Joint Labeling of Syntactic Function and Semantic Role Using Probabilistic Finite State Automata

被引:1
作者
Salama, Amr Rekaby [1 ]
Menzel, Wolfgang [1 ]
机构
[1] Hamburg Univ, Dept Informat, Fac Math Informat & Nat Sci, Hamburg, Germany
来源
INTELLIGENT SYSTEMS AND APPLICATIONS, INTELLISYS, VOL 2 | 2019年 / 869卷
关键词
Joint parsing; Finite state automata; Syntactic dependency parsing; Semantic role labeling;
D O I
10.1007/978-3-030-01057-7_46
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Syntactic parsing and semantic labeling are common natural language processing tasks. Traditionally, they were mostly arranged in a pipeline architecture. During the last decade, however, different joint parsing approaches have been introduced where the sequential dependency between the two levels is reduced. In this paper, we present a model for a simplified joint parsing, namely, labeling, based on probabilistic finite state automata through the extended label set paradigm. The parsing (labeling) we present in this research considers syntactic dependency annotation and semantic role labeling without constructing a complete dependency hierarchy. In our experiment, we show that the proposed model outperforms the standard finite transducer approach (Hidden Markov Model). In spite of the considerably increased search space for the joint syntactic and semantic labeling, the proposed solution keeps a high accuracy of the syntactic labeling on par with the quality of syntax-only models. In addition to that it provides a reasonable semantic annotation quality without a separate processing step.
引用
收藏
页码:588 / 605
页数:18
相关论文
共 49 条
  • [41] An Integration of Function- and Affordance-Based Methods for Product-Service System Utilizing Finite State Automata
    Ko, Hyunwoong
    Moon, Seung Ki
    Wood, Kristin L.
    Oh, Hyung Sool
    2016 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL ENGINEERING AND ENGINEERING MANAGEMENT (IEEM), 2016, : 577 - 581
  • [42] Jointly Part-of-Speech Tagging and Semantic Role Labeling Using Auxiliary Deep Neural Network Model
    Shen, Yatian
    Mai, Yubo
    Shen, Xiajiong
    Ding, Wenke
    Guo, Mengjiao
    CMC-COMPUTERS MATERIALS & CONTINUA, 2020, 65 (01): : 529 - 541
  • [43] Improvement of Prosody Modeling Using Semantic Role Labeling, Hybrid Feature Selection and BPSO–PSO–Optimized RNN
    Mansour Sheikhan
    National Academy Science Letters, 2017, 40 : 171 - 175
  • [44] Evaluation of Semantic Role Labeling Based on Lexical Features Using Conditional Random Fields and Support Vector Machine
    Ravidhaa, K.
    Meena, Radha S.
    Milton, R. S.
    2013 INTERNATIONAL CONFERENCE ON RECENT TRENDS IN INFORMATION TECHNOLOGY (ICRTIT), 2013, : 50 - 55
  • [45] Using finite state automata (FSA) for formal modelling of affordances in human-machine cooperative manufacturing systems
    Kim, N.
    Shin, D.
    Wysk, R. A.
    Rothrock, L.
    INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH, 2010, 48 (05) : 1303 - 1320
  • [46] Improvement of Prosody Modeling Using Semantic Role Labeling, Hybrid Feature Selection and BPSO-PSO-Optimized RNN
    Sheikhan, Mansour
    NATIONAL ACADEMY SCIENCE LETTERS-INDIA, 2017, 40 (03): : 171 - 175
  • [47] FINITE-STATE AUTOMATA-BASED REPRESENTATION OF DEVICE STATES FOR FUNCTION MODELING AND FORMAL DEFINITIONS OF SIGNAL-PROCESSING FUNCTIONS
    Chowdhury, Ahmed
    Mao, Xiaoyang
    Venkatanarasimhan, Lakshmi N. A.
    Sen, Chiradeep
    PROCEEDINGS OF THE ASME INTERNATIONAL DESIGN ENGINEERING TECHNICAL CONFERENCES AND COMPUTERS AND INFORMATION IN ENGINEERING CONFERENCE, 2019, VOL 1, 2020,
  • [48] Plant Model-Based Fault Detection during Aircraft Takeoff Using Non-Deterministic Finite-State Automata
    Settele, Ferdinand
    Weber, Alexander
    Knoll, Alexander
    AEROSPACE, 2020, 7 (08)
  • [49] A Highway-Driving System Design Viewpoint Using an Agent-Based Modeling of an Affordance-Based Finite State Automata
    Ransikarbum, Kasin
    Kim, Namhun
    Ha, Sangho
    Wysk, Richard A.
    Rothrock, Ling
    IEEE ACCESS, 2018, 6 : 2193 - 2205