Enhancing biomedical word embeddings by retrofitting to verb clusters
SIGBIOMED WORKSHOP ON BIOMEDICAL NATURAL LANGUAGE PROCESSING (BIONLP 2019)(2019)
摘要
Verbs play a fundamental role in many biomedical tasks and applications such as relation and event extraction. We hypothesize that performance on many downstream tasks can be improved by aligning the input pretrained embeddings according to semantic verb classes. In this work, we show that by using semantic clusters for verbs, a large lexicon of verb classes derived from biomedical literature, we are able to improve the performance of common pretrained embeddings in downstream tasks by retrofitting them to verb classes. We present a simple and computationally efficient approach using a widely-available "off-the-shelf" retrofitting algorithm to align pretrained embeddings according to semantic verb clusters. We achieve state-of-the-art results on text classification and relation extraction tasks.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络