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

Zhou D, He Y - ScientificWorldJournal (2014)

Bottom Line: The proposed framework can automatically induce derivation rules that map sentences to their semantic meaning representations.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.

View Article: PubMed Central - PubMed

Affiliation: School of Computer Science and Engineering, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University, Nanjing 210096, China.

ABSTRACT
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.

Show MeSH

Related in: MedlinePlus

Time consumed in each iteration by CRFs and HM-SVMs.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4127215&req=5

fig2: Time consumed in each iteration by CRFs and HM-SVMs.

Mentions: We first compare the time consumed in each iteration using HM-SVMs or CRFs as shown in Figure 2. The experiments were conducted on the Intel(R) Xeon(TM) model Linux server equipped with 3.00 Ghz processor and 4 GB RAM. It can be observed that, for CRFs, the time consumed in SGD is almost doubled compared to that in L-BFGS in each iteration. However, since SGD converges much faster than L-BFGS, the total time required for training is almost the same. As SGD gives balanced precision and recall values, it should be preferred more than L-BFGS in our proposed learning procedure. On the other hand, as opposed to CRFs which consume much less time after iteration 1, HM-SVMs take almost the same run time for all the iterations. Nevertheless, the total run time until convergence is almost the same for CRFs and HM-SVMs.


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

Zhou D, He Y - ScientificWorldJournal (2014)

Time consumed in each iteration by CRFs and HM-SVMs.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4127215&req=5

fig2: Time consumed in each iteration by CRFs and HM-SVMs.
Mentions: We first compare the time consumed in each iteration using HM-SVMs or CRFs as shown in Figure 2. The experiments were conducted on the Intel(R) Xeon(TM) model Linux server equipped with 3.00 Ghz processor and 4 GB RAM. It can be observed that, for CRFs, the time consumed in SGD is almost doubled compared to that in L-BFGS in each iteration. However, since SGD converges much faster than L-BFGS, the total time required for training is almost the same. As SGD gives balanced precision and recall values, it should be preferred more than L-BFGS in our proposed learning procedure. On the other hand, as opposed to CRFs which consume much less time after iteration 1, HM-SVMs take almost the same run time for all the iterations. Nevertheless, the total run time until convergence is almost the same for CRFs and HM-SVMs.

Bottom Line: The proposed framework can automatically induce derivation rules that map sentences to their semantic meaning representations.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.

View Article: PubMed Central - PubMed

Affiliation: School of Computer Science and Engineering, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University, Nanjing 210096, China.

ABSTRACT
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.

Show MeSH
Related in: MedlinePlus