no code implementations • 15 Nov 2017 • Syed Sarfaraz Akhtar, Arihant Gupta, Avijit Vajpayee, Arjit Srivastava, Manish Shrivastava
We evaluate our method using small sized training sets on eleven test sets for the word similarity task across seven languages.
no code implementations • 15 Nov 2017 • Syed Sarfaraz Akhtar, Arihant Gupta, Avijit Vajpayee, Arjit Srivastava, Madan Gopal Jhawar, Manish Shrivastava
Our model handles the problem of data scarcity which is faced by many languages in the world and yields improved word embeddings for words in the target language by relying on transformed embeddings of words of the source language.
no code implementations • EMNLP 2017 • Arihant Gupta, Syed Sarfaraz Akhtar, Avijit Vajpayee, Arjit Srivastava, Madan Gopal Jhanwar, Manish Shrivastava
We present an unsupervised, language agnostic approach for exploiting morphological regularities present in high dimensional vector spaces.
no code implementations • WS 2017 • Syed Sarfaraz Akhtar, Arihant Gupta, Avijit Vajpayee, Arjit Srivastava, Manish Shrivastava
With the advent of word representations, word similarity tasks are becoming increasing popular as an evaluation metric for the quality of the representations.