Xu Sun

A New Recurrent Neural CRF for Learning Non-linear Edge Features

2016 · arXiv (Cornell University)

Conditional Random Field (CRF) and recurrent neural models have achieved success in structured prediction. More recently, there is a marriage of CRF and recurrent neural models, so that we can gain from both non-linear dense …

Automatic Academic Paper Rating Based on Modularized Hierarchical Convolutional Neural Network

2018 · arXiv (Cornell University)

As more and more academic papers are being submitted to conferences and journals, evaluating all these papers by professionals is time-consuming and can cause inequality due to the personal factors of the reviewers. In this …

Layer-Wise Cross-View Decoding for Sequence-to-Sequence Learning.

2020

In sequence-to-sequence learning, the decoder relies on the attention mechanism to efficiently extract information from the encoder. While it is common practice to draw information from only the last encoder layer, recent work has proposed …

Parallel Data Augmentation for Formality Style Transfer

2020 · arXiv (Cornell University)

The main barrier to progress in the task of Formality Style Transfer is the inadequacy of training data. In this paper, we study how to augment parallel data and propose novel and simple data augmentation …

Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter

2023

Federated Multilingual Neural Machine Translation (Fed-MNMT) has emerged as a promising paradigm for institutions with limited language resources. This approach allows multiple institutions to act as clients and train a unified model through model synchronization, …

DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

2024 · arXiv (Cornell University)

The visual projector, which bridges the vision and language modalities and facilitates cross-modal alignment, serves as a crucial component in MLLMs. However, measuring the effectiveness of projectors in vision-language alignment remains under-explored, which currently can …

Adaptive Zero-Crossing Regulation Algorithm for Multi-Winding Parallel-Wound Distribution TransFormers

2024

Transformer losses significantly impact grid losses. The adaptive load distribution transformer can adjust voltage taps and automatically switch operating modes based on system conditions without disconnecting the load. This reduces no-load losses, cutting grid losses …

F-Score Driven Max Margin Neural Network for Named Entity Recognition in Chinese Social Media

2017

We focus on named entity recognition (NER) for Chinese social media. With massive unlabeled text and quite limited labelled corpus, we propose a semisupervised learning model based on B-LSTM neural network. To take advantage of …

Duplicate Question Identification by Integrating FrameNet With Neural Networks

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

There are two major problems in duplicate question identification, namely lexical gap and essential constituents matching. Previous methods either design various similarity features or learn representations via neural networks, which try to solve the lexical …

Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation

2018

Existing text generation methods tend to produce repeated and "boring" expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN). The proposed model assigns low reward for …

Papers by this author

A New Recurrent Neural CRF for Learning Non-linear Edge Features

Automatic Academic Paper Rating Based on Modularized Hierarchical Convolutional Neural Network

Layer-Wise Cross-View Decoding for Sequence-to-Sequence Learning.

Parallel Data Augmentation for Formality Style Transfer

Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter

DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Adaptive Zero-Crossing Regulation Algorithm for Multi-Winding Parallel-Wound Distribution TransFormers

F-Score Driven Max Margin Neural Network for Named Entity Recognition in Chinese Social Media

Duplicate Question Identification by Integrating FrameNet With Neural Networks

Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation

A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer

Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach

Aligning Cross-Lingual Entities with Multi-Aspect Information

Asking Clarification Questions in Knowledge-Based Question Answering

A Survey on In-context Learning