Embedding Wikipedia Title based on Its Wikipedia Text and Categories
Authors | Chi-Yen Chen Wei-Yun Ma |
|---|---|
Publication date | 2017 |
DOI | 10.1109/ialp.2017.8300566 |
Links | Original |
Embedding Wikipedia Title based on Its Wikipedia Text and Categories - scientific work related to Wikipedia quality published in 2017, written by Chi-Yen Chen and Wei-Yun Ma.
Overview
Distributed word representation is widely used in many NLP tasks and knowledge-based resources also provide valuable information. Comparing to conventional knowledge bases, Wikipedia provides semi-structural data other than structural data. Authors argue that a Wikipedia title's categories can help complement the title's meaning besides Wikipedia text, so the categories should be utilized to improve the title's embedding. Authors propose two directions of using categories, cooperating with conventional context-based approaches, to generate embeddings of Wikipedia titles. Authors conduct extensively large scale experiments on the generated title embeddings on Chinese Wikipedia. Experiments on word similarity task and analogical reasoning task show that approaches significantly outperform conventional context-based approaches.
Embed
Wikipedia Quality
Chen, Chi-Yen; Ma, Wei-Yun. (2017). "[[Embedding Wikipedia Title based on Its Wikipedia Text and Categories]]".DOI: 10.1109/ialp.2017.8300566.
English Wikipedia
{{cite journal |last1=Chen |first1=Chi-Yen |last2=Ma |first2=Wei-Yun |title=Embedding Wikipedia Title based on Its Wikipedia Text and Categories |date=2017 |doi=10.1109/ialp.2017.8300566 |url=https://wikipediaquality.com/wiki/Embedding_Wikipedia_Title_based_on_Its_Wikipedia_Text_and_Categories}}
HTML
Chen, Chi-Yen; Ma, Wei-Yun. (2017). "<a href="https://wikipediaquality.com/wiki/Embedding_Wikipedia_Title_based_on_Its_Wikipedia_Text_and_Categories">Embedding Wikipedia Title based on Its Wikipedia Text and Categories</a>".DOI: 10.1109/ialp.2017.8300566.
