Cheng-Jie Sun

Also published as: Chengjie Sun


pdf bib
ITNLP2022 at SemEval-2022 Task 8: Pre-trained Model with Data Augmentation and Voting for Multilingual News Similarity
Zhongan Chen | Weiwei Chen | YunLong Sun | Hongqing Xu | Shuzhe Zhou | Bohan Chen | Chengjie Sun | Yuanchao Liu
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

This article introduces a system to solve the SemEval 2022 Task 8: Multilingual News Article Similarity. The task focuses on the consistency of events reported in two news articles. The system consists of a pre-trained model(e.g., INFOXLM and XLM-RoBERTa) to extract multilingual news features, following fully-connected networks to measure the similarity. In addition, data augmentation and Ten Fold Voting are used to enhance the model. Our final submitted model is an ensemble of three base models, with a Pearson value of 0.784 on the test dataset.

pdf bib
How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis
Shaobo Li | Xiaoguang Li | Lifeng Shang | Zhenhua Dong | Chengjie Sun | Bingquan Liu | Zhenzhou Ji | Xin Jiang | Qun Liu
Findings of the Association for Computational Linguistics: ACL 2022

Recently, there has been a trend to investigate the factual knowledge captured by Pre-trained Language Models (PLMs). Many works show the PLMs’ ability to fill in the missing factual words in cloze-style prompts such as ”Dante was born in [MASK].” However, it is still a mystery how PLMs generate the results correctly: relying on effective clues or shortcut patterns? We try to answer this question by a causal-inspired analysis that quantitatively measures and evaluates the word-level patterns that PLMs depend on to generate the missing words. We check the words that have three typical associations with the missing words: knowledge-dependent, positionally close, and highly co-occurred. Our analysis shows: (1) PLMs generate the missing factual words more by the positionally close and highly co-occurred words than the knowledge-dependent words; (2) the dependence on the knowledge-dependent words is more effective than the positionally close and highly co-occurred words. Accordingly, we conclude that the PLMs capture the factual knowledge ineffectively because of depending on the inadequate associations.


pdf bib
Knowledge-Interactive Network with Sentiment Polarity Intensity-Aware Multi-Task Learning for Emotion Recognition in Conversations
Yunhe Xie | Kailai Yang | Chengjie Sun | Bingquan Liu | Zhenzhou Ji
Findings of the Association for Computational Linguistics: EMNLP 2021

Emotion Recognition in Conversation (ERC) has gained much attention from the NLP community recently. Some models concentrate on leveraging commonsense knowledge or multi-task learning to help complicated emotional reasoning. However, these models neglect direct utterance-knowledge interaction. In addition, these models utilize emotion-indirect auxiliary tasks, which provide limited affective information for the ERC task. To address the above issues, we propose a Knowledge-Interactive Network with sentiment polarity intensity-aware multi-task learning, namely KI-Net, which leverages both commonsense knowledge and sentiment lexicon to augment semantic information. Specifically, we use a self-matching module for internal utterance-knowledge interaction. Considering correlations with the ERC task, a phrase-level Sentiment Polarity Intensity Prediction (SPIP) task is devised as an auxiliary task. Experiments show that all knowledge integration, self-matching and SPIP modules improve the model performance respectively on three datasets. Moreover, our KI-Net model shows 1.04% performance improvement over the state-of-the-art model on the IEMOCAP dataset.

pdf bib
ITNLP at SemEval-2021 Task 11: Boosting BERT with Sampling and Adversarial Training for Knowledge Extraction
Genyu Zhang | Yu Su | Changhong He | Lei Lin | Chengjie Sun | Lili Shan
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

This paper describes the winning system in the End-to-end Pipeline phase for the NLPContributionGraph task. The system is composed of three BERT-based models and the three models are used to extract sentences, entities and triples respectively. Experiments show that sampling and adversarial training can greatly boost the system. In End-to-end Pipeline phase, our system got an average F1 of 0.4703, significantly higher than the second-placed system which got an average F1 of 0.3828.


pdf bib
ITNLP-ARC at SemEval-2018 Task 12: Argument Reasoning Comprehension with Attention
Wenjie Liu | Chengjie Sun | Lei Lin | Bingquan Liu
Proceedings of The 12th International Workshop on Semantic Evaluation

