Zhunchen Luo


pdf bib
Characterizing and Verifying Scientific Claims: Qualitative Causal Structure is All You Need
Jinxuan Wu | Wenhan Chao | Xian Zhou | Zhunchen Luo
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

A scientific claim typically begins with the formulation of a research question or hypothesis, which is a tentative statement or proposition about a phenomenon or relationship between variables. Within the realm of scientific claim verification, considerable research efforts have been dedicated to attention architectures and leveraging the text comprehension capabilities of Pre-trained Language Models (PLMs), yielding promising performances. However, these models overlook the causal structure information inherent in scientific claims, thereby failing to establish a comprehensive chain of causal inference. This paper delves into the exploration to highlight the crucial role of qualitative causal structure in characterizing and verifying scientific claims based on evidence. We organize the qualitative causal structure into a heterogeneous graph and propose a novel attention-based graph neural network model to facilitate causal reasoning across relevant causally-potent factors. Our experiments demonstrate that by solely utilizing the qualitative causal structure, the proposed model achieves comparable performance to PLM-based models. Furthermore, by incorporating semantic features, our model outperforms state-of-the-art approaches comprehensively.

pdf bib
TP-Detector: Detecting Turning Points in the Engineering Process of Large-scale Projects
Qi Wu | WenHan Chao | Xian Zhou | Zhunchen Luo
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

This paper introduces a novel task of detecting turning points in the engineering process of large-scale projects, wherein the turning points signify significant transitions occurring between phases. Given the complexities involving diverse critical events and limited comprehension in individual news reports, we approach the problem by treating the sequence of related news streams as a window with multiple instances. To capture the evolution of changes effectively, we adopt a deep Multiple Instance Learning (MIL) framework and employ the multiple instance ranking loss to discern the transition patterns exhibited in the turning point window. Extensive experiments consistently demonstrate the effectiveness of our proposed approach on the constructed dataset compared to baseline methods. We deployed the proposed mode and provided a demonstration video to illustrate its functionality. The code and dataset are available on GitHub.

pdf bib
Improved Training of Deep Text Clustering
Zonghao Yang | Wenpeng Hu | Yushan Tan | Zhunchen Luo
Findings of the Association for Computational Linguistics: EMNLP 2023

The classical deep clustering optimization methods basically leverage information such as clustering centers, mutual information, and distance metrics to construct implicit generalized labels to establish information feedback (weak supervision) and thus optimize the deep model. However, the resulting generalized labels have different degrees of errors in the whole clustering process due to the limitation of clustering accuracy, which greatly interferes with the clustering process. To this end, this paper proposes a general deep clustering optimization method from the perspective of empirical risk minimization, using the correlation relationship between the samples. Experiments on two classical deep clustering methods demonstrate the necessity and effectiveness of the method. Code is available at https://github.com/yangzonghao1024/DCGLU.


pdf bib
Identifying Principals and Accessories in a Complex Case based on the Comprehension of Fact Description
Yakun Hu | Zhunchen Luo | Wenhan Chao
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

In this paper, we study the problem of identifying the principals and accessories from the fact description with multiple defendants in a criminal case. We treat the fact descriptions as narrative texts and the defendants as roles over the narrative story. We propose to model the defendants with behavioral semantic information and statistical characteristics, then learning the importances of defendants within a learning-to-rank framework. Experimental results on a real-world dataset demonstrate the behavior analysis can effectively model the defendants’ impacts in a complex case.


pdf bib
A Context-based Framework for Modeling the Role and Function of On-line Resource Citations in Scientific Literature
He Zhao | Zhunchen Luo | Chong Feng | Anqing Zheng | Xiaopeng Liu
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

We introduce a new task of modeling the role and function for on-line resource citations in scientific literature. By categorizing the on-line resources and analyzing the purpose of resource citations in scientific texts, it can greatly help resource search and recommendation systems to better understand and manage the scientific resources. For this novel task, we are the first to create an annotation scheme, which models the different granularity of information from a hierarchical perspective. And we construct a dataset SciRes, which includes 3,088 manually annotated resource contexts. In this paper, we propose a possible solution by using a multi-task framework to build the scientific resource classifier (SciResCLF) for jointly recognizing the role and function types. Then we use the classification results to help a scientific resource recommendation (SciResREC) task. Experiments show that our model achieves the best results on both the classification task and the recommendation task. The SciRes dataset is released for future research.


pdf bib
Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation
Xiao Liu | Zhunchen Luo | Heyan Huang
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Event extraction is of practical utility in natural language processing. In the real world, it is a common phenomenon that multiple events existing in the same sentence, where extracting them are more difficult than extracting a single event. Previous works on modeling the associations between events by sequential modeling methods suffer a lot from the low efficiency in capturing very long-range dependencies. In this paper, we propose a novel Jointly Multiple Events Extraction (JMEE) framework to jointly extract multiple event triggers and arguments by introducing syntactic shortcut arcs to enhance information flow and attention-based graph convolution networks to model graph information. The experiment results demonstrate that our proposed framework achieves competitive results compared with state-of-the-art methods.

pdf bib
Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions
Hai Ye | Xin Jiang | Zhunchen Luo | Wenhan Chao
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

