We introduce the range of oBERTa language models, an easy-to-use set
of language models which allows Natural Language Processing (NLP) practitioners to obtain between 3.8 and 24.3 times faster models without expertise in model compression. Specifically, oBERTa extends existing work on pruning, knowledge distillation, and quantization and leverages frozen embeddings, improves
distillation, and model initialization to deliver higher accuracy on a broad range of transfer tasks.

oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes
Daniel Campos, Alexandre Marques, Mark Kurtz and Cheng Xiang Zhai (dcampos3@illinois.edu)
Status: Accept

We consider the problem of improving the inference latency of language model-based dense retrieval systems by introducing structural compression and model size asymmetry between the context and query encoders. First, we investigate the impact of pre and post-training compression on the MSMARCO, Natural Questions, TriviaQA, SQUAD, and SCIFACT, finding that asymmetry in the dual-encoders in dense retrieval can lead to improved inference efficiency. Knowing this, we introduce Kullback–Leibler Alignment of Embeddings (KALE), an efficient and accurate method for increasing the inference efficiency of dense retrieval methods by pruning and aligning the query encoder after training. Specifically, KALE extends traditional Knowledge Distillation after bi-encoder training, allowing for effective query encoder compression without full retraining or index generation. Using KALE and asymmetric training, we can generate models which exceed the performance of DistilBERT despite having 3x faster inference.

Quick Dense Retrievers Consume KALE: Post Training Kullback–Leibler Alignment of Embeddings for Asymmetrical dual encoders
Daniel Campos, Alessandro Magnani and Chengxiang Zhai (dcampos3@illinois.edu)
Status: Accept

Sequence-to-sequence language models can be used to produce abstractive summaries which are coherent, relevant, and concise. Still, model sizes can make deployment in latency-sensitive or web-scale implementations difficult. This paper studies the relationship between model size, structured pruning, inference efficiency, and summarization accuracy on widely used summarization datasets. We show that model accuracy is tied to the encoder size while inference efficiency is connected to the decoder. Using asymmetric pruning can lead to nearly 3x improvement in inference latency with ~1 point loss in Rouge-2. Moreover, we find both the average degradation and the role of asymmetry to be consistent across model sizes and variations in datasets.

To Asymmetry and Beyond: Structured Pruning of Sequence to Sequence Models for Improved Inference Efficiency
Daniel Campos and ChengXiang Zhai (dcampos3@illinois.edu)
Status: Accept

The Natural Language Processing (NLP) community has, in recent years, demonstrated a notable focus on improving higher scores on standard benchmarks and taking the lead on community-wide leaderboards (e.g., GLUE, SentEval). While this aspiration has led to improvements in benchmark performance of (predominantly neural) models, it has also came at a cost, i.e., increased model complexity and the ever-growing amount of computational resources required for training and using the current state-of-the-art models. Moreover, the recent research efforts have, for the most part, failed to identify sources of empirical gains in models, often failing to empirically justify the model complexity beyond benchmark performance

Because of these easily observable trends, we have proposed the SustaiNLP workshop with the goal of promoting more sustainable NLP research and practices, with two main objectives: (1) encouraging development of more efficient NLP models; and (2) providing simpler architectures and empirical justification of model complexity. For both aspects, we will encourage submissions from all topical areas of NLP.

 For more details visit our workshop website: https://sites.google.com/view/sustainlp2023
#### [Visit GatherTown](https://app.gather.town/app/5OscLswEEuYf2Psb/ACL2023)

W6: The 4th Workshop on Simple and Efficient Natural Language Processing (SustaiNLP)

workshop paper

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
 The conference will be held in Toronto, Canada, July 9-14, 2023. 
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience. 
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**

ACL 2023

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

Daniel Campos

3

SHORT BIO

Presentations

oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes Daniel Campos, Alexandre Marques, Mark Kurtz and Cheng Xiang Zhai (dcampos3@illinois.edu) Status: Accept

Quick Dense Retrievers Consume KALE: Post Training Kullback–Leibler Alignment of Embeddings for Asymmetrical dual encoders Daniel Campos, Alessandro Magnani and Chengxiang Zhai (dcampos3@illinois.edu) Status: Accept

To Asymmetry and Beyond: Structured Pruning of Sequence to Sequence Models for Improved Inference Efficiency Daniel Campos and ChengXiang Zhai (dcampos3@illinois.edu) Status: Accept

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES