Evaluating Sequence Alignment for Learning Inflectional Morphology

@inproceedings{King2016EvaluatingSA,
  title={Evaluating Sequence Alignment for Learning Inflectional Morphology},
  author={David L. King},
  booktitle={SIGMORPHON},
  year={2016}
}
  • David L. King
  • Published in SIGMORPHON 1 August 2016
  • Biology, Linguistics
This work examines CRF-based sequence alignment models for learning natural language morphology. Although these systems have performed well for a limited number of languages, this work, as part of the SIGMORPHON 2016 shared task, specifically sets out to determine whether these models handle non-concatenative morphology as well as previous work might suggest. Results, however, indicate a strong preference for simpler, concatenative morphological systems. 

Figures and Tables from this paper

Neural sequence-to-sequence models for low-resource morphology
TLDR
This thesis presents approaches to generate morphological inflections or analyze word forms through canonical segmentation through state-of-the art deep learning models and shows that similar languages can improve performance of morphological generation systems in low-resource settings.
Data Augmentation for Morphological Reinflection
TLDR
This paper presents the submission of the Linguistics Department of the University of Colorado at Boulder for the 2017 CoNLL-SIGMORPHON Shared Task on Universal Morphological Reinflection with substantial improvement in accuracy compared to a non-neural baseline system in presence of varying amounts of training data.
ISI at the SIGMORPHON 2017 Shared Task on Morphological Reinflection
TLDR
From the test set results, it is found that the proposed model beats the baseline on 15 out of the 52 languages in high resource scenario, but its performance is poor when the training set size is medium or low.
The SIGMORPHON 2016 Shared Task - Morphological Reinflection
TLDR
The 2016 SIGMORPHON Shared Task was devoted to the problem of morphological reinflection and introduced morphological datasets for 10 languages with diverse typological characteristics, showing a strong state of the art.
Computational Morphology with Neural Network Approaches
  • Ling Liu
  • Computer Science, Biology
    ArXiv
  • 2021
TLDR
The advantages and problems of neural network approaches to computational morphology are analyzed, and some directions to be explored by future research and study are pointed out.

References

SHOWING 1-10 OF 16 REFERENCES
Inflection Generation as Discriminative String Transduction
TLDR
Results of experiments demonstrate that the approach to morphological inflection generation as discriminative string transduction improves the state of the art in terms of predicting inflected word-forms.
Supervised Learning of Complete Morphological Paradigms
We describe a supervised approach to predicting the set of all inflected forms of a lexical item. Our system automatically acquires the orthographic transformation rules of morphological paradigms
The SIGMORPHON 2016 Shared Task - Morphological Reinflection
TLDR
The 2016 SIGMORPHON Shared Task was devoted to the problem of morphological reinflection and introduced morphological datasets for 10 languages with diverse typological characteristics, showing a strong state of the art.
Scaling conditional random fields for natural language processing
TLDR
This thesis addresses the issue of training efficiency by proposing two novel training methods, which both reduce the resource requirements and improve the scalability of training, such that CRFs can be applied to substantially larger tasks.
Applied morphological processing of English
TLDR
Two newly developed computational tools for morphological processing are described: a program for analysis of English inflectional morphology, and a morphological generator, automatically derived from the analyser, which are fast, being based on finite-state techniques, and robust, in that they are able to deal effectively with unknown words.
A General Computational Model For Word-Form Recognition And Production
TLDR
A language independent model for recognition and production of word forms is presented, based on a new way of describing morphological alternations that is capable of both analyzing and synthesizing word-forms.
Semi-Markov Conditional Random Fields for Information Extraction
TLDR
Intuitively, a semi-CRF on an input sequence x outputs a "segmentation" of x, in which labels are assigned to segments rather than to individual elements of xi, and transitions within a segment can be non-Markovian.
An Introduction to Conditional Random Fields
TLDR
This survey describes conditional random fields, a popular probabilistic method for structured prediction, and describes methods for inference and parameter estimation for CRFs, including practical issues for implementing large-scale CRFs.
Online Passive-Aggressive Algorithms
TLDR
This work presents a unified view for online classification, regression, and uni-class problems, and proves worst case loss bounds for various algorithms for both the realizable case and the non-realizable case.
A linear space algorithm for computing maximal common subsequences
The problem of finding a longest common subsequence of two strings has been solved in quadratic time and space. An algorithm is presented which will solve this problem in quadratic time and in linear
...
...