Dominican Republic

Dynamic early exiting aims to accelerate the inference of pre-trained language models (PLMs) by emitting predictions in internal layers without passing through the entire model.
In this paper, we empirically analyze the working mechanism of dynamic early exiting and find that it faces a performance bottleneck under high speed-up ratios. 
On one hand, the PLMs&#39; representations in shallow layers lack high-level semantic information and thus are not sufficient for accurate predictions. 
On the other hand, the exiting decisions made by internal classifiers are unreliable, leading to wrongly emitted early predictions.
We instead propose a new framework for accelerating the inference of PLMs, CascadeBERT, which dynamically selects proper-sized and complete models in a cascading manner, providing comprehensive representations for predictions. 
We further devise a difficulty-aware objective, encouraging the model to output the class probability that reflects the real difficulty of each instance for a more reliable cascading mechanism.
Experimental results show that CascadeBERT can achieve an overall 15% improvement under 4x speed-up compared with existing dynamic early exiting methods on six classification tasks, yielding more calibrated and accurate predictions.

EMNLP 2021

{C}ascade{BERT}: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible. The experience for on-site participants would closely approximate a normal pre-COVID *ACL conference, with 5-6 thematically organized parallel sessions and live Q/A and interactive discussion immediately after the talks. Presentations by virtual participants will be equitably interleaved with those of on-site participants, projected on the auditorium screens as if on-site, and also followed immediately by live Q/A and interactive discussion at a time during reasonable waking hours for the virtual presenter. For all participants, on-site and virtual, who are unable to attend a session due to either time-zone issues or because they are participating in another session live, talk recordings and slides will be available online at a minimum after the live presentation (and in many cases before as well), and questions may be submitted in advance on session-specific discussion boards and answered live in session with the usual visual aids if desired.

<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/ceby/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>

Please Note: The EMNLP registration system is not currently connected to the underline site as we are still in the process of building out EMNLP 2021. You will receive access instructions from underline the week of November 1st. 

Access is given only to EMNLP upon registration, if you have not registered please do so [here](https://2021.emnlp.org/registration).

Registered attendees will receive access the week of November 1st.

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible.

Dynamic early exiting aims to accelerate the inference of pre-trained language models (PLMs) by emitting predictions in internal layers without passing through the entire model.
In this paper, we empirically analyze the working mechanism of dynamic early exiting and find that it faces a performance bottleneck under high speed-up ratios. 
On one hand, the PLMs' representations in shallow layers lack high-level semantic information and thus are not sufficient for accurate predictions. 
On the other hand, the exiting decisions made by internal classifiers are unreliable, leading to wrongly emitted early predictions.
We instead propose a new framework for accelerating the inference of PLMs, CascadeBERT, which dynamically selects proper-sized and complete models in a cascading manner, providing comprehensive representations for predictions. 
We further devise a difficulty-aware objective, encouraging the model to output the class probability that reflects the real difficulty of each instance for a more reliable cascading mechanism.
Experimental results show that CascadeBERT can achieve an overall 15% improvement under 4x speed-up compared with existing dynamic early exiting methods on six classification tasks, yielding more calibrated and accurate predictions.

technical paper

Knowledge Distillation (KD) is a model compression algorithm that helps transfer the knowledge in a large neural network into a smaller one. Even though KD has shown promise on a wide range of Natural Language Processing (NLP) applications, little is understood about how one KD algorithm compares to another and whether these approaches can be complimentary to each other.
In this work, we evaluate various KD algorithms on in-domain, out-of-domain and adversarial testing. We propose a framework to assess adversarial robustness of multiple KD algorithms. Moreover, we introduce a new KD algorithm, Combined-KD, which takes advantage of two promising approaches (better training scheme and more efficient data augmentation). Our extensive experimental results show that Combined-KD achieves state-of-the-art results on the GLUE benchmark, out-of-domain generalization, and adversarial robustness compared to competitive methods.

How to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding

Biomedical entity linking is the task of linking entity mentions in a biomedical document to referent entities in a knowledge base. Recently, many BERT-based models have been introduced for the task. While these models achieve competitive results on many datasets, they are computationally expensive and contain about 110M parameters. Little is known about the factors contributing to their impressive performance and whether the over-parameterization is needed. In this work, we shed some light on the inner workings of these large BERT-based models. Through a set of probing experiments, we have found that the entity linking performance only changes slightly when the input word order is shuffled or when the attention scope is limited to a fixed window size. From these observations, we propose an efficient convolutional neural network with residual connections for biomedical entity linking. Because of the sparse connectivity and weight sharing properties, our model has a small number of parameters and is highly efficient. On five public datasets, our model achieves comparable or even better linking accuracy than the state-of-the-art BERT-based models while having about 60 times fewer parameters.

BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks

Numeracy plays a key role in natural language understanding. However, existing NLP approaches, not only traditional word2vec approach or contextualized transformer-based language models, fail to learn numeracy. As the result, the performance of these models is limited when they are applied to number-intensive applications in clinical and financial domains. In this work, we propose a simple number embedding approach based on knowledge graph. We construct a knowledge graph consisting of number entities and magnitude relations. Knowledge graph embedding method is then applied to obtain number vectors. Our approach is easy to implement, and experiment results on various numeracy-related NLP tasks demonstrate the effectiveness and efficiency of our method.

