An Encoder-Decoder Approach to the Paradigm Cell Filling Problem
2018-10-01EMNLP 2018Code Available0· sign in to hype
Miikka Silfverberg, Mans Hulden
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/mpsilfve/pcfp-dataOfficialIn papernone★ 0
Abstract
The 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.