United Arab Emirates

Word alignment which aims to extract lexicon translation equivalents between source and target sentences, serves as a fundamental tool for natural language processing. Recent studies in this area have yielded substantial improvements by generating alignments from contextualized embeddings of the pre-trained multilingual language models. However, we find that the existing approaches capture few interactions between the input sentence pairs, which degrades the word alignment quality severely, especially for the ambiguous words in the monolingual context. To remedy this problem, we propose Cross-Align to model deep interactions between the input sentence pairs, in which the source and target sentences are encoded separately with the shared self-attention modules in the shallow layers, while cross-lingual interactions are explicitly constructed by the cross-attention modules in the upper layers. Besides, to train our model effectively, we propose a two-stage training framework, where the model is trained with a simple Translation Language Modeling (TLM) objective in the first stage and then finetuned with a self-supervised alignment objective in the second stage. Experiments show that the proposed Cross-Align achieves the state-of-the-art (SOTA) performance on four out of five language pairs.

EMNLP 2022

Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment

cross-attention

word alignment

multilingual language models

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.

Automatic evaluation metrics are crucial to the development of generative systems. In recent years, pre-trained language model (PLM) based metrics, such as BERTScore, have been commonly adopted in various generation tasks. However, it has been demonstrated that PLMs encode a range of stereotypical societal biases, leading to a concern about the fairness of PLMs as metrics. To that end, this work presents the first systematic study on the social bias in PLM-based metrics. We demonstrate that popular PLM-based metrics exhibit significantly higher social bias than traditional metrics on 6 sensitive attributes, namely race, gender, religion, physical appearance, age, and socioeconomic status. In-depth analysis suggests that choosing paradigms (matching, regression, or generation) of the metric has a greater impact on fairness than choosing PLMs. In addition, we develop debiasing adapters that are injected into PLM layers, mitigating bias in PLM-based metrics while retaining high performance for evaluating text generation.

BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation

Hierarchical text classification (HTC) is a challenging subtask of multi-label classification due to its complex label hierarchy.
Recently, the pretrained language models (PLM)
have been widely adopted in HTC through a fine-tuning paradigm. However, in this paradigm, there exists a huge gap between the classification tasks with sophisticated label hierarchy and the masked language model (MLM) pretraining tasks of PLMs and thus the potential of PLMs cannot be fully tapped.
To bridge the gap, in this paper, we propose HPT, a Hierarchy-aware Prompt Tuning method to handle HTC from a multi-label MLM perspective.
Specifically, we construct a dynamic virtual template and label words that take the form of soft prompts to fuse the label hierarchy knowledge and introduce a zero-bounded multi-label cross-entropy loss to harmonize the objectives of HTC and MLM.
Extensive experiments show HPT achieves state-of-the-art performances on 3 popular HTC datasets and is adept at handling the imbalance and low resource situations. Our code is available at https://github.com/wzh9969/HPT.

HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification

Understanding narrative flow and text coherence in long-form documents (novels) remains an open problem in NLP.
To gain insight, we explore the task of chapter ordering, reconstructing the original order of chapters in novel given a random permutation of the text. This can be seen as extending the well-known sentence ordering task to vastly larger documents: our task deals with over 9,000 novels with an average of twenty chapters each, versus standard sentence ordering datasets averaging only 5-8 sentences. We formulate the task of reconstructing order as a constraint solving problem, using minimum feedback arc set and traveling salesman problem optimization criteria, where the weights of the graph are generated based on models for character occurrences and chapter boundary detection, using relational chapter scores derived from RoBERTa. Our best methods yield a Spearman correlation of 0.59 on this novel and challenging task, substantially above baseline.

Chapter Ordering in Novels

In educational applications, knowledge tracing refers to the problem of estimating students' time-varying concept/skill mastery level from their past responses to questions and predicting their future performance.
One key limitation of most existing knowledge tracing methods is that they treat student responses to questions as binary-valued, i.e., whether they are correct or incorrect. 
Response correctness analysis/prediction is straightforward, but it ignores important information regarding mastery, especially for open-ended questions.
In contrast, exact student responses can provide much more information.
In this paper, we conduct the first exploration int open-ended knowledge tracing (OKT) by studying the new task of predicting students' exact open-ended responses to questions.
Our work is grounded in the domain of computer science education with programming questions. 
We develop an initial solution to the OKT problem, a student knowledge-guided code generation approach, that combines program synthesis methods using language models with student knowledge tracing methods. 
We also conduct a series of quantitative and qualitative experiments on a real-world student code dataset to validate and demonstrate the promise of OKT.

Open-ended Knowledge Tracing for Computer Science Education

Recently, Sharpness-Aware Minimization (SAM) algorithm has shown state-of-the-art generalization abilities in vision tasks. It demonstrates that flat minima tend to imply better generalization abilities. However, it has some difficulty implying SAM to some natural language tasks, especially to models with drastic gradient changes, such as RNNs. In this work, we analyze the relation between the flatness of the local minimum and its generalization ability from a novel and straightforward theoretical perspective. We propose that the shift of the training and test distributions can be equivalently seen as a virtual parameter corruption or perturbation, which can explain why flat minima that are robust against parameter corruptions or perturbations have better generalization performances. On its basis, we propose a Gradient-Strength based Adaptive Sharpness-Aware Minimization (GA-SAM) algorithm to help to learn algorithms find flat minima that generalize better. Results in various language benchmarks validate the effectiveness of the proposed GA-SAM algorithm on natural language tasks.

GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization

Recent advances in distilling pretrained language models have discovered that, besides the expressiveness of knowledge, the student-friendliness should be taken into consideration to realize a truly knowledgeable teacher. Based on a pilot study, we find that over-parameterized teachers can produce expressive yet student-unfriendly knowledge and are thus limited in overall knowledgeableness. To remove the parameters that result in student-unfriendliness, we propose a sparse teacher trick under the guidance of an overall knowledgeable score for each teacher parameter. The knowledgeable score is essentially an interpolation of the expressiveness and student-friendliness scores. The aim is to ensure that the expressive parameters are retained while the student-unfriendly ones are removed. Extensive experiments on the GLUE benchmark show that the proposed sparse teachers can be dense with knowledge and lead to students with compelling performance in comparison with a series of competitive baselines.

Sparse Teachers Can Be Dense with Knowledge

Most downstream adaptation methods tune all or part of the parameters of pre-trained models (PTMs) through gradient descent, where the tuning cost increases linearly with the growth of the model size.
By contrast, gradient-free methods only require the forward computation of the PTM to tune the prompt, retaining the benefits of efficient tuning and deployment.
Though, past work on gradient-free tuning often introduces gradient descent to seek a good initialization of prompt and lacks versatility across tasks and PTMs.
In this paper, we present BBTv2, an improved version of Black-Box Tuning, to drive PTMs for few-shot learning.
We prepend continuous prompts to every layer of the PTM and propose a divide-and-conquer gradient-free algorithm to optimize the prompts at different layers alternately.
Extensive experiments across various tasks and PTMs show that BBTv2 can achieve comparable performance to full model tuning and state-of-the-art parameter-efficient methods (e.g., Adapter, LoRA, BitFit, etc.) under few-shot settings while maintaining much fewer tunable parameters.

BBTv2: Towards a Gradient-Free Future with Large Language Models

Language differs dramatically from context to context. To some degree, large language models like GPT-3 account for such variation by conditioning on strings of initial input text, or prompts. However, prompting can be ineffective when contexts are sparse, out-of-sample, or extra-textual. In this paper, we introduce the mixed-effects transformer (MET), a novel approach for learning hierarchically-structured prefixes--- lightweight modules prepended to an input sequence--- to account for structured variation in language use. Specifically, we show how the popular class of mixed-effects regression models may be extended to transformer-based architectures using a regularized prefix-tuning procedure with dropout. We evaluate this approach on several domain-adaptation benchmarks, finding that it learns contextual variation from minimal data while generalizing well to unseen contexts.

Mixed-effects transformers for hierarchical adaptation

Document images are a ubiquitous source of data where the text is organized in a complex hierarchical structure ranging from fine granularity (e.g., words), medium granularity (e.g., regions such as paragraphs or figures), to coarse granularity (e.g., the whole page). The spatial hierarchical relationships between content at different levels of granularity are crucial for document image understanding tasks. Existing methods learn features from either word-level or region-level but fail to consider both simultaneously. Word-level models are restricted by the fact that they originate from pure-text language models, which only encode the word-level context. In contrast, region-level models attempt to encode regions corresponding to paragraphs or text blocks into a single embedding, but they perform worse with additional word-level features. To deal with these issues, we propose MGDoc, a new multi-modal multi-granular pre-training framework that encodes page-level, region-level, and word-level information at the same time. MGDoc uses a unified text-visual encoder to obtain multi-modal features across different granularities, which makes it possible to project the multi-granular features into the same hyperspace. To model the region-word correlation, we design a cross-granular attention mechanism and specific pre-training tasks for our model to reinforce the model of learning the hierarchy between regions and words. Experiments demonstrate that our proposed model can learn better features that perform well across granularities and lead to improvements in downstream tasks.

MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding

Dataset bias has attracted increasing attention recently for its detrimental effect on the generalization ability of fine-tuned models. The current mainstream solution is designing an additional shallow model to pre-identify biased instances. However, such two-stage methods scale up the computational complexity of training process and obstruct valid feature information while mitigating bias.
To address this issue, we utilize the representation normalization method which aims at disentangling the correlations between features of encoded sentences. We find it also promising in eliminating the bias problem by providing isotropic data distribution. We further propose Kernel-Whitening, a Nystrom kernel approximation method to achieve more thorough debiasing on nonlinear spurious correlations. Our framework is end-to-end with similar time consumption to fine-tuning. Experiments show that Kernel-Whitening significantly improves the performance of BERT on out-of-distribution datasets while maintaining in-distribution accuracy.

Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment

Downloads

Next from EMNLP 2022

BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment

.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

BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads