An integrated architecture for shallow and deep processing

被引:0
|
作者
Crysmann, B [1 ]
Frank, A [1 ]
Kiefer, B [1 ]
Müller, S [1 ]
Neumann, G [1 ]
Piskorski, J [1 ]
Schäfer, U [1 ]
Siegel, M [1 ]
Uszkoreit, H [1 ]
Xu, FY [1 ]
Becker, M [1 ]
Krieger, HU [1 ]
机构
[1] DFKI GmbH, Saarbrucken, Germany
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present an architecture for the integration of shallow and deep NLP components which is aimed at flexible combination of different language technologies for a range of practical current and future applications. In particular, we describe the integration of a high-level HPSG parsing system with different high-performance shallow components, ranging from named entity recognition to chunk parsing and shallow clause recognition. The NLP components enrich a representation of natural language text with layers of new XML meta-information using a single shared data structure, called the text chart. We describe details of the integration methods, and show how information extraction and language checking applications for realworld German text benefit from a deep grammatical analysis.
引用
收藏
页码:441 / 448
页数:8
相关论文
共 50 条
  • [1] Deep and Shallow Architecture of Multilayer Neural Networks
    Chang, Chih-Hung
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2015, 26 (10) : 2477 - 2486
  • [2] Deep learning with Shallow architecture for Image Classification
    ElAdel, Asma
    Ejbali, Ridha
    Zaied, Mourad
    Ben Amar, Chokri
    [J]. PROCEEDINGS OF THE 2015 INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING & SIMULATION (HPCS 2015), 2015, : 408 - 412
  • [3] Shallow language processing, deep language processing and domain ontologies
    Uszkoreit, H
    [J]. Proceedings of the 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering (IEEE NLP-KE'05), 2005, : 7 - 8
  • [4] Deep syntactic processing by combining shallow methods
    Dienes, M
    Dubey, A
    [J]. 41ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, 2003, : 431 - 438
  • [5] Predicting publication productivity for authors: Shallow or deep architecture?
    Wumei Du
    Zheng Xie
    Yiqin Lv
    [J]. Scientometrics, 2021, 126 : 5855 - 5879
  • [6] Predicting publication productivity for authors: Shallow or deep architecture?
    Du, Wumei
    Xie, Zheng
    Lv, Yiqin
    [J]. SCIENTOMETRICS, 2021, 126 (07) : 5855 - 5879
  • [7] INTEGRATED DEEP AND SHALLOW NETWORKS FOR SALIENT OBJECT DETECTION
    Zhang, Jing
    Li, Bo
    Dai, Yuchao
    Porikli, Fatih
    He, Mingyi
    [J]. 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 1537 - 1541
  • [8] Integrated shallow and deep parsing:: TopP meets HPSG
    Frank, A
    Becker, M
    Crysmann, B
    Kiefer, B
    Schäfer, U
    [J]. 41ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, 2003, : 104 - 111
  • [9] Effects of coherence and relevance on shallow and deep text processing
    Lehman, S
    Schraw, G
    [J]. JOURNAL OF EDUCATIONAL PSYCHOLOGY, 2002, 94 (04) : 738 - 750
  • [10] An Integrated Architecture for Processing Business Documents in Turkish
    Adali, Serif
    Sonmez, A. Coskun
    Gokturk, Mehmet
    [J]. COMPUTATIONAL LINGUISTICS AND INTELLIGENT TEXT PROCESSING, 2009, 5449 : 394 - +