United Arab Emirates

Adversarial training is one of the most powerful methods to improve the robustness of pre-trained language models (PLMs). However, this approach is typically more expensive than traditional fine-tuning because of the necessity to generate adversarial examples via gradient descent. Delving into the optimization process of adversarial training, we find that robust connectivity patterns emerge in the early training phase (typically $0.15\sim0.3$ epochs), far before parameters converge. Inspired by this finding, we dig out robust early-bird tickets (i.e., subnetworks) to develop an efficient adversarial training method: (1) searching for robust tickets with structured sparsity in the early stage; (2) fine-tuning robust tickets in the remaining time. To extract the robust tickets as early as possible, we design a ticket convergence metric to automatically terminate the searching process. Experiments show that the proposed efficient adversarial training method can achieve up to $7\times \sim 13 \times$ training speedups while maintaining comparable or even better robustness compared to the most competitive state-of-the-art adversarial training methods.

EMNLP 2022

Efficient Adversarial Training with Robust Early-Bird Tickets

lottery ticket hypothesis

pretrained language models

robustness

adversarial training

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.

Entity typing aims at predicting one or more words that describe the type(s) of a specific mention in a sentence. Due to shortcuts from surface patterns to annotated entity labels and biased training, existing entity typing models are subject to the problem of spurious correlations. To comprehensively investigate the faithfulness and reliability of entity typing methods, we first systematically define distinct kinds of model biases that are reflected mainly from spurious correlations. Particularly, we identify six types of existing model biases, including mention-context bias, lexical overlapping bias, named entity bias, pronoun bias, dependency bias, and overgeneralization bias. To mitigate model biases, we then introduce a counterfactual data augmentation method. By augmenting the original training set with their debiased
counterparts, models are forced to fully comprehend sentences and discover the fundamental cues for entity typing, rather than relying on spurious correlations for shortcuts. Experimental results on the UFET dataset show our counterfactual data augmentation approach helps improve generalization of different entity typing models with consistently better performance on both the original and debiased test sets.

Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing

Neural retrieval models have superseded classic bag-of-words methods such as BM25 as the retrieval framework of choice. However, neural systems lack the interpretability of bag-of-words models; it is not trivial to connect a query change to a change in the latent space that ultimately determines the retrieval results. To shed light on this embedding space, we learn a "query decoder" that, given a latent representation of a neural search engine, generates the corresponding query. We show that it is possible to decode a meaningful query from its latent representation and, when moving in the right direction in latent space, to decode a query that retrieves the relevant paragraph. In particular, the query decoder can be useful to understand "what should have been asked" to retrieve a particular paragraph from the collection. We employ the query decoder to generate a large synthetic dataset of query reformulations for MSMarco, leading to improved retrieval performance. On this data, we train a pseudo-relevance feedback (PRF) T5 model for the application of query suggestion that outperforms both query reformulation and PRF information retrieval baselines.

Decoding a Neural Retriever's Latent Space for Query Suggestion

Parsing natural language questions into executable logical forms is a useful and interpretable way to perform question answering on structured data such as knowledge bases (KB) or databases (DB). 
However, existing approaches on semantic parsing cannot adapt to both modalities, as they suffer from the exponential growth of the logical form candidates and can hardly generalize to unseen data.
In this work, we propose Uni-Parser, a unified semantic parser for question answering (QA) on both KB and DB. We define the primitive (relation and entity in KB, and table name, column name and cell value in DB) as the essential element in our framework. The number of primitives grows only at a linear rate to the number of retrieved relations in KB and DB, preventing us from exponential logic form candidates. 
We leverage the generator to predict final logical forms by altering and composing top-ranked primitives with different operations (e.g. select, where, count). With sufficiently pruned search space by a contrastive primitive ranker, the generator is empowered to capture the composition of primitives enhancing its generalization ability. We achieve competitive results on multiple KB and DB QA benchmarks with more efficiency, especially in the compositional and zero-shot settings.

Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database

On vision-language understanding (VLU) tasks, fusion-encoder vision-language models achieve superior results but sacrifice efficiency because of the simultaneous encoding of images and text. On the contrary, the dual encoder model that separately encodes images and text has the advantage in efficiency, while failing on VLU tasks due to the lack of deep cross-modal interactions. To get the best of both worlds, we propose DiDE, a framework that distills the knowledge of the fusion-encoder teacher model into the dual-encoder student model. Since the cross-modal interaction is the key to the superior performance of teacher model but is absent in the student model, we encourage the student not only to mimic the predictions of teacher, but also to calculate the cross-modal attention distributions and align with the teacher. Experimental results demonstrate that DiDE is competitive with the fusion-encoder teacher model in performance (only a 1% drop) while enjoying 4 times faster inference. Further analyses reveal that the proposed cross-modal attention distillation is crucial to the success of our framework.

