Xingxing Zhang

Automatic Grammatical Error Correction for Sequence-to-sequence Text Generation: An Empirical Study

2019

Sequence-to-sequence (seq2seq) models have achieved tremendous success in text generation tasks. However, there is no guarantee that they can always generate sentences without grammatical errors. In this paper, we present a preliminary empirical study on …

Memory Replay with Data Compression for Continual Learning

2022 · arXiv (Cornell University)

Continual learning needs to overcome catastrophic forgetting of the past. Memory replay of representative old training samples has been shown as an effective solution, and achieves the state-of-the-art (SOTA) performance. However, existing work is mainly …

Optimization of cloud computing task scheduling based on whale optimization algorithm with quasi-opposition-based and nonlinear factor

2024

Task scheduling has a significant impact on the resource availability and operation cost of the system in cloud computing. In order to improve the efficiency of task execution in the cloud for a given computational …

A study of the recurrent neural network encoder-decoder for large vocabulary speech recognition

2015

Deep neural networks have advanced the state-of-the-art in automatic speech recognition, when combined with hidden Markov models (HMMs). Recently there has been interest in using systems based on recurrent neural networks (RNNs) to perform sequence …

Sentence Simplification with Deep Reinforcement Learning

2017

Sentence simplification aims to make sentences easier to read and understand. Most recent approaches draw on insights from machine translation to learn simplification rewrites from monolingual corpora of complex and simple sentences. We address the …

Neural Latent Extractive Document Summarization

2018

Extractive summarization models require sentence-level labels, which are usually created heuristically (e.g., with rule-based methods) given that most summarization datasets only have document-summary pairs. Since these labels might be suboptimal, we propose a latent variable …

HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization

2019

Neural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods. Training the hierarchical encoder with these inaccurate labels is …