2018/09/07 by Takashi Wada, Wada, Takashi, Tomoharu Iwata +1 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling #cs.AI #cs.CL #cs.LG
paper · pdf · doi:10.48550/arxiv.1809.02306
8 pages
arxiv created 2018/09/07 · openalex publication_date 2018/09/07 · arxiv updated 2018/09/10 · openalex created_date 2022/08/03 · openalex updated_date 2026/07/28
We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as an input. The proposed model contains bidirectional LSTMs that perform as forward and backward language models, and these networks are shared among all the languages. The other parameters, i.e. word embeddings and linear transformation between hidden states and outputs, are specific to each language. The shared LSTMs can capture the common sentence structure among all languages. Accordingly, word embeddings of each language are mapped into a common latent space, making it possible to measure the similarity of words across multiple languages. We evaluate the quality of the cross-lingual word embeddings on a word alignment task. Our experiments demonstrate that our model can obtain cross-lingual embeddings of much higher quality than existing unsupervised models when only a small amount of monolingual data (i.e. 50k sentences) are available, or the domains of monolingual data are different across languages.