On Approximately Searching for Similar Word Embeddings
ACL2016 (the annual meeting of the Association for Computational Linguistics), to appear, 2016/8
自然言語処理 (Natural Language Processing) 情報検索 (Information Retrieval) 機械学習 (Machine Learning)
- We discuss an approximate similarity search for word embeddings, which is an operation to approximately find embeddings close to a given vector. We compared several metric-based search algorithms with hash-, tree-, and graph- based indexing from different aspects. Our experimental results showed that a graph-based indexing exhibits robust performance and additionally provided useful information, e.g., vector normalization achieves an efficient search with cosine similarity.
On Approximately Searching for Similar Word Embeddings（外部サイト／External Site Link）