Search Results for author: Lifu Tu

Found 14 papers, 6 papers with code

Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP

no code implementations27 Aug 2021 Lifu Tu

In this dissertation, we discuss the concept of the energy function and structured models with different energy functions.

Representation Learning Structured Prediction

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

1 code implementation EMNLP 2020 Lifu Tu, Tianyu Liu, Kevin Gimpel

Many tasks in natural language processing involve predicting structured outputs, e. g., sequence labeling, semantic role labeling, parsing, and machine translation.

Machine Translation Representation Learning +2

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

1 code implementation14 Jul 2020 Lifu Tu, Garima Lalwani, Spandana Gella, He He

Recent work has shown that pre-trained language models such as BERT improve robustness to spurious correlations in the dataset.

Multi-Task Learning Natural Language Inference +1

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

1 code implementation ACL 2020 Lifu Tu, Richard Yuanzhe Pang, Sam Wiseman, Kevin Gimpel

We propose to train a non-autoregressive machine translation model to minimize the energy defined by a pretrained autoregressive model.

Machine Translation Translation

Generating Diverse Story Continuations with Controllable Semantics

no code implementations WS 2019 Lifu Tu, Xiaoan Ding, Dong Yu, Kevin Gimpel

We propose a simple and effective modeling framework for controlled generation of multiple, diverse outputs.

Benchmarking Approximate Inference Methods for Neural Structured Prediction

1 code implementation NAACL 2019 Lifu Tu, Kevin Gimpel

One approach is to perform gradient descent with respect to the output structure directly (Belanger and McCallum, 2016).

Structured Prediction

Learning Approximate Inference Networks for Structured Prediction

3 code implementations ICLR 2018 Lifu Tu, Kevin Gimpel

Prior work used gradient descent for inference, relaxing the structured output to a set of continuous variables and then optimizing the energy with respect to them.

Language Modelling Multi-Label Classification +2

Network Inference by Learned Node-Specific Degree Prior

no code implementations7 Feb 2016 Qingming Tang, Lifu Tu, Weiran Wang, Jinbo Xu

We propose a novel method for network inference from partially observed edges using a node-specific degree prior.

Matrix Completion

Cannot find the paper you are looking for? You can Submit a new open access paper.