CLLGJan 10, 2017

Implicitly Incorporating Morphological Information into Word Embedding

arXiv:1701.02481v31.316 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of improving word embeddings for natural language processing tasks, offering a novel approach that is incremental but shows strong gains.

The authors tackled the problem of enhancing word embeddings by implicitly incorporating morphological information, resulting in models that outperform state-of-the-art baselines on word similarity and syntactic analogy tasks, with performance on a small corpus matching that of CBOW on a corpus five times larger.

In this paper, we propose three novel models to enhance word embedding by implicitly using morphological information. Experiments on word similarity and syntactic analogy show that the implicit models are superior to traditional explicit ones. Our models outperform all state-of-the-art baselines and significantly improve the performance on both tasks. Moreover, our performance on the smallest corpus is similar to the performance of CBOW on the corpus which is five times the size of ours. Parameter analysis indicates that the implicit models can supplement semantic information during the word embedding training process.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes