Search Results for author: Yao Meng

Found 16 papers, 1 papers with code

Learning Structural Information for Syntax-Controlled Paraphrase Generation

no code implementations Findings (NAACL) 2022 Erguang Yang, Chenglin Bai, Deyi Xiong, Yujie Zhang, Yao Meng, Jinan Xu, Yufeng Chen

To model the alignment relation between words and nodes, we propose an attention regularization objective, which makes the decoder accurately select corresponding syntax nodes to guide the generation of words. Experiments show that SI-SCP achieves state-of-the-art performances in terms of semantic and syntactic quality on two popular benchmark datasets. Additionally, we propose a Syntactic Template Retriever (STR) to retrieve compatible syntactic structures.

Paraphrase Generation Relation

TaxoKnow: Taxonomy as Prior Knowledge in the Loss Function of Multi-class Classification

no code implementations24 May 2023 Mohsen Pourvali, Yao Meng, Chen Sheng, Yangzhou Du

Our obtained results show the significant effect of a taxonomy in increasing the performance of a learner in semisupervised multi-class classification and the considerable results obtained in a fully supervised fashion.

Multi-class Classification

Embrace Limited and Imperfect Training Datasets: Opportunities and Challenges in Plant Disease Recognition Using Deep Learning

no code implementations19 May 2023 Mingle Xu, Hyongsuk Kim, Jucheng Yang, Alvaro Fuentes, Yao Meng, Sook Yoon, Taehyun Kim, Dong Sun Park

We believe that our paper sheds light on the importance of embracing poor datasets, enhances the understanding of the associated challenges, and contributes to the ambitious objective of deploying deep learning in real-world applications.

A Learning-Exploring Method to Generate Diverse Paraphrases with Multi-Objective Deep Reinforcement Learning

no code implementations COLING 2020 Mingtong Liu, Erguang Yang, Deyi Xiong, Yujie Zhang, Yao Meng, Changjian Hu, Jinan Xu, Yufeng Chen

We propose a learning-exploring method to generate sentences as learning objectives from the learned data distribution, and employ reinforcement learning to combine these new learning objectives for model training.

Paraphrase Generation Reinforcement Learning (RL)

Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling

no code implementations COLING 2020 Xu Cao, Deyi Xiong, Chongyang Shi, Chao Wang, Yao Meng, Changjian Hu

Joint intent detection and slot filling has recently achieved tremendous success in advancing the performance of utterance understanding.

Intent Detection slot-filling +1

FeederGAN: Synthetic Feeder Generation via Deep Graph Adversarial Nets

no code implementations3 Apr 2020 Ming Liang, Yao Meng, Jiyu Wang, David Lubkeman, Ning Lu

This paper presents a novel, automated, generative adversarial networks (GAN) based synthetic feeder generation mechanism, abbreviated as FeederGAN.

Attribute

Detecting Concept-level Emotion Cause in Microblogging

no code implementations30 Apr 2015 Shuangyong Song, Yao Meng

In this paper, we propose a Concept-level Emotion Cause Model (CECM), instead of the mere word-level models, to discover causes of microblogging users' diversified emotions on specific hot event.

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