Stephen Rawls
YOU?
Author Swipe
View article: LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models
LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models Open
Large language models (LLMs) have revolutionized various domains, yet their utility comes with significant challenges related to outdated or problematic knowledge embedded during pretraining. This paper addresses the challenge of modifying…
View article: Translation-Enhanced Multilingual Text-to-Image Generation
Translation-Enhanced Multilingual Text-to-Image Generation Open
Research on text-to-image generation (TTI) still predominantly focuses on the English language due to the lack of annotated image-caption data in other languages; in the long run, this might widen inequitable access to TTI technology. In t…
View article: Visual Item Selection With Voice Assistants
Visual Item Selection With Voice Assistants Open
Interacting with voice assistants, such as Amazon Alexa to aid in day-to-day tasks has become a ubiquitous phenomenon in modern-day households. These voice assistants often have screens to provide visual content (e.g., images, videos) to t…
View article: Translation-Enhanced Multilingual Text-to-Image Generation
Translation-Enhanced Multilingual Text-to-Image Generation Open
Research on text-to-image generation (TTI) still predominantly focuses on the English language due to the lack of annotated image-caption data in other languages; in the long run, this might widen inequitable access to TTI technology. In t…
View article: Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data
Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data Open
Scaling up weakly-supervised datasets has shown to be highly effective in the\nimage-text domain and has contributed to most of the recent state-of-the-art\ncomputer vision and multimodal neural networks. However, existing large-scale\nvid…
View article: Alexa Teacher Model
Alexa Teacher Model Open
We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their applicati…
View article: AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model Open
In this work, we demonstrate that multilingual large-scale sequence-to-sequence (seq2seq) models, pre-trained on a mixture of denoising and Causal Language Modeling (CLM) tasks, are more efficient few-shot learners than decoder-only models…
View article: Multimodal Context Carryover
Multimodal Context Carryover Open
Prashan Wanigasekara, Nalin Gupta, Fan Yang, Emre Barut, Zeynab Raeesy, Kechen Qin, Stephen Rawls, Xinyue Liu, Chengwei Su, Spurthi Sandiri. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry T…
View article: Don't Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding
Don't Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding Open
Semantic parsing is one of the key components of natural language understanding systems. A successful parse transforms an input utterance to an action that is easily understood by the system. Many algorithms have been proposed to solve thi…
View article: Don’t Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding
Don’t Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding Open
Semantic parsing is one of the key components of natural language understanding systems. A successful parse transforms an input utterance to an action that is easily understood by the system. Many algorithms have been proposed to solve thi…
View article: Implicit Language Model in LSTM for OCR
Implicit Language Model in LSTM for OCR Open
Neural networks have become the technique of choice for OCR, but many aspects of how and why they deliver superior performance are still unknown. One key difference between current neural network techniques using LSTMs and the previous sta…
View article: Implicit Language Model in LSTM for OCR
Implicit Language Model in LSTM for OCR Open
Neural networks have become the technique of choice for OCR, but many aspects\nof how and why they deliver superior performance are still unknown. One key\ndifference between current neural network techniques using LSTMs and the\nprevious …
View article: Learning Document Image Binarization from Data
Learning Document Image Binarization from Data Open
In this paper we present a fully trainable binarization solution for degraded document images. Unlike previous attempts that often used simple features with a series of pre- and post-processing, our solution encodes all heuristics about wh…