Skip to yearly menu bar Skip to main content


Workshop

Second Workshop on Efficient Natural Language and Speech Processing (ENLSP-II)

Mehdi Rezagholizadeh ⋅ Peyman Passban ⋅ Yue Dong ⋅ Lili Mou ⋅ Pascal Poupart ⋅ Ali Ghodsi ⋅ Qun Liu
Project Page [ Contact: neurips.enlsp.2022@gmail.com ]

Abstract

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles
5:30 AM
Breakfast
5:50 AM
Opening Remarks
7:35 AM
Collective Knowledge Graph Completion with Mutual Knowledge Distillation
Weihang Zhang ⋅ Ovidiu Serban ⋅ Jiahao Sun ⋅ Yike Guo
7:45 AM
Attribute Controlled Dialogue Prompting
Runcheng Liu ⋅ Ahmad Rashid ⋅ Ivan Kobyzev ⋅ Mehdi Rezaghoizadeh ⋅ Pascal Poupart
7:56 AM
Fast DistilBERT on CPUs
Haihao Shen ⋅ Ofir Zafrir ⋅ Bo Dong ⋅ Hengyu Meng ⋅ Xinyu Ye ⋅ Zhe Wang ⋅ Yi Ding ⋅ Hanwen Chang ⋅ Guy Boudoukh ⋅ Moshe Wasserblat
10:05 AM
Efficient Few-Shot Learning Without Prompts
Oren Pereg ⋅ Daniel Korat ⋅ Moshe Wasserblat ⋅ Lewis Tunstall ⋅ Unso Eun Seo Jo ⋅ Luke Bates ⋅ Nils Reimers
12:00 PM
Interactive Industrial Panel
Jiahao Sun ⋅ Ahmed Ibrahim ⋅ Marjan Ghazvininejad ⋅ Yu Cheng ⋅ Boxing Chen ⋅ Mohammad Norouzi ⋅ Rahul Gupta
12:50 PM
Improving the Robustness of DistilHuBERT to Unseen Noisy Conditions via Data Augmentation, Curriculum Learning, and Multi-Task Enhancement
Heitor Guimarães ⋅ Arthur Pimentel ⋅ Anderson R. Avila ⋅ Mehdi Rezaghoizadeh ⋅ Tiago H Falk
12:59 PM
Gradient Knowledge Distillation for Pre-trained Language Models
Lean Wang ⋅ Lei Li ⋅ Xu Sun
Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning
Mingyu Derek Ma ⋅ Jiun-Yu Kao ⋅ Shuyang Gao ⋅ arpit gupta ⋅ Di Jin ⋅ Tagyoung Chung ⋅ Nanyun Peng
BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning
Mohsen Fayyaz ⋅ Ehsan Aghazadeh ⋅ Seyed MohammadAli Modarressi ⋅ Mohammad Taher Pilehvar ⋅ Yadollah Yaghoobzadeh ⋅ Samira Ebrahimi Kahou
Pre-Training a Graph Recurrent Network for Language Representation
Yile Wang ⋅ Linyi Yang ⋅ Zhiyang Teng ⋅ Ming Zhou ⋅ Yue Zhang
An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks
Yuxiang Wu ⋅ Yu Zhao ⋅ Baotian Hu ⋅ Pasquale Minervini ⋅ Pontus Lars Erik Saito Stenetorp ⋅ Sebastian Riedel
QuaLA-MiniLM: a Quantized Length Adaptive MiniLM
Shira Guskin ⋅ Moshe Wasserblat ⋅ Haihao Shen ⋅ Chang Wang
Towards Data Efficient And Robust Speech Representation Model Distillation
Pheobe Sun ⋅ Ruibo Shi ⋅ Ahmad Emami ⋅ Sean Moran
On Spectral and Temporal Feature Encoding Behaviour in Stacked Architectures
Vaibhav Singh ⋅ Vinayak Abrol ⋅ Karan Nathwani
Few-Shot Aspect Extraction using Prompt Training
Oren Pereg ⋅ Daniel Korat ⋅ Moshe Wasserblat ⋅ Kfir Bar
The Ineffectiveness of TKGE Models in Encoding Real-World Knowledge Graphs
Chuan Ming Ong ⋅ Jiahao Sun ⋅ Ovidiu Serban ⋅ Yike Guo
PEST: Combining Parameter-Efficient Fine-Tuning with Self-Training and Co-Training
Hunter Lang ⋅ Monica Agrawal ⋅ Yoon Kim ⋅ David Sontag
ContextNER: Contextual Phrase Generation at Scale
Himanshu Gupta ⋅ Shreyas Verma ⋅ Tarun Kumar ⋅ Swaroop Mishra ⋅ Tamanna Agrawal ⋅ Amogh Badugu ⋅ Himanshu Bhatt
Dynamic Query Representation for Extractive Question Answering
Urchade Zaratiana ⋅ Niama El Khbir ⋅ Dennis Núñez-Fernández ⋅ Pierre Holat ⋅ Nadi Tomeh ⋅ Thierry Charnois
Strategies for Applying Low Rank Decomposition to Transformer-Based Models
Habib Hajimolahoseini ⋅ Walid Ahmed ⋅ Mehdi Rezaghoizadeh ⋅ Vahid Partovi Nia ⋅ Yang Liu
DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low Rank Adaptation
Mojtaba Valipour ⋅ Mehdi Rezaghoizadeh ⋅ Ivan Kobyzev ⋅ Ali Ghodsi
Pyramid Dynamic Inference: Encouraging Faster Inference via Early Exit Boosting
Ershad Banijamali ⋅ Pegah Kharazmi ⋅ Samridhi Choudhary ⋅ Sepehr Eghbali ⋅ Clement Chung
An efficient RNN Language Model using activity sparsity and sparse back-propagation through time
Mark Schoene ⋅ Khaleelulla Khan Nazeer ⋅ David Kappel ⋅ Christian Mayr ⋅ Anand Subramoney
An Exploration of Methods for Zero-shot Transfer in Small Language Models
Alon Albalak ⋅ Akshat Shrivastava ⋅ Chinnadhurai Sankar ⋅ Adithya Sagar ⋅ Mike Ross
INT8 Transformers for Inference Acceleration
Andy Rock ⋅ Omar Khalil ⋅ Ofer Shai ⋅ Paul Grouchy
Parameter and Data Efficient Continual Pre-training for Robustness to Dialectal Variance in Arabic
Soumajyoti Sarkar ⋅ Saab Mansour ⋅ Sailik Sengupta ⋅ Sheng Zha ⋅ Kaixiang Lin
SymbolicGPT: A Generative Transformer Model for Symbolic Regression
Mojtaba Valipour ⋅ Bowen You ⋅ Maysum H Panju ⋅ Ali Ghodsi
Using Informative Data Subsets for Efficient Training of Large Language Models: An Initial Study
H S V N S Kowndinya Renduchintala ⋅ Krishnateja Killamsetty ⋅ Sumit Bhatia ⋅ Milan Aggarwal ⋅ Ganesh Ramakrishnan ⋅ Rishabh Iyer
Using Selective Masking as a Bridge between Pre-training and Fine-tuning
Tanish Lad ⋅ Himanshu Maheshwari ⋅ Shreyas Kottukkal ⋅ Radhika Mamidi
Topic Segmentation in the Wild: Towards Segmentation of Semi-structured & Unstructured Chats
Reshmi Ghosh ⋅ Sharanya Kamath ⋅ Soundararajan Srinivasan ⋅ Dhuri Shrivastava ⋅ Samyadeep Basu ⋅ Harjeet Kajal
A Theory of Unsupervised Translation for Understanding Animal Communication
Shafi Goldwasser ⋅ David Gruber ⋅ Adam Tauman Kalai ⋅ Orr Paradise
Collective Knowledge Graph Completion with Mutual Knowledge Distillation
Weihang Zhang ⋅ Ovidiu Serban ⋅ Jiahao Sun ⋅ Yike Guo
Efficient Few-Shot Learning Without Prompts
Oren Pereg ⋅ Daniel Korat ⋅ Moshe Wasserblat ⋅ Lewis Tunstall ⋅ Unso Eun Seo Jo ⋅ Luke Bates ⋅ Nils Reimers
Fast DistilBERT on CPUs
Haihao Shen ⋅ Ofir Zafrir ⋅ Bo Dong ⋅ Hengyu Meng ⋅ Xinyu Ye ⋅ Zhe Wang ⋅ Yi Ding ⋅ Hanwen Chang ⋅ Guy Boudoukh ⋅ Moshe Wasserblat
Improving the Robustness of DistilHuBERT to Unseen Noisy Conditions via Data Augmentation, Curriculum Learning, and Multi-Task Enhancement
Heitor Guimarães ⋅ Arthur Pimentel ⋅ Anderson R. Avila ⋅ Mehdi Rezaghoizadeh ⋅ Tiago H Falk
Attribute Controlled Dialogue Prompting
Runcheng Liu ⋅ Ahmad Rashid ⋅ Ivan Kobyzev ⋅ Mehdi Rezaghoizadeh ⋅ Pascal Poupart
TBD7
Kenneth Heafield