One-Shot Neural Cross-Lingual Transfer for Paradigm Completion
نویسندگان
چکیده
We present a novel cross-lingual transfer method for paradigm completion, the task of mapping a lemma to its inflected forms, using a neural encoder-decoder model, the state of the art for the monolingual task. We use labeled data from a high-resource language to increase performance on a lowresource language. In experiments on 21 language pairs from four different language families, we obtain up to 58% higher accuracy than without transfer and show that even zero-shot and one-shot learning are possible. We further find that the degree of language relatedness strongly influences the ability to transfer morphological knowledge.
منابع مشابه
Exploring Cross-Lingual Transfer of Morphological Knowledge In Sequence-to-Sequence Models
Multi-task training is an effective method to mitigate the data sparsity problem. It has recently been applied for crosslingual transfer learning for paradigm completion—the task of producing inflected forms of lemmata—with sequenceto-sequence networks. However, it is still vague how the model transfers knowledge across languages, as well as if and which information is shared. To investigate th...
متن کاملImproving Neural Knowledge Base Completion with Cross-Lingual Projections
In this paper we present a cross-lingual extension of a neural tensor network model for knowledge base completion. We exploit multilingual synsets from BabelNet to translate English triples to other languages and then augment the reference knowledge base with cross-lingual triples. We project monolingual embeddings of different languages to a shared multilingual space and use them for network i...
متن کاملModelling of Conventional and Severe Shot Peening Influence on Properties of High Carbon Steel via Artificial Neural Network
Shot peening (SP), as one of the severe plastic deformation (SPD) methods is employed for surface modification of the engineering components by improving the metallurgical and mechanical properties. Furthermore artificial neural network (ANN) has been widely used in different science and engineering problems for predicting and optimizing in the last decade. In the present study, effects of conv...
متن کاملCross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages
In cross-lingual dependency annotation projection, information is often lost during transfer because of early decoding. We present an end-to-end graph-based neural network dependency parser that can be trained to reproduce matrices of edge scores, which can be directly projected across word alignments. We show that our approach to cross-lingual dependency parsing is not only simpler, but also a...
متن کاملSemi-Supervised and Cross-Lingual Knowledge Transfer Learnings for DNN Hybrid Acoustic Models Under Low-Resource Conditions
Semi-supervised and cross-lingual knowledge transfer learnings are two strategies for boosting performance of lowresource speech recognition systems. In this paper, we propose a unified knowledge transfer learning method to deal with these two learning tasks. Such a knowledge transfer learning is realized by fine-tuning of Deep Neural Network (DNN). We demonstrate its effectiveness in both mono...
متن کامل