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.
no code implementations • 30 Mar 2023 • Nankai Lin, Hongbin Zhang, Menglan Shen, Yu Wang, Shengyi Jiang, Aimin Yang
Grammatical error correction (GEC) is a challenging task of natural language processing techniques.
1 code implementation • 3 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.
no code implementations • 2 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.
no code implementations • 25 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.
no code implementations • 10 Sep 2022 • Nankai Lin, Sihui Fu, Hongyan Wu, Shengyi Jiang
Chinese features prominently in the Chinese communities located in the nations of Malay Archipelago.
no code implementations • 14 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.
no code implementations • 4 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.
no code implementations • 30 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.
no code implementations • 6 Apr 2022 • Yingwen Fu, Jinyi Chen, Nankai Lin, Xixuan Huang, Xinying Qiu, Shengyi Jiang
The Yunshan Cup 2020 track focused on creating a framework for evaluating different methods of part-of-speech (POS).
1 code implementation • 2 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
no code implementations • 2 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.
no code implementations • 3 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.
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.
no code implementations • 23 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.
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.
no code implementations • 3 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).
no code implementations • 18 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.
1 code implementation • NeurIPS 2021 • Xu-Hui Liu, Zhenghai Xue, Jing-Cheng Pang, Shengyi Jiang, Feng Xu, Yang Yu
In reinforcement learning, experience replay stores past samples for further reuse.
1 code implementation • 1 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.
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.
1 code implementation • 15 Jan 2020 • Zhenyu Xuan, Rui Bao, Shengyi Jiang
Except for adding glyph information, this method may also add extra interactive information with the fusion mechanism.
Ranked #2 on Chinese Named Entity Recognition on Resume NER
Chinese Named Entity Recognition named-entity-recognition +3