no code implementations • 22 Oct 2023 • Baohao Liao, Michael Kozielski, Sanjika Hewavitharana, Jiangbo Yuan, Shahram Khadivi, Tomer Lancewicki
How to teach a model to learn embedding from different modalities without neglecting information from the less dominant modality is challenging.
1 code implementation • 9 Nov 2022 • Baohao Liao, David Thulke, Sanjika Hewavitharana, Hermann Ney, Christof Monz
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.
1 code implementation • WMT (EMNLP) 2021 • Baohao Liao, Shahram Khadivi, Sanjika Hewavitharana
Surprisingly, the smaller size of vocabularies perform better, and the extensive monolingual English data offers a modest improvement.
no code implementations • IWSLT (EMNLP) 2018 • Shen Yan, Leonard Dahlmann, Pavel Petrushkov, Sanjika Hewavitharana, Shahram Khadivi
Pre-training a model with word weights improves fine-tuning up to 1. 24% BLEU absolute and 1. 64% TER, respectively.
no code implementations • 25 Jul 2017 • Ajinkya Kale, Thrivikrama Taula, Sanjika Hewavitharana, Amit Srivastava
Query Segmentation is one of the critical components for understanding users' search intent in Information Retrieval tasks.