Filters








23,405 Hits in 4.4 sec

Chinese Information Retrieval Based on Terms and Ontology

Lingpeng Yang, Donghong Ji, Li Tang
2004 NTCIR Conference on Evaluation of Information Access Technologies  
Firstly, we automatically extract terms (short-terms and long terms) from document set and use them to build indexes; secondly, for a query, we use short terms in the query and documents to do initial  ...  In this paper, we describe our approach for single language information retrieval (SLIR) on Chinese language of NTCIR4 tasks.  ...  Introduction At NTCIR4, we participated in SLIR tasks of Chinese language in Cross Lingual Information Retrieval (CLIR) track, where both the query and the document set are in traditional Chinese language  ... 
dblp:conf/ntcir/YangJT04 fatcat:46nbj6zj3badnfpqbdfak4i32q

Improving Retrieval Effectiveness by Using Key Terms in Top Retrieved Documents [chapter]

Yang Lingpeng, Ji Donghong, Zhou Guodong, Nie Yu
2005 Lecture Notes in Computer Science  
In this paper, we propose a method to improve the precision of top retrieved documents in Chinese information retrieval where the query is a short description by re-ordering retrieved documents in the  ...  To reorder the documents, we firstly find out terms in query and their importance scales by making use of the information derived from top N (N<=30) retrieved documents in the initial retrieval; secondly  ...  Step 1: Find out terms in q and their weight by information in top N documents; Step 1.1 Extract key terms from each document d in top N retrieved documents by using term extraction algorithm in Fig.  ... 
doi:10.1007/978-3-540-31865-1_13 fatcat:djvozbjynvgt3cbkidxijqqolm

Chinese Information Retrieval Using Lemur: NTCIR-5 CIR Experiments at UNT

Jiangping Chen, Rowena Li, Fei Li
2005 NTCIR Conference on Evaluation of Information Access Technologies  
This paper describes our participation in NTCIR-5 Chinese Information Retrieval (IR) evaluation. The main purpose is to evaluate Lemur, a freely available information retrieval toolkit.  ...  We also compared manual queries vs. automatic queries for Chinese IR. The results show that manually generated queries did not have much effect on IR performance.  ...  Topic 025 was removed from the relevant judgment file due to too few rigid relevant documents [4] .  ... 
dblp:conf/ntcir/ChenLL05 fatcat:e5vqkrrjb5d7bhzzfjrn7paxb4

Using Opinion Scores of Words for Sentence-Level Opinion Extraction

Lun-Wei Ku, Yong-Sheng Lo, Hsin-Hsi Chen
2007 NTCIR Conference on Evaluation of Information Access Technologies  
It contains the challenges of opinion sentence extraction, opinion polarity judgment, opinion holder extraction and relevance sentence extraction.  ...  In this paper, we introduce our system for analyzing opinionated information.  ...  An Chinese Opinion Extraction System: CopeOpi The Chinese opinion extraction system for opinionated information (CopeOpi) is a web-based system developed from news documents.  ... 
dblp:conf/ntcir/KuLC07 fatcat:lsxxl3wwkjgwlf7lygo3t2n4cm

An Efficient Approach to Learning Chinese Judgment Document Similarity Based on Knowledge Summarization [article]

Yinglong Ma, Peng Zhang, Jiangang Ma
2018 arXiv   pre-print
By utilizing domain ontologies for judgment documents, the core semantics of Chinese judgment documents is summarized based on knowledge blocks.  ...  However, current approaches for judgment document similarity computation failed to capture the core semantics of judgment documents and therefore suffer from lower accuracy and higher computation complexity  ...  Koniaris et al. presented an approach for extracting a machine readable semantic representation from unstructured legal document formats [16] .  ... 
arXiv:1808.01843v1 fatcat:abegbxq6kfeoxg7hkuru3amn4u

Translation enhancement

Daqing He, Dan Wu
2008 Proceeding of the 17th ACM conference on Information and knowledge mining - CIKM '08  
In this paper, we propose a novel RF method called translation enhancement (TE), which uses the extracted translation relationships from relevant documents to revise the translation probabilities of query  ...  As an effective technique for improving retrieval effectiveness, relevance feedback (RF) has been widely studied in both monolingual and cross-language information retrieval (CLIR) settings.  ...  Extracting Intended Translation Relationships from Relevant Documents Pairs When obtaining relevance feedback from users, the relevance judgments can be performed on various granularities of documents.  ... 
doi:10.1145/1458082.1458180 dblp:conf/cikm/HeW08 fatcat:lwh7qbavjvdbhmtqfldarduspq

Automatic Corpus-Based Extraction of Chinese Legal Terms

Oi Yee Kwong, Benjamin K. Tsou
2001 Natural Language Processing Pacific Rim Symposium  
We used a word segmented corpus of Chinese court judgments to extract salient legal expressions with standard collocation learning techniques.  ...  This paper reports on a study involving the automatic extraction of Chinese legal terms.  ...  Acknowledgements We thank the Judiciary of the HKSAR for providing the judgment data, colleagues on the ELDoS project for discussion, and the two law students for helping with the evaluation.  ... 
dblp:conf/nlprs/KwongT01 fatcat:fodkairlovathm5csriwdmbetu

An Ontology-Based and Deep Learning-Driven Method for Extracting Legal Facts from Chinese Legal Texts

Yong Ren, Jinfeng Han, Yingcheng Lin, Xiujiu Mei, Ling Zhang
2022 Electronics  
In the information extraction test of judicial datasets composed of Chinese legal texts on theft, the proposed method effectively extracts up to 38 categories of legal facts from legal texts and the number  ...  and deep learning-driven method for extracting legal facts from Chinese legal texts.  ...  [1] used regular expressions and feature dictionaries to extract basic case information from Chinese judgment documents. Solihin et al.  ... 
doi:10.3390/electronics11121821 fatcat:ou3zrd6nlnhalk22ayh3i3l73y

CJRC: A Reliable Human-Annotated Benchmark DataSet for Chinese Judicial Reading Comprehension [chapter]

Xingyi Duan, Baoxin Wang, Ziyue Wang, Wentao Ma, Yiming Cui, Dayong Wu, Shijin Wang, Ting Liu, Tianxiang Huo, Zhen Hu, Heng Wang, Zhiyuan Liu
2019 Lecture Notes in Computer Science  
The documents come from judgment documents and the questions are annotated by law experts. The CJRC dataset can help researchers extract elements by reading comprehension technology.  ...  By contrast, machine reading comprehension technology can quickly extract elements by answering various questions from the long document. We build two strong baseline models based on BERT and BiDAF.  ...  Moreover, a large number of documents make it challenging to extract information from them.  ... 
doi:10.1007/978-3-030-32381-3_36 fatcat:jsyu36ricnggzlkddermwnqwru

Legal Judgment Prediction Based on Multiclass Information Fusion

Kongfan Zhu, Rundong Guo, Weifeng Hu, Zeqiang Li, Yujun Li, Shirui Pan
2020 Complexity  
Legal judgment prediction (LJP), as an effective and critical application in legal assistant systems, aims to determine the judgment results according to the information based on the fact determination  ...  Experimental results show that our method outperforms state-of-the-art LJP methods on all judgment prediction tasks.  ...  Based on the topological structure between multiple tasks, we extract the information from the fact description via the Transformer-HAN encoder, extract the external information from the judgment document  ... 
doi:10.1155/2020/3089189 fatcat:b5wl5s3t4ff2pc3rbtawxb2pw4

Evidential Reasoning for Forensic Readiness

Yi-Ching Liao, Hanno Langweg
2016 Journal of Digital Forensics, Security and Law  
To learn from the past, we analyse 1,088 "computer as a target" judgments for evidential reasoning by extracting four case elements: decision, intent, fact, and evidence.  ...  Examining the evidence used against a defendant from previous judgments can facilitate the preparation of evidence for upcoming legal disclosure.  ...  Since there is no frequently used term to indicate the intent in Chinese judgments, we fail to extract the intent element from 134 Chinese judgments, from which we can observe that the pre-defined words  ... 
doi:10.15394/jdfsl.2016.1372 fatcat:h6slaxngsrewppreiunzkomymq

Information Retrieval Using Label Propagation Based Ranking

Lingpeng Yang, Donghong Ji, Yu Nie
2007 NTCIR Conference on Evaluation of Information Access Technologies  
Since no labeled relevant or irrelevant documents are generally available in IR, our approach tries to extract some pseudo labeled documents from the ranking list of the initial retrieval.  ...  In this paper, we describe our approach on Chinese Single Language Information Retrieval (SLIR) task and English-Chinese Bilingual CLIR task (BLIR).  ...  Introduction At NTCIR6, we participated in two sub-tasks in the Cross Lingual Information Retrieval (CLIR): Chinese Single Language Information Retrieval (SLIR) and English-Chinese Bilingual CLIR (BLIR  ... 
dblp:conf/ntcir/YangJN07 fatcat:5dkvfvh2pvdjfd53nxb6pmhxvm

Ice-tea

Dan Wu, Daqing He
2008 Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '08  
The main idea of TE, therefore, is to extract intended translation relationships of query terms from the relevant document pairs (original returned documents and their translations) and then to enhance  ...  It also displays the original returned documents and their translations (both surrogate and full-text) to help users to make multi-level relevance judgments.  ...  The main idea of TE, therefore, is to extract intended translation relationships of query terms from the relevant document pairs (original returned documents and their translations) and then to enhance  ... 
doi:10.1145/1390334.1390556 dblp:conf/sigir/WuH08 fatcat:zxqsbis6lzbe3nujsvq5cje5qu

Hierarchical RNN for Information Extraction from Lawsuit Documents [article]

Xi Rao, Zhenxing Ke
2018 arXiv   pre-print
However, the extraction of these information from the document is difficult because the language is too complicated and sentences varied at length.  ...  We treat this problem as a task of sequence labeling, and this paper presents the first research to extract relevant information from the civil lawsuit document in China with the hierarchical RNN framework  ...  DATASET We introduce a novel corpus consisting of lawsuit documents (judgments) from the Chinese court.  ... 
arXiv:1804.09321v1 fatcat:iewytmipyffphdroqt6f5jaswi

Sentence-Level Opinion Analysis by CopeOpi in NTCIR-7

Lun-Wei Ku, I-Chien Liu, Chia-Ying Lee, Kuang-hua Chen, Hsin-Hsi Chen
2008 NTCIR Conference on Evaluation of Information Access Technologies  
In this paper, we introduce our system, CopeOpi, for analyzing opinionated information in NTCIR-7 MOAT task's document collections.  ...  We participated in all tasks except opinion target extraction and submitted three runs for both simplified and traditional Chinese sides.  ...  An Chinese Opinion Extraction System: NTU CopeOpi The Chinese opinion extraction system for opinionated information (CopeOpi) is a web-based system developed from news documents.  ... 
dblp:conf/ntcir/KuLLCC08 fatcat:hrobbpuqijai3eivfajph4viie
« Previous Showing results 1 — 15 out of 23,405 results