: ASR, OCR, or noisy text (UGC). In a second step, we combine these components at runtime via dynamic routing or, when the source of noise is unknown, via two new transfer learning mechanisms (Fast Fusion and Multi Fusion). We show that our method provides a flexible, state-of-the-art, architecture able to deal with noisy multimodal inputs.

Multimodal Robustness for Neural Machine Translation

Medical term normalization consists in mapping a piece of text to a large number of output classes.
Given the small size of the annotated datasets and the extremely long tail distribution of the concepts, it is of utmost importance to develop models that are capable to generalize to scarce or unseen concepts.
An important attribute of most target ontologies is their hierarchical structure. In this paper we introduce a simple and effective learning strategy that leverages such information to enhance the generalizability of both discriminative and generative models.
The evaluation shows that the proposed strategy produces state-of-the-art performance on seen concepts and consistent improvements on unseen ones, allowing also for efficient zero-shot knowledge transfer across text typologies and datasets.

Generalizing over Long Tail Concepts for Medical Term Normalization

Trainable evaluation metrics for machine translation (MT) exhibit strong correlation with human judgements, but they are often hard to interpret and might produce unreliable scores 
under noisy or out-of-domain data. 
Recent work has attempted to mitigate this with simple uncertainty quantification techniques (Monte Carlo dropout and deep ensembles), however these techniques (as we show) are limited in several ways – for example, they are unable to distinguish between different kinds of uncertainty, and they are time and memory consuming. 
In this paper, we propose more powerful and efficient uncertainty predictors for MT evaluation, and we assess their ability to target different sources of aleatoric and epistemic uncertainty. 
To this end, we develop and compare training objectives for the COMET metric to enhance it with an uncertainty prediction output, including heteroscedastic regression, divergence minimization, and direct uncertainty prediction.
Our experiments show improved results on uncertainty prediction for the WMT metrics task datasets, with a substantial reduction in computational costs. Moreover, they demonstrate the ability of these predictors to address specific uncertainty causes in MT evaluation, such as low quality references and 
out-of-domain data.

Disentangling Uncertainty in Machine Translation Evaluation

Knowledge about outcomes is critical for complex event understanding but is hard to acquire.
We show that by pre-identifying a participant in a complex event, crowdworkers are able
to (1) infer the collective impact of salient events that make up the situation, (2) annotate the volitional engagement of participants in causing the situation, and (3) ground the
outcome of the situation in state changes of the participants. By creating a multi-step interface and a careful quality control strategy, we collect a high quality annotated dataset of
8K short newswire narratives and ROCStories with high inter-annotator agreement (0.74-0.96
weighted Fleiss Kappa). Our dataset, POQue (Participant Outcome Questions), enables the
exploration and development of models that address multiple aspects of semantic understanding. Experimentally, we show that current language models lag behind human performance in subtle ways through our task formulations that target abstract and specific comprehension of a complex event, its outcome, and a participant's influence over the event culmination.

POQue: Asking Participant-specific Outcome Questions for a Deeper Understanding of Complex Events

Unwanted and often harmful social biases are becoming ever more salient in NLP research, affecting both models and datasets. In this work, we ask whether training on demographically perturbed data leads to fairer language models. We collect a large dataset of human annotated text perturbations and train a neural perturbation model, which we show outperforms heuristic alternatives. We find that (i) language models (LMs) pre-trained on demographically perturbed corpora are typically more fair, and (ii) LMs finetuned on perturbed GLUE datasets exhibit less demographic bias on downstream tasks, and (iii) fairness improvements do not come at the expense of performance on downstream tasks. Lastly, we discuss outstanding questions about how best to evaluate the (un)fairness of large language models. We hope that this exploration of neural demographic perturbation will help drive more improvement towards fairer NLP.

Tutoring Helps Students Learn Better: Improving Knowledge Distillation for BERT with Tutor Network

Downloads

Next from EMNLP 2022

Unifying Data Perspectivism and Personalization: An Application to Social Norms

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Tutoring Helps Students Learn Better: Improving Knowledge Distillation for BERT with Tutor Network

.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

Unifying Data Perspectivism and Personalization: An Application to Social Norms

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads