Hi, I'm Ralph.


I'm passionate about machine learning, natural language processing, computer vision, speech processing, and statistics. Research-wise, I've driven the creative vision and technical direction for my 20+ first-author papers, winning a best paper award at ACL 2023 and an outstanding paper award at EMNLP 2024. Engineering-wise, I've led and implemented AI language technology systems serving 20 million+ daily queries, receiving two companywide innovation awards at Comcast.

I've served as a reviewer for AAAI, AACL-IJCNLP, ACL, COLM, EACL, EMNLP Industry, and NAACL, as well as an area chair for ACL. My curriculum vitae has more details.

Papers and Talks

2024
Multilingual Pretraining Using a Large Corpus Machine-Translated from a Single Source Language
Jiayi Wang, Yao Lu, Maurice Weber, Max Ryabinin, Yihong Chen, Raphael Tang, Pontus Stenetorp
arXiv
Systems and Methods for Processing Voice Queries of a Different Duration
Raphael Tang, Karun Kumar, Kendra Chalkley, G. Craig Murray, Ferhan Ture
US Patent App. 18/193,212
Systems and Methods for Improved Automatic Speech Recognition Systems
Raphael Tang, Karun Kumar, Kendra Chalkley, ..., G. Craig Murray
US Patent App. 18/066,174
Words Worth a Thousand Pictures: Measuring and Understanding Perceptual Variability in Text-to-Image Generation
Raphael Tang, Xinyu Zhang, Lixinyu Xu, Yao Lu, Wenyan Li, Pontus Stenetorp, Jimmy Lin, Ferhan Ture
EMNLP 2024 (Outstanding Paper Award)
FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture
Wenyan Li, Xinyu Zhang, Jiaang Li, Qiwei Peng, Raphael Tang, ..., Anders Søgaard, Daniel Herschcovich, Desmond Elliott
EMNLP 2024
Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning
Wenyan Li, Jiaang Li, Rita Ramos, Raphael Tang, Desmond Elliott
ACL 2024
"Ask Me Anything": How Comcast Uses LLMs to Assist Agents in Real Time
Scott Rome, Tianwen Chen, Raphael Tang, Luwei Zhou, Ferhan Ture
SIGIR Industry 2024
Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models
Raphael Tang*, Xinyu Zhang*, Xueguang Ma, Jimmy Lin, Ferhan Ture
NAACL 2024
*Equal contribution.
Strings from the Library of Babel: Random Sampling as a Strong Baseline for Prompt Optimisation
Yao Lu, Jiayi Wang, Raphael Tang, Sebastian Riedel, Pontus Stenetorp
NAACL 2024
2023
Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models
Xinyu Zhang, Sebastian Hofstatter, Patrick Lewis, Raphael Tang, Jimmy Lin
arXiv
What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations
Raphael Tang, Xinyu Zhang, Jimmy Lin, Ferhan Ture
arXiv
Methods and Systems for Voice Control
Raphael Tang, Karun Kumar, ..., G. Craig Murray
US Patent App. 17/566,036
What the DAAM: Interpreting Stable Diffusion Using Cross Attention
Raphael Tang*, Linqing Liu*, Akshat Pandey, ..., Karun Kumar, Pontus Stenetorp, Jimmy Lin, Ferhan Ture
ACL 2023 (Best Paper Award)
*Equal contribution.
Operator Selection and Ordering in a Pipeline Approach to Efficiency Optimizations for Transformers
Ji Xin, Raphael Tang, Zhiying Jiang, Yaoliang Yu, Jimmy Lin
ACL 2023 Findings
"Low-Resource" Text Classification: A Parameter-Free Classification Method with Compressors
Zhiying Jiang, Matthew Y. R. Yang, Mikhail Tsirlin, Raphael Tang, Yiqin Dai, Jimmy Lin
ACL 2023 Findings
Comcast SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale
Raphael Tang
Snorkel FDCAI 2023
Predictive Query Execution
Raphael Tang, Karun Kumar, ..., G. Craig Murray
US Patent App. 17/454,234
2022
Systems and Methods for Improved Automatic Speech Recognition Systems
Raphael Tang, Karun Kumar, ..., Craig Murray
Filed US Patent
SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale
Raphael Tang, Karun Kumar, Gefei Yang, Akshat Pandey, ..., Craig Murray, Ferhan Ture, Jimmy Lin
EMNLP 2022 Industry
Temporal Early Exiting for Streaming Speech Commands Recognition
Raphael Tang, Karun Kumar, ..., G. Craig Murray, Jimmy Lin
ICASSP 2022
2021
How Does BERT Rerank Passages? An Attribution Analysis with Information Bottlenecks
Zhiying Jiang, Raphael Tang, Ji Xin, Jimmy Lin
EMNLP 2021 BlackboxNLP Workshop
Voice Query Auto Completion
Raphael Tang, Karun Kumar, Kendra Chalkley, Ji Xin, ..., G. Craig Murray, Jimmy Lin
EMNLP 2021 (Oral)
The Art of Abstention: Selective Prediction and Error Regularization for Natural Language Processing
Ji Xin, Raphael Tang, Yaoliang Yu, Jimmy Lin
ACL-IJCNLP 2021
BERxiT: Early Exiting for *BERT with Better Fine-Tuning and Extension to Regression
Ji Xin, Raphael Tang, Yaoliang Yu, Jimmy Lin
EACL 2021
2020
Inserting Information Bottlenecks for Attribution in Transformers
Zhiying Jiang, Raphael Tang, Ji Xin, Jimmy Lin
EMNLP 2020 Findings
Howl: A Deployed, Open-Source Wake Word Detection System
Raphael Tang*, Jaejun Lee*, Afsaneh Razi, Julia Cambre, Ian Bicking, Jofish Kaye, Jimmy Lin
EMNLP 2020 NLPOSS Workshop
*Equal contribution.
Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset
Edwin Zhang, Nikhil Gupta, Raphael Tang, ..., Kyunghyun Cho, Hui Fang, Jimmy Lin
EMNLP 2020 SDP Workshop
Exploring the Limits of Simple Learners in Knowledge Distillation for Document Classification
Ashutosh Adhikari, Achyudh Ram, Raphael Tang, Jimmy Lin
ACL 2020 Repl4NLP Workshop
Showing Your Work Doesn't Always Work
Raphael Tang, Jaejun Lee, Ji Xin, Xinyu Liu, Yaoliang Yu, Jimmy Lin
ACL 2020
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
Ji Xin, Raphael Tang, Jaejun Lee, Yaoliang Yu, Jimmy Lin
ACL 2020
Rapidly Bootstrapping a Question Answering Dataset for COVID-19
Raphael Tang, ..., Phuong Cam, Kyunghyun Cho, Jimmy Lin
arXiv
2019
Machine Learning for Streamflow Prediction: Current Status and Future Prospects
Martin Gauch, Raphael Tang, Juliane Mai, Bryan Tolson, Shervan Gharari, Jimmy Lin
AGU Fall Meeting 2019
The Runoff Model-Intercomparison Project over Lake Erie and the Great Lakes
Juliane Mai, ..., Jimmy Lin, Raphael Tang
AGU Fall Meeting 2019
What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning
Jaejun Lee, Raphael Tang, Jimmy Lin
arXiv
Explicit Pairwise Word Interaction Modeling Improves Pretrained Transformers for English Semantic Similarity Tasks
Yinan Zhang, Raphael Tang, Jimmy Lin
arXiv
Natural Language Generation for Effective Knowledge Distillation
Raphael Tang, Yao Lu, Jimmy Lin
EMNLP-IJCNLP 2019 DeepLo Workshop
Incorporating Contextual and Syntactic Structures Improves Semantic Similarity Modeling
Linqing Liu, Wei Yang, Jinfeng Rao, Raphael Tang, Jimmy Lin
EMNLP-IJCNLP 2019 (Oral)
Honkling: In-Browser Personalization for Ubiquitous Keyword Spotting
Jaejun Lee, Raphael Tang, Jimmy Lin
EMNLP-IJCNLP 2019 Demo
Challenges and Opportunities in Understanding Spoken Queries Directed at Modern Entertainment Platforms
Ferhan Ture, Jinfeng Rao, Raphael Tang, Jimmy Lin
SIGIR Industry 2019
DocBERT: BERT for Document Classification
Ashutosh Adhikari, Achyudh Ram, Raphael Tang, Jimmy Lin
arXiv
Distilling Task-Specific Knowledge from BERT into Simple Neural Networks
Raphael Tang*, Yao Lu*, Linqing Liu*, Lili Mou, Olga Vechtomova, Jimmy Lin
arXiv
*Equal contribution.
Yelling at Your TV: An Analysis of Speech Recognition Errors and Subsequent User Behavior on Entertainment Systems
Raphael Tang, Ferhan Ture, Jimmy Lin
SIGIR 2019
Universal Voice-Enabled User Interfaces using JavaScript
Jaejun Lee, Raphael Tang, Jimmy Lin
IUI 2019 Demo
Rethinking Complex Neural Network Architectures for Document Classification
Ashutosh Adhikari*, Achyudh Ram*, Raphael Tang, Jimmy Lin
NAACL 2019 (Oral)
*Equal contribution.
2018
Streaming Voice Query Recognition Using Causal Convolutional Recurrent Neural Networks
Raphael Tang, Gefei Yang, Hong Wei, Yajie Mao, Ferhan Ture, Jimmy Lin
arXiv
FLOPs as a Direct Optimization Objective for Learning Sparse Neural Networks
Raphael Tang, Ashutosh Adhikari, Jimmy Lin
NIPS 2018 Workshop on Compact Deep Neural Networks with Industrial Applications
Progress and Tradeoffs in Neural Language Models
Raphael Tang, Jimmy Lin
arXiv
JavaScript Convolutional Neural Networks for Keyword Spotting in the Browser: An Experimental Analysis
Jaejun Lee, Raphael Tang, Jimmy Lin
arXiv
Adaptive Pruning of Neural Language Models for Mobile Devices
Raphael Tang, Jimmy Lin
arXiv
An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting
Raphael Tang, Weijie Wang, Zhucheng Tu, Jimmy Lin
ICASSP 2018
Deep Residual Learning for Small-Footprint Keyword Spotting
Raphael Tang, Jimmy Lin
ICASSP 2018
2017
Honk: A PyTorch Reimplementation of Convolutional Neural Networks for Keyword Spotting
Raphael Tang, Jimmy Lin
arXiv


Projects