Improving sequence segmentation learning by predicting trigrams

A. van den Bosch, W. Daelemans

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    9 Citations (Scopus)
    118 Downloads (Pure)


    Symbolic machine-learning classifiers are known to suffer from near-sightedness when performing sequence segmentation (chunking) tasks in natural language processing: without special architectural additions they are oblivious of the decisions they made earlier when making new ones. We introduce a new pointwise-prediction single-classifier method that predicts trigrams of class labels on the basis of windowed input sequences, and uses a simple voting mechanism to decide on the labels in the final output sequence. We apply the method to maximum-entropy, sparse winnow, and memory-based classifiers using three different sentence-level chunking tasks, and show that the method is able to boost generalization performance in most experiments, attaining error reductions of up to 51%. We compare and combine the method with two known alternative methods to combat near-sightedness, viz. a feedback-loop method and a stacking method, using the memory-based classifier. The combination with a feedback loop suffers from the label bias problem, while the combination with a stacking method produces the best overall results.
    Original languageEnglish
    Title of host publicationProceedings of the Ninth Conference on Natural Language Learning, CONLL-2005, June 29-30
    EditorsI. Dagan, D. Gildea
    Place of PublicationAnn Arbor, MI
    Number of pages8
    Publication statusPublished - 2005


    Dive into the research topics of 'Improving sequence segmentation learning by predicting trigrams'. Together they form a unique fingerprint.
    • Optimization in machine learning of language

      Daelemans, W. M. P.


      Project: Research project

    • Memory models of language

      van den Bosch, A.


      Project: Research project

    Cite this