Incorporating Both Distributional and Relational Semantics in Word Representations
University of Arizona（亚利桑那大学）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）
英文摘要：
We investigate the hypothesis that word representations ought to incorporate both distributional and relational semantics. To this end, we employ the Alternating Direction Method of Multipliers (ADMM), which flexibly optimizes a distributional objective on raw text and a relational objective on WordNet. Preliminary results on knowledge base completion, analogy tests, and parsing show that word representations trained on both objectives can give improvements in some cases.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
