Lifu Tu

is this you? claim profile

0 followers
Toyota Technological Institute at Chicago

An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks

Many tasks in natural language processing involve predicting structured ...
10/06/2020 ∙ by Lifu Tu, et al. ∙ 0 ∙ share

read it
An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models

Recent work has shown that pre-trained language models such as BERT impr...
07/14/2020 ∙ by Lifu Tu, et al. ∙ 0 ∙ share

read it
ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation

We propose to train a non-autoregressive machine translation model to mi...
05/02/2020 ∙ by Lifu Tu, et al. ∙ 0 ∙ share

read it
Improving Joint Training of Inference Networks and Structured Prediction Energy Networks

Deep energy-based models are powerful, but pose challenges for learning ...
11/07/2019 ∙ by Lifu Tu, et al. ∙ 0 ∙ share

read it
Generating Diverse Story Continuations with Controllable Semantics

We propose a simple and effective modeling framework for controlled gene...
09/30/2019 ∙ by Lifu Tu, et al. ∙ 4 ∙ share

read it
Benchmarking Approximate Inference Methods for Neural Structured Prediction

Exact structured inference with neural network scoring functions is comp...
04/01/2019 ∙ by Lifu Tu, et al. ∙ 6 ∙ share

read it
Learning Approximate Inference Networks for Structured Prediction

Structured prediction energy networks (SPENs; Belanger & McCallum 2016) ...
03/09/2018 ∙ by Lifu Tu, et al. ∙ 0 ∙ share

read it
Learning to Embed Words in Context for Syntactic Tasks

We present models for embedding words in the context of surrounding word...
06/09/2017 ∙ by Lifu Tu, et al. ∙ 0 ∙ share

read it
Network Inference by Learned Node-Specific Degree Prior

We propose a novel method for network inference from partially observed ...
02/07/2016 ∙ by Qingming Tang, et al. ∙ 0 ∙ share

read it

Lifu Tu

Featured Co-authors

Dong Yu

Kevin Gimpel

Karen Livescu

Weiran Wang

Tianyu Liu

He He

Sam Wiseman

Qingming Tang

Spandana Gella

Jinbo Xu

Richard Yuanzhe Pang

An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks

An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models

ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation

Improving Joint Training of Inference Networks and Structured Prediction Energy Networks

Generating Diverse Story Continuations with Controllable Semantics

Benchmarking Approximate Inference Methods for Neural Structured Prediction

Learning Approximate Inference Networks for Structured Prediction

Learning to Embed Words in Context for Syntactic Tasks

Network Inference by Learned Node-Specific Degree Prior