Legal Judgment Elements Extraction Approach with Law Article-aware Mechanism

Author(s):  
Hu Zhang ◽  
Bangze Pan ◽  
Ru Li

Legal judgment elements extraction (LJEE) aims to identify the different judgment features from the fact description in legal documents automatically, which helps to improve the accuracy and interpretability of the judgment results. In real court rulings, judges usually need to scan both the fact descriptions and the law articles repeatedly to find out the relevant information, and it is hard to acquire the key judgment features quickly, so legal judgment elements extraction is a crucial and challenging task for legal judgment prediction. However, most existing methods follow the text classification framework, which fails to model the attentive relations of the law articles and the legal judgment elements. To address this issue, we simulate the working process of human judges, and propose a legal judgment elements extraction method with a law article-aware mechanism, which captures the complex semantic correlations of the law article and the legal judgment elements. Experimental results show that our proposed method achieves significant improvements than other state-of-the-art baselines on the element recognition task dataset. Compared with the BERT-CNN model, the proposed “All labels Law Articles Embedding Model (ALEM)” improves the accuracy, recall, and F1 value by 0.5, 1.4 and 1.0, respectively.

Terminology ◽  
2000 ◽  
Vol 6 (2) ◽  
pp. 195-210 ◽  
Author(s):  
Hiroshi Nakagawa

The NTCIR1 TMREC group called for participation of the term recognition task which is a part of NTCIR1 held in 1999. As an activity of TMREC, they have provided us with the test collection of the term recognition task. The goal of this task is to automatically recognize and extract terms from the text corpus which consists of 1,870 abstracts gathered from the NACSIS Academic Conference Database. This article describes the term extraction method we have proposed to extract terms consisting of simple and compound nouns and the experimental evaluation of the proposed method with this NTCIR TMREC test collection. The basic idea of scoring a simple noun N of our term extraction method is to count how many nouns are conjoined with N to make compound nouns. Then we extend this score to measure the score of compound nouns because most of technical terms are compound nouns. Our method has a parameter to tune the degree of preference either for longer compound nouns or for shorter compound nouns. As for term candidates, in addition to noun sequences, we may add variations such as patterns of "A no B" that roughly means "B of A" or "A’ś B" and/or "A na B" where "A na" is an adjective. Experimental results of our method are promising, namely recall of 0.83, precision of 0.46 and F-value of 0.59 for exactly matched extracted terms when we take into account top scoring 16,000 extracted terms.


Author(s):  
Liang Yao ◽  
Chengsheng Mao ◽  
Yuan Luo

Text classification is an important and classical problem in natural language processing. There have been a number of studies that applied convolutional neural networks (convolution on regular grid, e.g., sequence) to classification. However, only a limited number of studies have explored the more flexible graph convolutional neural networks (convolution on non-grid, e.g., arbitrary graph) for the task. In this work, we propose to use graph convolutional networks for text classification. We build a single text graph for a corpus based on word co-occurrence and document word relations, then learn a Text Graph Convolutional Network (Text GCN) for the corpus. Our Text GCN is initialized with one-hot representation for word and document, it then jointly learns the embeddings for both words and documents, as supervised by the known class labels for documents. Our experimental results on multiple benchmark datasets demonstrate that a vanilla Text GCN without any external word embeddings or knowledge outperforms state-of-the-art methods for text classification. On the other hand, Text GCN also learns predictive word and document embeddings. In addition, experimental results show that the improvement of Text GCN over state-of-the-art comparison methods become more prominent as we lower the percentage of training data, suggesting the robustness of Text GCN to less training data in text classification.


2020 ◽  
Vol 34 (05) ◽  
pp. 8665-8672 ◽  
Author(s):  
Libo Qin ◽  
Wanxiang Che ◽  
Yangming Li ◽  
Mingheng Ni ◽  
Ting Liu

In dialog system, dialog act recognition and sentiment classification are two correlative tasks to capture speakers' intentions, where dialog act and sentiment can indicate the explicit and the implicit intentions separately (Kim and Kim 2018). Most of the existing systems either treat them as separate tasks or just jointly model the two tasks by sharing parameters in an implicit way without explicitly modeling mutual interaction and relation. To address this problem, we propose a Deep Co-Interactive Relation Network (DCR-Net) to explicitly consider the cross-impact and model the interaction between the two tasks by introducing a co-interactive relation layer. In addition, the proposed relation layer can be stacked to gradually capture mutual knowledge with multiple steps of interaction. Especially, we thoroughly study different relation layers and their effects. Experimental results on two public datasets (Mastodon and Dailydialog) show that our model outperforms the state-of-the-art joint model by 4.3% and 3.4% in terms of F1 score on dialog act recognition task, 5.7% and 12.4% on sentiment classification respectively. Comprehensive analysis empirically verifies the effectiveness of explicitly modeling the relation between the two tasks and the multi-steps interaction mechanism. Finally, we employ the Bidirectional Encoder Representation from Transformer (BERT) in our framework, which can further boost our performance in both tasks.


2021 ◽  
Vol 11 (7) ◽  
pp. 3009
Author(s):  
Sungjin Park ◽  
Taesun Whang ◽  
Yeochan Yoon ◽  
Heuiseok Lim

Visual dialog is a challenging vision-language task in which a series of questions visually grounded by a given image are answered. To resolve the visual dialog task, a high-level understanding of various multimodal inputs (e.g., question, dialog history, and image) is required. Specifically, it is necessary for an agent to (1) determine the semantic intent of question and (2) align question-relevant textual and visual contents among heterogeneous modality inputs. In this paper, we propose Multi-View Attention Network (MVAN), which leverages multiple views about heterogeneous inputs based on attention mechanisms. MVAN effectively captures the question-relevant information from the dialog history with two complementary modules (i.e., Topic Aggregation and Context Matching), and builds multimodal representations through sequential alignment processes (i.e., Modality Alignment). Experimental results on VisDial v1.0 dataset show the effectiveness of our proposed model, which outperforms previous state-of-the-art methods under both single model and ensemble settings.


Author(s):  
Jin Wang ◽  
Zhongyuan Wang ◽  
Dawei Zhang ◽  
Jun Yan

Text classification is a fundamental task in NLP applications. Most existing work relied on either explicit or implicit text representation to address this problem. While these techniques work well for sentences, they can not easily be applied to short text because of its shortness and sparsity. In this paper, we propose a framework based on convolutional neural networks that combines explicit and implicit representations of short text for classification. We first conceptualize a short text as a set of relevant concepts using a large taxonomy knowledge base. We then obtain the embedding of short text by coalescing the words and relevant concepts on top of pre-trained word vectors. We further incorporate character level features into our model to capture fine-grained subword information. Experimental results on five commonly used datasets show that our proposed method significantly outperforms state-of-the-art methods.


Author(s):  
L.L. KHOPERSKAYA

The article deals with the problem of completeness of information on measures to counter terrorism and extremism taken by the labor-surplus states of Central Asia. With the help of some former labor migrants, a new model of terrorism (IS 2.0) is being developed based on the use of pendulum migration of radical Islamists to the countries of Central Asia and Russia, such Islamists serve as the core of various extremist organizations. A serious problem for the Russian experts is that none of the countries (Tajikistan, Kyrgyzstan or Uzbekistan) sending labor migrants to Russia publishes complex information each country publishes mainly statistical or regulatory information or news. For example, not all official documents are available in Tajikistan or Uzbekistan and it is difficult to obtain official statistics in Uzbekistan or Kyrgyzstan. Nevertheless, the analysis of the disparate experience of the three countries, among which we can highlight the purposeful work with labor migrants carried out by the representative offices of the Republic of Tajikistan abroad the courses for imams of mosques and clerics on the prevention of radicalization of the population organized by the State Commission for religious affairs of the Kyrgyz Republic and the system of social rehabilitation of repentant extremists in Uzbekistan prove the need for relevant information in a certain standardized form. The main sources of information used in the article are documents of the UN, the CIS Anti-Terrorist Center, speeches of the President of the Republic of Tajikistan containing statistical information, news information from the websites of the special services of the Kyrgyz Republic and legal documents of Uzbekistan. The article substantiates the conclusion about the need to highlight the information aspect in the formation of the anti-terrorist Eurasian space, the relevance of which was discussed at the Council of the CSTO Parliamentary Assembly in May 2019.


2020 ◽  
Author(s):  
Pathikkumar Patel ◽  
Bhargav Lad ◽  
Jinan Fiaidhi

During the last few years, RNN models have been extensively used and they have proven to be better for sequence and text data. RNNs have achieved state-of-the-art performance levels in several applications such as text classification, sequence to sequence modelling and time series forecasting. In this article we will review different Machine Learning and Deep Learning based approaches for text data and look at the results obtained from these methods. This work also explores the use of transfer learning in NLP and how it affects the performance of models on a specific application of sentiment analysis.


2020 ◽  
Vol 8 (1) ◽  
pp. 33-41
Author(s):  
Dr. S. Sarika ◽  

Phishing is a malicious and deliberate act of sending counterfeit messages or mimicking a webpage. The goal is either to steal sensitive credentials like login information and credit card details or to install malware on a victim’s machine. Browser-based cyber threats have become one of the biggest concerns in networked architectures. The most prolific form of browser attack is tabnabbing which happens in inactive browser tabs. In a tabnabbing attack, a fake page disguises itself as a genuine page to steal data. This paper presents a multi agent based tabnabbing detection technique. The method detects heuristic changes in a webpage when a tabnabbing attack happens and give a warning to the user. Experimental results show that the method performs better when compared with state of the art tabnabbing detection techniques.


Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 325
Author(s):  
Zhihao Wu ◽  
Baopeng Zhang ◽  
Tianchen Zhou ◽  
Yan Li ◽  
Jianping Fan

In this paper, we developed a practical approach for automatic detection of discrimination actions from social images. Firstly, an image set is established, in which various discrimination actions and relations are manually labeled. To the best of our knowledge, this is the first work to create a dataset for discrimination action recognition and relationship identification. Secondly, a practical approach is developed to achieve automatic detection and identification of discrimination actions and relationships from social images. Thirdly, the task of relationship identification is seamlessly integrated with the task of discrimination action recognition into one single network called the Co-operative Visual Translation Embedding++ network (CVTransE++). We also compared our proposed method with numerous state-of-the-art methods, and our experimental results demonstrated that our proposed methods can significantly outperform state-of-the-art approaches.


2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Changyong Li ◽  
Yongxian Fan ◽  
Xiaodong Cai

Abstract Background With the development of deep learning (DL), more and more methods based on deep learning are proposed and achieve state-of-the-art performance in biomedical image segmentation. However, these methods are usually complex and require the support of powerful computing resources. According to the actual situation, it is impractical that we use huge computing resources in clinical situations. Thus, it is significant to develop accurate DL based biomedical image segmentation methods which depend on resources-constraint computing. Results A lightweight and multiscale network called PyConvU-Net is proposed to potentially work with low-resources computing. Through strictly controlled experiments, PyConvU-Net predictions have a good performance on three biomedical image segmentation tasks with the fewest parameters. Conclusions Our experimental results preliminarily demonstrate the potential of proposed PyConvU-Net in biomedical image segmentation with resources-constraint computing.


Sign in / Sign up

Export Citation Format

Share Document