b'Xuezhe Ma'

research

∙ 05/25/2022

Know Where You're Going: Meta-Learning for Parameter-Efficient Fine-tuning

A recent family of techniques, dubbed as lightweight fine-tuning methods...

Mozhdeh Gheini, et al. ∙

research

∙ 04/29/2022

Prompt Consistency for Zero-Shot Task Generalization

One of the most impressive results of recent NLP history is the ability ...

Chunting Zhou, et al. ∙

research

∙ 02/18/2022

Learning Representations Robust to Group Shifts and Adversarial Examples

Despite the high performance achieved by deep neural networks on various...

Ming-Chang Chiu, et al. ∙

research

∙ 10/08/2021

Towards a Unified View of Parameter-Efficient Transfer Learning

Fine-tuning large pre-trained language models on downstream tasks has be...

Junxian He, et al. ∙

research

∙ 06/14/2021

Examining and Combating Spurious Features under Distribution Shift

A central goal of machine learning is to learn robust representations th...

Chunting Zhou, et al. ∙

research

∙ 06/03/2021

Luna: Linear Unified Nested Attention

The quadratic computational and memory complexities of the Transformer's...

Xuezhe Ma, et al. ∙

research

∙ 06/02/2021

COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences

Commonsense reasoning is intuitive for humans but has been a long-term c...

Shikhar Singh, et al. ∙

research

∙ 02/03/2021

DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation

Having engaging and informative conversations with users is the utmost g...

Sarik Ghazarian, et al. ∙

research

∙ 09/28/2020

Apollo: An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization

In this paper, we introduce Apollo, a quasi-Newton method for nonconvex ...

Xuezhe Ma, et al. ∙

research

∙ 09/20/2019

Cross-lingual Dependency Parsing with Unlabeled Auxiliary Languages

Cross-lingual transfer learning has become an important weapon to battle...

Wasi Uddin Ahmad, et al. ∙

research

∙ 09/05/2019

FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow

Most sequence-to-sequence (seq2seq) models are autoregressive; they gene...

Xuezhe Ma, et al. ∙

research

∙ 08/30/2019

Handling Syntactic Divergence in Low-resource Machine Translation

Despite impressive empirical successes of neural machine translation (NM...

Chunting Zhou, et al. ∙

research

∙ 05/29/2019

Choosing Transfer Languages for Cross-Lingual Learning

Cross-lingual transfer, where a high-resource transfer language is used ...

Yu-Hsiang Lin, et al. ∙

research

∙ 04/04/2019

Density Matching for Bilingual Word Embedding

Recent approaches to cross-lingual word embedding have generally been ba...

Chunting Zhou, et al. ∙

research

∙ 02/12/2019

MaCow: Masked Convolutional Generative Flow

Flow-based generative models, conceptually attractive due to tractabilit...

Xuezhe Ma, et al. ∙

research

∙ 01/06/2019

MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders

Variational Autoencoder (VAE), a simple and effective deep generative mo...

Xuezhe Ma, et al. ∙

research

∙ 11/01/2018

Near or Far, Wide Range Zero-Shot Cross-Lingual Dependency Parsing

Cross-lingual transfer is the major means toleverage knowledge from high...

Wasi Uddin Ahmad, et al. ∙

research

∙ 09/04/2018

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation

We introduce Texar, an open-source toolkit aiming to support the broad s...

Zhiting Hu, et al. ∙

research

∙ 05/03/2018

Stack-Pointer Networks for Dependency Parsing

We introduce a novel architecture for dependency parsing: stack-pointer ...

Xuezhe Ma, et al. ∙

research

∙ 05/19/2017

Softmax Q-Distribution Estimation for Structured Prediction: A Theoretical Interpretation for RAML

Reward augmented maximum likelihood (RAML), a simple and effective learn...

Xuezhe Ma, et al. ∙

research

∙ 04/19/2017

An Interpretable Knowledge Transfer Model for Knowledge Base Completion

Knowledge bases are important resources for a variety of natural languag...

Qizhe Xie, et al. ∙

research

∙ 01/04/2017

Neural Probabilistic Model for Non-projective MST Parsing

In this paper, we propose a probabilistic parsing model, which defines a...

Xuezhe Ma, et al. ∙

research

∙ 09/26/2016

Dropout with Expectation-linear Regularization

Dropout, a simple and effective way to train deep neural networks, has l...

Xuezhe Ma, et al. ∙

research

∙ 03/21/2016

Harnessing Deep Neural Networks with Logic Rules

Combining deep neural networks with structured logic rules is desirable ...

Zhiting Hu, et al. ∙

research

∙ 03/15/2016

Unsupervised Ranking Model for Entity Coreference Resolution

Coreference resolution is one of the first stages in deep language under...

Xuezhe Ma, et al. ∙

research

∙ 03/04/2016

End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

State-of-the-art sequence labeling systems traditionally require large a...

Xuezhe Ma, et al. ∙

research

∙ 02/14/2015

Probabilistic Models for High-Order Projective Dependency Parsing

This paper presents generalized probabilistic models for high-order proj...

Xuezhe Ma, et al. ∙

Xuezhe Ma

Featured Co-authors

Graham Neubig

Xiaodan Liang

Eric P Xing

Hai Zhao

Kai-Wei Chang

Luke Zettlemoyer

Di Wang

Nanyun Peng

Aram Galstyan

Eric Xing

Taylor Berg-Kirkpatrick

Know Where You're Going: Meta-Learning for Parameter-Efficient Fine-tuning

Prompt Consistency for Zero-Shot Task Generalization

Learning Representations Robust to Group Shifts and Adversarial Examples

Towards a Unified View of Parameter-Efficient Transfer Learning

Examining and Combating Spurious Features under Distribution Shift

Luna: Linear Unified Nested Attention

COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences

DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation

Apollo: An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization

Cross-lingual Dependency Parsing with Unlabeled Auxiliary Languages

FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow

Handling Syntactic Divergence in Low-resource Machine Translation

Choosing Transfer Languages for Cross-Lingual Learning

Density Matching for Bilingual Word Embedding

MaCow: Masked Convolutional Generative Flow

MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders

Near or Far, Wide Range Zero-Shot Cross-Lingual Dependency Parsing

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation

Stack-Pointer Networks for Dependency Parsing

Softmax Q-Distribution Estimation for Structured Prediction: A Theoretical Interpretation for RAML

An Interpretable Knowledge Transfer Model for Knowledge Base Completion

Neural Probabilistic Model for Non-projective MST Parsing

Dropout with Expectation-linear Regularization

Harnessing Deep Neural Networks with Logic Rules

Unsupervised Ranking Model for Entity Coreference Resolution

End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

Probabilistic Models for High-Order Projective Dependency Parsing