Abstract
One of the current state-of-the-art multilingual document embedding model is the bidirectional LSTM-based multilingual neural machine translation model (LASER). This paper presents a transformer-based sentence/document embedding model, T-LASER, which makes three significant improvements. Firstly, the BiLSTM encoder is replaced by the attention-based transformer structure, which is more capable of learning sequential patterns in longer texts. Secondly, due to the absence of recurrence, T-LASER enables faster parallel computations in the encoder to generate the text embedding. Thirdly, we augment the NMT translation loss function with an additional novel distance constraint loss. This distance constraint loss would further bring the embeddings of parallel sentences close together in the vector space; we call the T-LASER model trained with distance constraint, cT-LASER. Our cT-LASER model significantly outperforms both BiLSTM-based LASER and the simpler transformer-based T-LASER.
Abstract (translated)
URL
https://arxiv.org/abs/2008.08567
