Cover Image
QR Code

Semi-supervised learning of statistical models for natural language understanding.

Natural language understanding is to specify a computational model that maps sentences to their semantic mean representation. In this paper, we propose a novel framework to train the statistical models without using expensive fully annotated data. In particular, the input of our framework is a set o...

Full description

Published in:Scientific World Journal pp. 121650 - 121651
Main Authors: Zhou, Deyu, He, Yulan
Format: research Journal Article
Published: Wiley-Blackwell 2014
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=103842423&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 103842423
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        1537744X
        1BX5
      jtl: Scientific World Journal
      issn: 1537744X
      maglogo: N
    pubinfo:
      dt: 2014
      pid: 480
      pub: Wiley-Blackwell
      place: Malden, Massachusetts
    artinfo:
      ui:
        103842423
        103842423
        NLM25152899
        2012696835
        10.1155/2014/121650
        NLM25152899
        PMC4127215
        103842423
      ppf: 121650
      ppct: 1
      formats:
      tig:
        atl: Semi-supervised learning of statistical models for natural language understanding.
      aug:
        au:
          Zhou, Deyu
          He, Yulan
        affil: School of Computer Science and Engineering, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University, Nanjing 210096, China.
      sug:
        subj:
          Models, Statistical
          Natural Language Processing
          Algorithms
      ab: Natural language understanding is to specify a computational model that maps sentences to their semantic mean representation. In this paper, we propose a novel framework to train the statistical models without using expensive fully annotated data. In particular, the input of our framework is a set of sentences labeled with abstract semantic annotations. These annotations encode the underlying embedded semantic structural relations without explicit word/semantic tag alignment. The proposed framework can automatically induce derivation rules that map sentences to their semantic meaning representations. The learning framework is applied on two statistical models, the conditional random fields (CRFs) and the hidden Markov support vector machines (HM-SVMs). Our experimental results on the DARPA communicator data show that both CRFs and HM-SVMs outperform the baseline approach, previously proposed hidden vector state (HVS) model which is also trained on abstract semantic annotations. In addition, the proposed framework shows superior performance than two other baseline approaches, a hybrid framework combining HVS and HM-SVMs and discriminative training of HVS, with a relative error reduction rate of about 25% and 15% being achieved in F-measure.
      pubtype: Academic Journal
      doctype:
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N