In this paper, we propose to study the problem of court view generation from the fact description in a criminal case. The task aims to improve the interpretability of charge prediction systems and help automatic legal document generation. We formulate this task as a text-to-text natural language generation (NLG) problem. Sequence-to-sequence model has achieved cutting-edge performances in many NLG tasks. However, due to the non-distinctions of fact descriptions, it is hard for Seq2Seq model to generate charge-discriminative court views. In this work, we explore charge labels to tackle this issue. We propose a label-conditioned Seq2Seq model with attention for this problem, to decode court views conditioned on encoded charge labels. Experimental results show the effectiveness of our method.

pdf bib
IRCMS at SemEval-2018 Task 7 : Evaluating a basic CNN Method and Traditional Pipeline Method for Relation Classification
Zhongbo Yin | Zhunchen Luo | Wei Luo | Mao Bin | Changhai Tian | Yuming Ye | Shuai Wu
Proceedings of the 12th International Workshop on Semantic Evaluation

This paper presents our participation for sub-task1 (1.1 and 1.2) in SemEval 2018 task 7: Semantic Relation Extraction and Classification in Scientific Papers (Gábor et al., 2018). We experimented on this task with two methods: CNN method and traditional pipeline method. We use the context between two entities (included) as input information for both methods, which extremely reduce the noise effect. For the CNN method, we construct a simple convolution neural network to automatically learn features from raw texts without any manual processing. Moreover, we use the softmax function to classify the entity pair into a specific relation category. For the traditional pipeline method, we use the Hackabout method as a representation which is described in section3.5. The CNN method’s result is much better than traditional pipeline method (49.1% vs. 42.3% and 71.1% vs. 54.6% ).

pdf bib
Joker at SemEval-2018 Task 12: The Argument Reasoning Comprehension with Neural Attention
Guobin Sui | Wenhan Chao | Zhunchen Luo
Proceedings of the 12th International Workshop on Semantic Evaluation

This paper describes a classification system that participated in the SemEval-2018 Task 12: The Argument Reasoning Comprehension Task. Briefly the task can be described as that a natural language “argument” is what we have, with reason, claim, and correct and incorrect warrants, and we need to choose the correct warrant. In order to make fully understand of the semantic information of the sentences, we proposed a neural network architecture with attention mechanism to achieve this goal. Besides we try to introduce keywords into the model to improve accuracy. Finally the proposed system achieved 5th place among 22 participating systems

pdf bib
Real-time Scholarly Retweeting Prediction System
Zhunchen Luo | Xiao Liu
Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations

Twitter has become one of the most import channels to spread latest scholarly information because of its fast information spread speed. How to predict whether a scholarly tweet will be retweeted is a key task in understanding the message propagation within large user communities. Hence, we present the real-time scholarly retweeting prediction system that retrieves scholarly tweets which will be retweeted. First, we filter scholarly tweets from tracking a tweet stream. Then, we extract Tweet Scholar Blocks indicating metadata of papers. At last, we combine scholarly features with the Tweet Scholar Blocks to predict whether a scholarly tweet will be retweeted. Our system outperforms chosen baseline systems. Additionally, our system has the potential to predict scientific impact in real-time.

pdf bib
CRST: a Claim Retrieval System in Twitter
Wenjia Ma | WenHan Chao | Zhunchen Luo | Xin Jiang
Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations

For controversial topics, collecting argumentation-containing tweets which tend to be more convincing will help researchers analyze public opinions. Meanwhile, claim is the heart of argumentation. Hence, we present the first real-time claim retrieval system CRST that retrieves tweets containing claims for a given topic from Twitter. We propose a claim-oriented ranking module which can be divided into the offline topic-independent learning to rank model and the online topic-dependent lexicon model. Our system outperforms previous claim retrieval system and argument mining system. Moreover, the claim-oriented ranking module can be easily adapted to new topics without any manual process or external information, guaranteeing the practicability of our system.

pdf bib
Interpretable Rationale Augmented Charge Prediction System
Xin Jiang | Hai Ye | Zhunchen Luo | WenHan Chao | Wenjia Ma
Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations

This paper proposes a neural based system to solve the essential interpretability problem existing in text classification, especially in charge prediction task. First, we use a deep reinforcement learning method to extract rationales which mean short, readable and decisive snippets from input text. Then a rationale augmented classification model is proposed to elevate the prediction accuracy. Naturally, the extracted rationales serve as the introspection explanation for the prediction result of the model, enhancing the transparency of the model. Experimental results demonstrate that our system is able to extract readable rationales in a high consistency with manual annotation and is comparable with the attention model in prediction accuracy.


pdf bib
Jointly Extracting Relations with Class Ties via Effective Deep Ranking
Hai Ye | Wenhan Chao | Zhunchen Luo | Zhoujun Li
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Connections between relations in relation extraction, which we call class ties, are common. In distantly supervised scenario, one entity tuple may have multiple relation facts. Exploiting class ties between relations of one entity tuple will be promising for distantly supervised relation extraction. However, previous models are not effective or ignore to model this property. In this work, to effectively leverage class ties, we propose to make joint relation extraction with a unified model that integrates convolutional neural network (CNN) with a general pairwise ranking framework, in which three novel ranking loss functions are introduced. Additionally, an effective method is presented to relieve the severe class imbalance problem from NR (not relation) for model training. Experiments on a widely used dataset show that leveraging class ties will enhance extraction and demonstrate the effectiveness of our model to learn class ties. Our model outperforms the baselines significantly, achieving state-of-the-art performance.


pdf bib
Speculation and Negation Scope Detection via Convolutional Neural Networks
Zhong Qian | Peifeng Li | Qiaoming Zhu | Guodong Zhou | Zhunchen Luo | Wei Luo
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing