United Arab Emirates

We describe an application of Knowledge Distillation used to distill and deploy multilingual Transformer models for voice assistants, enabling text classification for customers globally.Transformers have set new state-of-the-art results for tasks like intent classification, and multilingual models exploit cross-lingual transfer to allow serving requests across 100+ languages. However, their prohibitive inference time makes them impractical to deploy in real-world scenarios with low latency requirements, such as is the case of voice assistants. We address the problem of cross-architecture distillation of multilingual Transformers to simpler models, while maintaining multilinguality without performance degradation. Training multilingual student models has received little attention, and is our main focus. We show that a teacher-student framework, where the teacher&#39;s unscaled activations (logits) on unlabelled data are used to supervise student model training, enables distillation of Transformers into efficient multilingual CNN models. Our student model achieves equivalent performance as the teacher, and outperforms a similar model trained on the labelled data used to train the teacher model. This approach has enabled us to accurately serve global customer requests at speed (18x improvement), scale, and low cost.

EMNLP 2022

Distilling Multilingual Transformers into CNNs for Scalable Intent Classification

efficient models

intent classification

text classification

knowledge distillation

We describe an application of Knowledge Distillation used to distill and deploy multilingual Transformer models for voice assistants, enabling text classification for customers globally.Transformers have set new state-of-the-art results for tasks like intent classification, and multilingual models exploit cross-lingual transfer to allow serving requests across 100+ languages. However, their prohibitive inference time makes them impractical to deploy in real-world scenarios with low latency requirements, such as is the case of voice assistants. We address the problem of cross-architecture distillation of multilingual Transformers to simpler models, while maintaining multilinguality without performance degradation. Training multilingual student models has received little attention, and is our main focus. We show that a teacher-student framework, where the teacher's unscaled activations (logits) on unlabelled data are used to supervise student model training, enables distillation of Transformers into efficient multilingual CNN models. Our student model achieves equivalent performance as the teacher, and outperforms a similar model trained on the labelled data used to train the teacher model. This approach has enabled us to accurately serve global customer requests at speed (18x improvement), scale, and low cost.

technical paper

## 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.

ASR Error Detection (AED) models aim to post-process the output of Automatic Speech Recognition (ASR) systems, in order to detect transcription errors. Modern approaches usually use text-based input, comprised solely of the ASR transcription hypothesis, disregarding additional signals from the ASR model. Instead, we utilize the ASR system's word-level confidence scores for improving AED performance. Specifically, we add an ASR Confidence Embedding (ACE) layer to the AED model's encoder, allowing us to jointly encode the confidence scores and the transcribed text into a contextualized representation. Our experiments show the benefits of ASR confidence scores for AED, their complementary effect over the textual signal, as well as the effectiveness and robustness of ACE for combining these signals. To foster further research, we publish a novel AED dataset consisting of ASR outputs on the LibriSpeech corpus with annotated transcription errors.

RED-ACE: Robust Error Detection for ASR using Confidence Embeddings

Transformer-based language models (LMs) are at the core of modern NLP, but their internal prediction construction process is opaque and largely not understood. In this work, we make a substantial step towards unveiling this underlying prediction process, by reverse-engineering the operation of the feed-forward network (FFN) layers, one of the building blocks of transformer models. We view the token representation as a changing distribution over the vocabulary, and the output from each FFN layer as an additive update to that distribution. Then, we analyze the FFN updates in the vocabulary space, showing that each update can be decomposed to sub-updates corresponding to single FFN parameter vectors, each promoting concepts that are often human-interpretable. We then leverage these findings for controlling LM predictions, where we reduce the toxicity of GPT2 by almost 50%, and for improving computation efficiency with a simple early exit rule, saving 20% of computation on average.

Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space

Recent advances in federated learning have demonstrated its promising capability to learn on decentralized datasets. However, a considerable amount of work has raised concerns due to the potential risks of adversaries participating in the framework to poison the global model for an adversarial purpose. This paper investigates the feasibility of model poisoning for backdoor attacks through rare word embeddings of NLP models. In text classification, less than 1% of adversary clients suffices to manipulate the model output without any drop in the performance of clean sentences. For a less complex dataset, a mere 0.1% of adversary clients is enough to poison the global model effectively. We also propose a technique specialized in the federated learning scheme called gradient ensemble, which enhances the backdoor performance in all experimental settings.

Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensembling

A wide range of NLP tasks benefit from the fine-tuning of pretrained language models (PLMs). However, a number of redundant parameters which contribute less to the downstream task are observed in a directly fine-tuned model. We consider the gap between pretraining and downstream tasks hinders the training of these redundant parameters, and results in a suboptimal performance of the overall model. In this paper, we present PATS (Perturbation According To Sensitivity), a noisy training mechanism which considers each parameter's importance in the downstream task to help fine-tune PLMs. The main idea of PATS is to add bigger noise to parameters with lower sensitivity and vice versa, in order to activate more parameters' contributions to downstream tasks without affecting the sensitive ones much. Extensive experiments conducted on different tasks of the GLUE benchmark show PATS can consistently empower the fine-tuning of different sizes of PLMs, and the parameters in the well-performing models always have more concentrated distributions of sensitivities, which experimentally proves the effectiveness of our method.

PATS: Sensitivity-aware Noisy Learning for Pretrained Language Models

We propose a simple and effective re-ranking method for improving passage retrieval in open question answering. The re-ranker re-scores retrieved passages with a zero-shot question generation model, which uses a pre-trained language model to compute the probability of the input question conditioned on a retrieved passage. This approach can be applied on top of any retrieval method (e.g. neural or keyword-based), does not require any domain- or task-specific training (and therefore is expected to generalize better to data distribution shifts), and provides rich cross-attention between query and passage (i.e. it must explain every token in the question). When evaluated on a number of open-domain retrieval datasets, our re-ranker improves strong unsupervised retrieval models by 6%-18% absolute and strong supervised models by up to 12% in terms of top-20 passage retrieval accuracy. We also obtain new state-of-the-art results on full open-domain question answering by simply adding the new re-ranker to existing models with no further changes.

Improving Passage Retrieval with Zero-Shot Question Generation

Recent joint multiple intent detection and slot filling models employ label embeddings to achieve the semantics-label interactions.
However, they treat all labels and label embeddings as uncorrelated individuals, ignoring the dependencies among them. Besides, they conduct the decoding for the two tasks independently, without leveraging the correlations between them.
Therefore, in this paper, we first construct a Heterogeneous Label Graph (HLG) containing two kinds of topologies: (1) statistical dependencies based on labels' co-occurrence patterns and hierarchies in slot labels; (2) rich relations among the label nodes.
Then we propose a novel model termed ReLa-Net.
It can capture beneficial correlations among the labels from HLG.
The label correlations are leveraged to enhance semantic-label interactions. Moreover, we also propose the label-aware inter-dependent decoding mechanism to further exploit the label correlations for decoding. 
Experiment results show that our ReLa-Net significantly outperforms previous models.
Remarkably, ReLa-Net surpasses the previous best model by over 20\% in terms of overall accuracy on MixATIS dataset.

Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling

We present an empirical study on methods for span finding, the selection of consecutive tokens in text for some downstream tasks. We focus on approaches that can be employed in training end-to-end information extraction systems, and find there is no definitive solution without considering task properties, and provide our observations to help with future design choices: 1) a tagging approach often yields higher precision while span enumeration and boundary prediction provide higher recall; 2) span type information can benefit a boundary prediction approach; 3) additional contextualization does not help span finding in most cases.

An Empirical Study on Finding Spans

Video-grounded Dialogue (VGD) aims to decode an answer sentence to a question regarding a given video and dialogue context. Despite the recent success of multi-modal reasoning to generate answer sentences, existing dialogue systems still suffer from a text hallucination problem, which denotes indiscriminate text-copying from input texts without an understanding of the question. This is due to learning spurious correlations from the fact that answer sentences in the dataset usually include the words of input texts, thus the VGD system excessively relies on copying words from input texts by hoping those words to overlap with ground-truth texts. Hence, we design Text Hallucination Mitigating (THAM) framework, which incorporates Text Hallucination Regularization (THR) loss derived from the proposed information-theoretic text hallucination measurement approach. Applying THAM with current dialogue systems validates the effectiveness on VGD benchmarks (i.e., AVSD@DSTC7 and AVSD@DSTC8) and shows enhanced interpretability.

Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue

Currently, in speech translation, the straightforward approach - cascading a recognition system with a translation system - delivers state-of-the-art results.
However, fundamental challenges such as error propagation from the automatic speech recognition system still remain.
To mitigate these problems, recently, people turn their attention to direct data and propose various joint training methods.
In this work, we seek to answer the question of whether joint training really helps cascaded speech translation.
We review recent papers on the topic and also investigate a joint training criterion by marginalizing the transcription posterior probabilities.
Our findings show that a strong cascaded baseline can diminish any improvements obtained using joint training, and we suggest alternatives to joint training.
We hope this work can serve as a refresher of the current speech translation landscape, and motivate research in finding more efficient and creative ways to utilize the direct data for speech translation.

Does Joint Training Really Help Cascaded Speech Translation?

In this paper, we present the results of a manual classification of all ethical consideration sections for ACL 2021. We also compare how many papers had an ethics consideration section per track and per world region in ACL 2021. We classified papers according to the ethical issues covered (research benefits, potential harms, and vulnerable groups affected) and whether the paper was marked as requiring ethics review by at least one reviewer. Moreover, we discuss recurring obstacles we have observed (highlighting some interesting texts we found along the way) and conclude with three suggestions. We think that this paper may be useful for anyone who needs to write --- or review --- an ethics section and would like to get an overview of what others have done.

Distilling Multilingual Transformers into CNNs for Scalable Intent Classification

Downloads

Next from EMNLP 2022

RED-ACE: Robust Error Detection for ASR using Confidence Embeddings

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Distilling Multilingual Transformers into CNNs for Scalable Intent Classification

.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

RED-ACE: Robust Error Detection for ASR using Confidence Embeddings

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads