Search Results for author: Haoran Xu

Found 33 papers, 20 papers with code

Adaptive Bridge between Training and Inference for Dialogue Generation

no code implementations EMNLP 2021 Haoran Xu, Hainan Zhang, Yanyan Zou, Hongshen Chen, Zhuoye Ding, Yanyan Lan

Although exposure bias has been widely studied in some NLP tasks, it faces its unique challenges in dialogue response generation, the representative one-to-various generation scenario. In real human dialogue, there are many appropriate responses for the same context, not only with different expressions, but also with different topics.

Dialogue Generation NMT +1

Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles

no code implementations4 Nov 2023 Weiting Tan, Haoran Xu, Lingfeng Shen, Shuyue Stella Li, Kenton Murray, Philipp Koehn, Benjamin Van Durme, Yunmo Chen

Large language models trained primarily in a monolingual setting have demonstrated their ability to generalize to machine translation using zero- and few-shot examples with in-context learning.

Machine Translation Translation

A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models

1 code implementation20 Sep 2023 Haoran Xu, Young Jin Kim, Amr Sharaf, Hany Hassan Awadalla

In this study, we propose a novel fine-tuning approach for LLMs that is specifically designed for the translation task, eliminating the need for the abundant parallel data that traditional translation models usually depend on.

Language Modelling Machine Translation +1

Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization

1 code implementation NeurIPS 2023 Xiangsen Wang, Haoran Xu, Yinan Zheng, Xianyuan Zhan

Offline reinforcement learning (RL) has received considerable attention in recent years due to its attractive capability of learning policies from offline datasets without environmental interactions.

Management Multi-agent Reinforcement Learning +3

Offline Reinforcement Learning with Imbalanced Datasets

no code implementations6 Jul 2023 Li Jiang, Sijie Chen, JieLin Qiu, Haoran Xu, Wai Kin Chan, Zhao Ding

The prevalent use of benchmarks in current offline reinforcement learning (RL) research has led to a neglect of the imbalance of real-world dataset distributions in the development of models.

D4RL Offline RL +4

PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning

1 code implementation25 May 2023 Jianxiong Li, Xiao Hu, Haoran Xu, Jingjing Liu, Xianyuan Zhan, Ya-Qin Zhang

Offline-to-online reinforcement learning (RL), by combining the benefits of offline pretraining and online finetuning, promises enhanced sample efficiency and policy performance.

reinforcement-learning Reinforcement Learning (RL)

Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity

1 code implementation3 May 2023 Haoran Xu, Maha Elbayad, Kenton Murray, Jean Maillard, Vedanuj Goswami

Mixture-of-experts (MoE) models that employ sparse activation have demonstrated effectiveness in significantly increasing the number of parameters while maintaining low computational requirements per token.

Machine Translation Translation

Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization

2 code implementations28 Mar 2023 Haoran Xu, Li Jiang, Jianxiong Li, Zhuoran Yang, Zhaoran Wang, Victor Wai Kin Chan, Xianyuan Zhan

This gives a deeper understanding of why the in-sample learning paradigm works, i. e., it applies implicit value regularization to the policy.

D4RL Offline RL +2

Language-Aware Multilingual Machine Translation with Self-Supervised Learning

1 code implementation10 Feb 2023 Haoran Xu, Jean Maillard, Vedanuj Goswami

In this work, we first investigate how to utilize intra-distillation to learn more *language-specific* parameters and then show the importance of these language-specific parameters.

Cross-Lingual Transfer Denoising +3

Mind the Gap: Offline Policy Optimization for Imperfect Rewards

1 code implementation3 Feb 2023 Jianxiong Li, Xiao Hu, Haoran Xu, Jingjing Liu, Xianyuan Zhan, Qing-Shan Jia, Ya-Qin Zhang

RGM is formulated as a bi-level optimization problem: the upper layer optimizes a reward correction term that performs visitation distribution matching w. r. t.

Reinforcement Learning (RL)

A Policy-Guided Imitation Approach for Offline Reinforcement Learning

1 code implementation15 Oct 2022 Haoran Xu, Li Jiang, Jianxiong Li, Xianyuan Zhan

We decompose the conventional reward-maximizing policy in offline RL into a guide-policy and an execute-policy.

D4RL Offline RL +3

Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations

1 code implementation20 Jul 2022 Haoran Xu, Xianyuan Zhan, Honglei Yin, Huiling Qin

We study the problem of offline Imitation Learning (IL) where an agent aims to learn an optimal expert behavior policy without additional online environment interactions.

Imitation Learning Offline RL +1

Discriminator-Guided Model-Based Offline Imitation Learning

no code implementations1 Jul 2022 Wenjia Zhang, Haoran Xu, Haoyi Niu, Peng Cheng, Ming Li, Heming Zhang, Guyue Zhou, Xianyuan Zhan

In this paper, we propose the Discriminator-guided Model-based offline Imitation Learning (DMIL) framework, which introduces a discriminator to simultaneously distinguish the dynamics correctness and suboptimality of model rollout data against real expert demonstrations.

Imitation Learning

The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains

1 code implementation23 May 2022 Haoran Xu, Philipp Koehn, Kenton Murray

We first highlight the large sensitivity (contribution) gap among high-sensitivity and low-sensitivity parameters and show that the model generalization performance can be significantly improved after balancing the contribution of all parameters.

Machine Translation Natural Language Understanding +2

When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning

2 code implementations23 May 2022 Jianxiong Li, Xianyuan Zhan, Haoran Xu, Xiangyu Zhu, Jingjing Liu, Ya-Qin Zhang

In offline reinforcement learning (RL), one detrimental issue to policy learning is the error accumulation of deep Q function in out-of-distribution (OOD) areas.

D4RL Offline RL +2

Por Qué Não Utiliser Alla Språk? Mixed Training with Gradient Optimization in Few-Shot Cross-Lingual Transfer

1 code implementation Findings (NAACL) 2022 Haoran Xu, Kenton Murray

The current state-of-the-art for few-shot cross-lingual transfer learning first trains on abundant labeled data in the source language and then fine-tunes with a few examples on the target language, termed target-adapting.

Cross-Lingual Transfer Model Selection +2

VAE based Text Style Transfer with Pivot Words Enhancement Learning

1 code implementation ICON 2021 Haoran Xu, Sixing Lu, Zhongkai Sun, Chengyuan Ma, Chenlei Guo

Text Style Transfer (TST) aims to alter the underlying style of the source text to another specific style while keeping the same content.

Style Transfer Text Style Transfer

Adaptive Bridge between Training and Inference for Dialogue

no code implementations22 Oct 2021 Haoran Xu, Hainan Zhang, Yanyan Zou, Hongshen Chen, Zhuoye Ding, Yanyan Lan

Although exposure bias has been widely studied in some NLP tasks, it faces its unique challenges in dialogue response generation, the representative one-to-various generation scenario.

Dialogue Generation NMT +1

Offline Reinforcement Learning with Soft Behavior Regularization

no code implementations14 Oct 2021 Haoran Xu, Xianyuan Zhan, Jianxiong Li, Honglei Yin

In this work, we start from the performance difference between the learned policy and the behavior policy, we derive a new policy learning objective that can be used in the offline setting, which corresponds to the advantage function value of the behavior policy, multiplying by a state-marginal density ratio.

Continuous Control reinforcement-learning +1

Enhancing semi-supervised learning via self-interested coalitional learning

no code implementations29 Sep 2021 Huiling Qin, Xianyuan Zhan, Yuanxun li, Haoran Xu, Yu Zheng

Jointly solving these two tasks allows full utilization of information from both labeled and unlabeled data, thus alleviating the problem of over-reliance on labeled data.

BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation

2 code implementations EMNLP 2021 Haoran Xu, Benjamin Van Durme, Kenton Murray

The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation (NMT) systems.

Language Modelling Machine Translation +2

Constraints Penalized Q-learning for Safe Offline Reinforcement Learning

no code implementations19 Jul 2021 Haoran Xu, Xianyuan Zhan, Xiangyu Zhu

We study the problem of safe offline reinforcement learning (RL), the goal is to learn a policy that maximizes long-term reward while satisfying safety constraints given only offline data, without further interaction with the environment.

Offline RL Q-Learning +2

Cross-Lingual BERT Contextual Embedding Space Mapping with Isotropic and Isometric Conditions

1 code implementation19 Jul 2021 Haoran Xu, Philipp Koehn

Typically, a linearly orthogonal transformation mapping is learned by aligning static type-level embeddings to build a shared semantic space.

Model-Based Offline Planning with Trajectory Pruning

1 code implementation16 May 2021 Xianyuan Zhan, Xiangyu Zhu, Haoran Xu

The recent offline reinforcement learning (RL) studies have achieved much progress to make RL usable in real-world systems by learning policies from pre-collected datasets without environment interaction.

Offline RL Reinforcement Learning (RL)

Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation

1 code implementation EACL (AdaptNLP) 2021 Haoran Xu, Philipp Koehn

Linear embedding transformation has been shown to be effective for zero-shot cross-lingual transfer tasks and achieve surprisingly promising results.

Dependency Parsing Translation +1

Gradual Fine-Tuning for Low-Resource Domain Adaptation

2 code implementations EACL (AdaptNLP) 2021 Haoran Xu, Seth Ebner, Mahsa Yarmohammadi, Aaron Steven White, Benjamin Van Durme, Kenton Murray

Fine-tuning is known to improve NLP models by adapting an initial model trained on more plentiful but less domain-salient examples to data in a target domain.

Domain Adaptation

DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning

no code implementations23 Feb 2021 Xianyuan Zhan, Haoran Xu, Yue Zhang, Xiangyu Zhu, Honglei Yin, Yu Zheng

Optimizing the combustion efficiency of a thermal power generating unit (TPGU) is a highly challenging and critical task in the energy industry.

Continuous Control Offline RL +2

Meet Changes with Constancy: Learning Invariance in Multi-Source Translation

no code implementations COLING 2020 Jianfeng Liu, Ling Luo, Xiang Ao, Yan Song, Haoran Xu, Jian Ye

Multi-source neural machine translation aims to translate from parallel sources of information (e. g. languages, images, etc.)

Machine Translation NMT +1

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