Search Results for author:
Found 8 papers, 2 papers with code
ITEm: Unsupervised Image-Text Embedding Learning for eCommerce
How to teach a model to learn embedding from different modalities without neglecting information from the less dominant modality is challenging.
Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token
We show: (1) [MASK]s can indeed be appended at a later layer, being disentangled from the word embedding; (2) The gathering of contextualized information from unmasked tokens can be conducted with a few layers.
Back-translation for Large-Scale Multilingual Machine Translation
Surprisingly, the smaller size of vocabularies perform better, and the extensive monolingual English data offers a modest improvement.
Word-based Domain Adaptation for Neural Machine Translation
Pre-training a model with word weights improves fine-tuning up to 1. 24% BLEU absolute and 1. 64% TER, respectively.
Towards Semantic Query Segmentation
Query Segmentation is one of the critical components for understanding users' search intent in Information Retrieval tasks.
