Search Results for author: Shengyi Jiang

Found 22 papers, 6 papers with code

BERT 4EVER@LT-EDI-ACL2022-Detecting signs of Depression from Social Media:Detecting Depression in Social Media using Prompt-Learning and Word-Emotion Cluster

no code implementations LTEDI (ACL) 2022 Xiaotian Lin, Yingwen Fu, Ziyu Yang, Nankai Lin, Shengyi Jiang

In this paper, we report the solution of the team BERT 4EVER for the LT-EDI-2022 shared task2: Homophobia/Transphobia Detection in social media comments in ACL 2022, which aims to classify Youtube comments into one of the following categories: no, moderate, or severe depression.

text-classification Text Classification +2

How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement

1 code implementation3 Mar 2023 Xu-Hui Liu, Feng Xu, Xinyu Zhang, Tianyuan Liu, Shengyi Jiang, Ruifeng Chen, Zongzhang Zhang, Yang Yu

In this paper, we propose a novel active imitation learning framework based on a teacher-student interaction model, in which the teacher's goal is to identify the best teaching behavior and actively affect the student's learning process.

Atari Games Imitation Learning

How to choose "Good" Samples for Text Data Augmentation

no code implementations2 Feb 2023 Xiaotian Lin, Nankai Lin, Yingwen Fu, Ziyu Yang, Shengyi Jiang

In this paper, we propose a novel self-training selection framework with two selectors to select the high-quality samples from data augmentation.

Data Augmentation Semantic Similarity +3

A Chinese Spelling Check Framework Based on Reverse Contrastive Learning

no code implementations25 Oct 2022 Nankai Lin, Hongyan Wu, Sihui Fu, Shengyi Jiang, Aimin Yang

Inspired by contrastive learning, we present a novel framework for Chinese spelling checking, which consists of three modules: language representation, spelling check and reverse contrastive learning.

Contrastive Learning

An Analysis of the Differences Among Regional Varieties of Chinese in Malay Archipelago

no code implementations10 Sep 2022 Nankai Lin, Sihui Fu, Hongyan Wu, Shengyi Jiang

Chinese features prominently in the Chinese communities located in the nations of Malay Archipelago.

Subgraph Frequency Distribution Estimation using Graph Neural Networks

no code implementations14 Jul 2022 Zhongren Chen, Xinyue Xu, Shengyi Jiang, Hao Wang, Lu Mi

Small subgraphs (graphlets) are important features to describe fundamental units of a large network.

Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement Learning

no code implementations4 Jun 2022 Xue-Kun Jin, Xu-Hui Liu, Shengyi Jiang, Yang Yu

Value function estimation is an indispensable subroutine in reinforcement learning, which becomes more challenging in the offline setting.

Off-policy evaluation reinforcement-learning

A New Evaluation Method: Evaluation Data and Metrics for Chinese Grammar Error Correction

no code implementations30 Apr 2022 Nankai Lin, Xiaotian Lin, Ziyu Yang, Shengyi Jiang

In terms of the reference-based metric, we introduce sentence-level accuracy and char-level BLEU to evaluate the corrected sentences.

Chinese Word Segmentation Grammatical Error Correction +2

CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment Analysis

1 code implementation2 Apr 2022 Nankai Lin, Yingwen Fu, Xiaotian Lin, Aimin Yang, Shengyi Jiang

In the distillation XABSA task, we further explore the comparative effectiveness of different data (source dataset, translated dataset, and code-switched dataset).

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2

A Dual-Contrastive Framework for Low-Resource Cross-Lingual Named Entity Recognition

no code implementations2 Apr 2022 Yingwen Fu, Nankai Lin, Ziyu Yang, Shengyi Jiang

In this paper, we describe our novel dual-contrastive framework ConCNER for cross-lingual NER under the scenario of limited source-language labeled data.

Contrastive Learning Cross-Lingual NER +7

Multilingual Text Classification for Dravidian Languages

no code implementations3 Dec 2021 Xiaotian Lin, Nankai Lin, Kanoksak Wattanachote, Shengyi Jiang, Lianxi Wang

On the other hand, in view of the problem that the model cannot well recognize and utilize the correlation among languages, we further proposed a language-specific representation module to enrich semantic information for the model.

Multilingual text classification Multi-Task Learning +2

Cross-modal Domain Adaptation for Cost-Efficient Visual Reinforcement Learning

1 code implementation NeurIPS 2021 Xiong-Hui Chen, Shengyi Jiang, Feng Xu, Zongzhang Zhang, Yang Yu

Experiments on MuJoCo and Hand Manipulation Suite tasks show that the agents deployed with our method achieve similar performance as it has in the source domain, while those deployed with previous methods designed for same-modal domain adaptation suffer a larger performance gap.

Domain Adaptation reinforcement-learning +1

Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Network

no code implementations23 Nov 2021 Ru Peng, Nankai Lin, Yi Fang, Shengyi Jiang, Tianyong Hao, BoYu Chen, Junbo Zhao

However, succeeding researches pointed out that limited by the uncontrolled nature of attention computation, the NMT model requires an external syntax to capture the deep syntactic awareness.

Machine Translation NMT +1

LaoPLM: Pre-trained Language Models for Lao

no code implementations LREC 2022 Nankai Lin, Yingwen Fu, Chuwei Chen, Ziyu Yang, Shengyi Jiang

In this work, we construct a text classification dataset to alleviate the resource-scare situation of the Lao language.

Part-Of-Speech Tagging text-classification +1

An Open-Source Dataset and A Multi-Task Model for Malay Named Entity Recognition

no code implementations3 Sep 2021 Yingwen Fu, Nankai Lin, Zhihe Yang, Shengyi Jiang

In this work, we propose a dataset construction framework, which is based on labeled datasets of homologous languages and iterative optimization, to build a Malay NER dataset (MYNER) comprising 28, 991 sentences (over 384 thousand tokens).

Boundary Detection named-entity-recognition +2

Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization

no code implementations18 May 2021 Jing-Cheng Pang, Tian Xu, Shengyi Jiang, Yu-Ren Liu, Yang Yu

Reinforcement learning (RL) has made remarkable progress in many decision-making tasks, such as Go, game playing, and robotics control.

Atari Games Decision Making +3

Cross-Modal Domain Adaptation for Reinforcement Learning

1 code implementation1 Jan 2021 Xiong-Hui Chen, Shengyi Jiang, Feng Xu, Yang Yu

Domain adaptation is a promising direction for deploying RL agents in real-world applications, where vision-based robotics tasks constitute an important part.

Domain Adaptation reinforcement-learning +1

Offline Imitation Learning with a Misspecified Simulator

no code implementations NeurIPS 2020 Shengyi Jiang, JingCheng Pang, Yang Yu

In this work, we investigate policy learning in the condition of a few expert demonstrations and a simulator with misspecified dynamics.

Friction Imitation Learning

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