Distilled Dual-Encoder Model for Vision-Language Understanding

Automatic topic classification has been studied extensively to assist managing and indexing scientific documents in a digital collection. With the large number of topics being available in recent years, it has become necessary to arrange them in a hierarchy. Therefore, the automatic classification systems need to be able to classify the documents hierarchically. In addition, each paper is often assigned to more than one relevant topic. For example, a paper can be assigned to several topics in a hierarchy tree. In this paper, we introduce a new dataset for hierarchical multi-label text classification (HMLTC) of scientific papers called SciHTC, which contains 186,160 papers and 1,234 categories from the ACM CCS tree. We establish strong baselines for HMLTC and propose a multi-task learning approach for topic classification with keyword labeling as an auxiliary task. Our best model achieves a Macro-F1 score of 34.57% which shows that this dataset provides significant research opportunities on hierarchical scientific topic classification. We make our dataset and code for all experiments publicly available.

Hierarchical Multi-Label Classification of Scientific Documents

In this paper, we introduce the task of modeling interpersonal relationships for story generation. For addressing this task, we propose Relationships as Latent Variables for Story Generation, (ReLiSt). ReLiSt generates stories sentence by sentence and has two major components - a relationship selector and a story continuer. The relationship selector specifies a latent variable to pick the relationship to exhibit in the next sentence and the story continuer generates the next sentence while expressing the selected relationship in a coherent way. Our automatic and human evaluations demonstrate that ReLiSt is able to generate stories with relationships that are more faithful to desired relationships while maintaining the content quality. The relationship assignments to sentences during inference brings interpretability to ReLiSt.

Towards Inter-character Relationship-driven Story Generation

Knowledge Distillation (KD) is an effective method to transfer knowledge from one network (a.k.a. teacher) to another (a.k.a. student). In this paper, we study KD on the emotion-related tasks from a new perspective: calibration. We further explore the impact of the mixup data augmentation technique on the distillation objective and propose to use a simple yet effective mixup method informed by training dynamics for calibrating the student models. Underpinned by the regularization impact of the mixup process by providing better training signals to the student models using training dynamics, our proposed mixup strategy gradually enhances the student model's calibration while effectively improving its performance. We evaluate the calibration of pre-trained language models through knowledge distillation over three tasks of emotion detection, sentiment analysis, and empathy detection. By conducting extensive experiments on different datasets, with both in-domain and out-of-domain test sets, we demonstrate that student models distilled from teacher models trained using our proposed mixup method obtained the lowest Expected Calibration Errors (ECEs) and best performance on both in-domain and out-of-domain test sets.

Calibrating Student Models for Emotion-related Tasks

Extracting entities, events, event arguments, and relations (i.e., task instances) from text represents four main challenging tasks in information extraction (IE), which have been solved jointly (JointIE) to boost the overall performance for IE. As such, previous work often leverages two types of dependencies between the tasks, i.e., cross-instance and cross-type dependencies representing relatedness between task instances and correlations between information types of the tasks. However, the cross-task dependencies in prior work are not optimal as they are only designed manually according to some task heuristics. To address this issue, we propose a novel model for JointIE that aims to learn cross-task dependencies from data. In particular, we treat each task instance as a node in a dependency graph where edges between the instances are inferred through information from different layers of a pretrained language model (e.g., BERT). Furthermore, we utilize the Chow-Liu algorithm to learn a dependency tree between information types for JointIE by seeking to approximate the joint distribution of the types from data. Finally, the Chow-Liu dependency tree is used to generate cross-type patterns, serving as anchor knowledge to guide the learning of representations and dependencies between instances for JointIE. Experimental results show that our proposed model significantly outperforms strong JointIE baselines over four datasets with different languages.

Learning Cross-Task Dependencies for Joint Extraction of Entities, Events, Event Arguments, and Relations

Building pretrained language models is considered expensive and data-intensive, but must we increase dataset size to achieve better performance? We propose an alternative to larger training sets by automatically identifying smaller yet domain-representative subsets. We extend Cynical Data Selection, a statistical sentence scoring method that conditions on a representative target domain corpus. As an example, we treat the OntoNotes corpus as a target domain and pretrain a RoBERTa-like encoder from a cynically selected subset of the Pile. On both perplexity and across several downstream tasks in the target domain, it consistently outperforms random selection with 20x less data, 3x fewer training iterations, and 2x less estimated cloud compute cost, validating the recipe of automatic document selection for LM pretraining.

Automatic Document Selection for Efficient Encoder Pretraining

Natural Language Processing (NLP) models are found to exhibit discriminatory stereotypes across many social constructs, e.g. gender and race. In comparison to the progress made in reducing bias from static word embeddings, fairness in sentence-level text encoders received little consideration despite their wider applicability in contemporary NLP tasks. In this paper, we propose a debiasing method for pre-trained text encoders that both reduces social stereotypes, and inflicts next to no semantic damage. Unlike previous studies that directly manipulate the embeddings, we suggest to dive deeper into the operation of these encoders, and pay more attention to the way they pay attention to different social groups. We find that stereotypes are also encoded in the attention layer. Then, we work on model debiasing by redistributing the attention scores of a text encoder such that it forgets any preference to historically advantaged groups, and attends to all social classes with the same intensity. Our experiments confirm that reducing bias from attention effectively mitigates it from the model's text representations.

Efficient Adversarial Training with Robust Early-Bird Tickets

Downloads

Next from EMNLP 2022

Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Efficient Adversarial Training with Robust Early-Bird Tickets

.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

Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads