conftrace_

2018 EMNLP EMNLP 2018

An Encoder-Decoder Approach to the Paradigm Cell Filling Problem

Abstract

AbstractThe Paradigm Cell Filling Problem in morphology asks to complete word inflection tables from partial ones. We implement novel neural models for this task, evaluating them on 18 data sets in 8 languages, showing performance that is comparable with previous work with far less training data. We also publish a new dataset for this task and code implementing the system described in this paper.

Authors

Miikka Silfverberg, Mans Hulden

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Optimization & Theory > Neural Network Optimization Deep Learning > Architectures > Autoencoders

Keywords

sequence to sequence neural model word inflection morphological processing encoder decoder paradigm cell filling cell filling

More from EMNLP 2018

All EMNLP 2018 papers →

A Framework for Understanding the Role of Morphology in Universal Dependency Parsing

The Lazy Encoder: A Fine-Grained Analysis of the Role of Morphology in Neural Machine Translation

Imitation Learning for Neural Morphological String Transduction

Generating Natural Language Adversarial Examples

Multi-Head Attention with Disagreement Regularization

Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study