--- tags: - word2vec language: te license: gpl-3.0 --- ## Description Word embedding model trained by Al-Rfou et al. ## How to use? ``` import pickle from numpy import dot from numpy.linalg import norm from huggingface_hub import hf_hub_download words, embeddings = pickle.load(open(hf_hub_download(repo_id="Word2vec/polyglot_words_embeddings_en", filename="words_embeddings_en.pkl"), 'rb'),encoding="latin1") word = "Irish" a = embeddings[words.index(word)] most_similar = [] for i in range(len(embeddings)): if i != words.index(word): b = embeddings[i] cos_sim = dot(a, b)/(norm(a)*norm(b)) most_similar.append(cos_sim) else: most_similar.append(0) words[most_similar.index(max(most_similar))] ``` ## Citation ``` @InProceedings{polyglot:2013:ACL-CoNLL, author = {Al-Rfou, Rami and Perozzi, Bryan and Skiena, Steven}, title = {Polyglot: Distributed Word Representations for Multilingual NLP}, booktitle = {Proceedings of the Seventeenth Conference on Computational Natural Language Learning}, month = {August}, year = {2013}, address = {Sofia, Bulgaria}, publisher = {Association for Computational Linguistics}, pages = {183--192}, url = {http://www.aclweb.org/anthology/W13-3520} } ```