Learning Numeracy: A Simple Yet Effective Number Embedding Approach Using Knowledge Graph

Non-autoregressive machine translation (NAT) approaches enable fast generation by utilizing parallelizable generative processes. The remaining bottleneck in these models is their decoder layers; unfortunately unlike in autoregressive models (Kasai et al., 2020), removing decoder layers from NAT models significantly degrades accuracy. This work proposes a sequence-to-lattice model that replaces the decoder with a search lattice. Our approach first constructs a candidate lattice using efficient lookup operations, generates lattice scores from a deep encoder, and finally finds the best path using dynamic programming. Experiments on three machine translation datasets show that our method is faster than past non-autoregressive generation approaches, and more accurate than naively reducing the number of decoder layers.

Sequence-to-Lattice Models for Fast Translation

Computational models of human language often involve combinatorial problems. For instance, a probabilistic parser may marginalize over exponentially many trees to make predictions. Algorithms for such problems often employ dynamic programming and are not always unique. Finding one with optimal asymptotic runtime can be unintuitive, time-consuming, and error-prone. Our work aims to automate this laborious process. Given an initial correct declarative program, we search for a sequence of semantics-preserving transformations to improve its running time as much as possible. To this end, we describe a set of program transformations, a simple metric for assessing the efficiency of a transformed program, and a heuristic search procedure to improve this metric. We show that in practice, automated search—like the mental search performed by human programmers—can find substantial improvements to the initial program. Empirically, we show that many speed-ups described in the NLP literature could have been discovered automatically by our system.

Searching for More Efficient Dynamic Programs

Improving Transformer efficiency has become increasingly attractive recently. A wide range of methods has been proposed, e.g., pruning, quantization, new architectures and etc. But these methods are either sophisticated in implementation or dependent on hardware. In this paper, we show that the efficiency of Transformer can be improved by combining some simple and hardware-agnostic methods, including tuning hyper-parameters, better design choices and training strategies. On the WMT news translation tasks, we improve the inference efficiency of a strong Transformer system by 3.80x on CPU and 2.52x on GPU.

Bag of Tricks for Optimizing Transformer Efficiency

Contextual language models have led to significantly better results, especially when pre-trained on the same data as the downstream task. While this additional pre-training usually improves performance, it can lead to information leakage and therefore risks the privacy of individuals mentioned in the training data. One method to guarantee the privacy of such individuals is to train a differentially-private language model, but this usually comes at the expense of model performance. Also, in the absence of a differentially private vocabulary training, it is not possible to modify the vocabulary to fit the new data, which might further degrade results. In this work we bridge these gaps, and provide guidance to future researchers and practitioners on how to improve privacy while maintaining good model performance. We introduce a novel differentially private word-piece algorithm, which allows training a tailored domain-specific vocabulary while maintaining privacy. We then experiment with entity extraction tasks from clinical notes, and demonstrate how to train a differentially private pre-trained language model (i.e., BERT) with a privacy guarantee of $\epsilon=1.1$ and with only a small degradation in performance. Finally, as it is hard to tell given a privacy parameter $\epsilon$ what was the effect on the trained representation, we present experiments showing that the trained model does not memorize private information.

Learning and Evaluating a Differentially Private Pre-trained Language Model

Recent works have found evidence of gender bias in models of machine translation and coreference resolution using mostly synthetic diagnostic datasets. While these quantify bias in a controlled experiment, they often do so on a small scale and consist mostly of artificial, out-of-distribution sentences.
In this work, we find grammatical patterns indicating stereotypical and non-stereotypical gender-role assignments (e.g., female nurses versus male dancers) in corpora from three domains, resulting in a first large-scale gender bias dataset of 108K diverse real-world English sentences.
We manually verify the quality of our corpus and use it to evaluate gender bias in various coreference resolution and machine translation models. We find that all tested models tend to over-rely on gender stereotypes when presented with natural inputs, which may be especially harmful when deployed in commercial systems.
Finally, we show that our dataset lends itself to finetuning a coreference resolution model, finding it mitigates bias on a held out set.
Our dataset and models are publicly available at github.com/SLAB-NLP/BUG. We hope they will spur future research into gender bias evaluation mitigation techniques in realistic settings.

Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation

Much of the world's population experiences some form of disability during their lifetime. Caution must be exercised while designing natural language processing (NLP) systems to prevent systems from inadvertently perpetuating ableist bias against people with disabilities, i.e., prejudice that favors those with typical abilities. We report on various analyses based on word predictions of a large-scale BERT language model. Statistically significant results demonstrate that people with disabilities can be disadvantaged. Findings also explore overlapping forms of discrimination related to interconnected gender and race identities.

Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens

With the recent surge in social applications relying on knowledge graphs, the need for techniques to ensure fairness in KG based methods is becoming increasingly evident. Previous works have demonstrated that KGs are prone to various social biases, and have proposed multiple methods for debiasing them. However, in such studies, the focus has been on debiasing techniques, while the relations to be debiased are specified manually by the user. As manual specification is itself susceptible to human cognitive bias, there is a need for a system capable of quantifying and exposing biases, that can support more informed decisions on what to debias. To address this gap in the literature, we describe a framework for identifying biases present in knowledge graph embeddings, based on numerical bias metrics. We illustrate the framework with three different bias measures on the task of profession prediction, and it can be flexibly extended to further bias definitions and applications. The relations flagged as biased can then be handed to decision makers for judgement upon subsequent debiasing.

{C}ascade{BERT}: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade

Downloads

Next from EMNLP 2021

How to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding

Similar lecture

ArabicTransformer: Efficient Large Arabic Language Model with Funnel Transformer and ELECTRA Objective

{C}ascade{BERT}: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade

.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 2021

How to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding

Similar lecture

ArabicTransformer: Efficient Large Arabic Language Model with Funnel Transformer and ELECTRA Objective

Downloads