Reasoning is a very important topic and has many important applications in the field of natural language processing. Semantic Evaluation (SemEval) 2018 Task 12 “The Argument Reasoning Comprehension” committed to research natural language reasoning. In this task, we proposed a novel argument reasoning comprehension system, ITNLP-ARC, which use Neural Networks technology to solve this problem. In our system, the LSTM model is involved to encode both the premise sentences and the warrant sentences. The attention model is used to merge the two premise sentence vectors. Through comparing the similarity between the attention vector and each of the two warrant vectors, we choose the one with higher similarity as our system’s final answer.


pdf bib
ITNLP-AiKF at SemEval-2017 Task 1: Rich Features Based SVR for Semantic Textual Similarity Computing
Wenjie Liu | Chengjie Sun | Lei Lin | Bingquan Liu
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

Semantic Textual Similarity (STS) devotes to measuring the degree of equivalence in the underlying semantic of the sentence pair. We proposed a new system, ITNLP-AiKF, which applies in the SemEval 2017 Task1 Semantic Textual Similarity track 5 English monolingual pairs. In our system, rich features are involved, including Ontology based, word embedding based, Corpus based, Alignment based and Literal based feature. We leveraged the features to predict sentence pair similarity by a Support Vector Regression (SVR) model. In the result, a Pearson Correlation of 0.8231 is achieved by our system, which is a competitive result in the contest of this track.

pdf bib
Neural Response Generation via GAN with an Approximate Embedding Layer
Zhen Xu | Bingquan Liu | Baoxun Wang | Chengjie Sun | Xiaolong Wang | Zhuoran Wang | Chao Qi
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

This paper presents a Generative Adversarial Network (GAN) to model single-turn short-text conversations, which trains a sequence-to-sequence (Seq2Seq) network for response generation simultaneously with a discriminative classifier that measures the differences between human-produced responses and machine-generated ones. In addition, the proposed method introduces an approximate embedding layer to solve the non-differentiable problem caused by the sampling-based output decoding procedure in the Seq2Seq generative model. The GAN setup provides an effective way to avoid noninformative responses (a.k.a “safe responses”), which are frequently observed in traditional neural response generators. The experimental results show that the proposed approach significantly outperforms existing neural response generation models in diversity metrics, with slight increases in relevance scores as well, when evaluated on both a Mandarin corpus and an English corpus.


pdf bib
Computing Semantic Text Similarity Using Rich Features
Yang Liu | Chengjie Sun | Lei Lin | Xiaolong Wang | Yuming Zhao
Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation

pdf bib
yiGou: A Semantic Text Similarity Computing System Based on SVM
Yang Liu | Chengjie Sun | Lei Lin | Xiaolong Wang
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

pdf bib
Predicting Polarities of Tweets by Composing Word Embeddings with Long Short-Term Memory
Xin Wang | Yuanchao Liu | Chengjie Sun | Baoxun Wang | Xiaolong Wang
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)


pdf bib
Generating Questions from Web Community Contents
Baoxun Wang | Bingquan Liu | Chengjie Sun | Xiaolong Wang | Deyuan Zhang
Proceedings of COLING 2012: Demonstration Papers


pdf bib
Learning to Detect Hedges and their Scope Using CRF
Qi Zhao | Chengjie Sun | Bingquan Liu | Yong Cheng
Proceedings of the Fourteenth Conference on Computational Natural Language Learning – Shared Task

pdf bib
CRF tagging for head recognition based on Stanford parser
Yong Cheng | Chengjie Sun | Bingquan Liu | Lei Lin
CIPS-SIGHAN Joint Conference on Chinese Language Processing

pdf bib
Modeling Semantic Relevance for Question-Answer Pairs in Web Social Communities
Baoxun Wang | Xiaolong Wang | Chengjie Sun | Bingquan Liu | Lin Sun
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics


pdf bib
Name Origin Recognition Using Maximum Entropy Model and Diverse Features
Min Zhang | Chengjie Sun | Haizhou Li | AiTi Aw | Chew Lim Tan | Xiaolong Wang
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I

pdf bib
A Study of Chinese Lexical Analysis Based on Discriminative Models
Guang-Lu Sun | Cheng-Jie Sun | Ke Sun | Xiao-Long Wang
Proceedings of the Sixth SIGHAN Workshop on Chinese Language Processing


pdf bib
Detecting Segmentation Errors in Chinese Annotated Corpus
Chengjie Sun | Chang-Ning Huang | Xiaolong Wang | Mu Li
Proceedings of the Fourth SIGHAN Workshop on Chinese Language Processing