22 citations · 51 across the 10 of their papers we have counts for
10 papers
Structure-Aware Fill-in-the-Middle Pretraining for Code
Linyuan Gong, Alvin Cheung, Mostafa Elhoushi +1
Fill-in-the-Middle (FIM) is a common pretraining method for code LLMs, where models complete code segments given surrounding context. However, existing LLMs treat code as plain tex…
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
Linyuan Gong, Sida Wang, Mostafa Elhoushi +1
We introduce Syntax-Aware Fill-In-the-Middle (SAFIM), a new benchmark for evaluating Large Language Models (LLMs) on the code Fill-in-the-Middle (FIM) task. This benchmark focuses…
AST-T5: Structure-Aware Pretraining for Code Generation and Understanding
Linyuan Gong, Mostafa Elhoushi, Alvin Cheung
Large language models (LLMs) have made significant advancements in code-related tasks, yet many LLMs treat code as simple sequences, neglecting its structured nature. We introduce…
Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers
Linyuan Gong, Chenyan Xiong, Xiaodong Liu +5
This paper explores the effectiveness of model-generated signals in improving zero-shot generalization of text-to-text Transformers such as T5. We study various designs to pretrain…
ADELT: Transpilation Between Deep Learning Frameworks
Linyuan Gong, Jiayi Wang, Alvin Cheung
We propose the Adversarial DEep Learning Transpiler (ADELT), a novel approach to source-to-source transpilation between deep learning frameworks. ADELT uniquely decouples code skel…
Joint Language Semantic and Structure Embedding for Knowledge Graph Completion
Jianhao Shen, Chenguang Wang, Linyuan Gong +1
The task of completing knowledge triplets has broad downstream applications. Both structural and semantic information plays an important role in knowledge graph completion. Unlike…
Anytime Sampling for Autoregressive Models via Ordered Autoencoding
Yilun Xu, Yang Song, Sahaj Garg +4
Autoregressive models are widely used for tasks such as image and audio generation. The sampling process of these models, however, does not allow interruptions and cannot adapt to…
MC-BERT: Efficient Language Pre-Training via a Meta Controller
Zhenhui Xu, Linyuan Gong, Guolin Ke +5
Pre-trained contextual representations (e.g., BERT) have become the foundation to achieve state-of-the-art results on many NLP tasks. However, large-scale pre-training is computati…
Microsoft Research Asia's Systems for WMT19
Yingce Xia, Xu Tan, Fei Tian +11
We Microsoft Research Asia made submissions to 11 language directions in the WMT19 news translation tasks. We won the first place for 8 of the 11 directions and the second place fo…
What Does a TextCNN Learn?
Linyuan Gong, Ruyi Ji
TextCNN, the convolutional neural network for text, is a useful deep learning algorithm for sentence classification tasks such as sentiment analysis and question classification. Ho…