no code implementations • 25 Mar 2022 • Tasnim Mohiuddin, Philipp Koehn, Vishrav Chaudhary, James Cross, Shruti Bhosale, Shafiq Joty
In this work, we introduce a two-stage curriculum training framework for NMT where we fine-tune a base NMT model on subsets of data, selected by both deterministic scoring using pre-trained methods and online scoring that considers prediction scores of the emerging NMT model.
no code implementations • Findings (ACL) 2021 • Tasnim Mohiuddin, M Saiful Bari, Shafiq Joty
We show that AUGVIC helps to attenuate the discrepancies between relevant and distant-domain monolingual data in traditional back-translation.
no code implementations • 1 Jan 2021 • M Saiful Bari, Tasnim Mohiuddin, Shafiq Joty
Transfer learning has yielded state-of-the-art (SoTA) results in many supervised NLP tasks.
no code implementations • CL 2020 • Tasnim Mohiuddin, Shafiq Joty
Crosslingual word embeddings learned from monolingual embeddings have a crucial role in many downstream tasks, ranging from machine translation to transfer learning.
no code implementations • EACL 2021 • Tasnim Mohiuddin, Prathyusha Jwalapuram, Xiang Lin, Shafiq Joty
Although coherence modeling has come a long way in developing novel models, their evaluation on downstream applications for which they are purportedly developed has largely been neglected.
no code implementations • ACL 2021 • M Saiful Bari, Tasnim Mohiuddin, Shafiq Joty
We propose UXLA, a novel unsupervised data augmentation framework for zero-resource transfer learning scenarios.
no code implementations • EMNLP 2020 • Tasnim Mohiuddin, M Saiful Bari, Shafiq Joty
Most of the successful and predominant methods for bilingual lexicon induction (BLI) are mapping-based, where a linear mapping function is learned with the assumption that the word embedding spaces of different languages exhibit similar geometric structures (i. e., approximately isomorphic).
Bilingual Lexicon Induction Cross-Lingual Word Embeddings +1
no code implementations • IJCNLP 2019 • Han Cheol Moon, Tasnim Mohiuddin, Shafiq Joty, Xu Chi
In this paper, we propose a unified coherence model that incorporates sentence grammar, inter-sentence coherence relations, and global coherence patterns into a common neural framework.
1 code implementation • NAACL 2019 • Tasnim Mohiuddin, Shafiq Joty
Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space.
no code implementations • NAACL 2019 • Tasnim Mohiuddin, Thanh-Tung Nguyen, Shafiq Joty
We address the problem of speech act recognition (SAR) in asynchronous conversations (forums, emails).
no code implementations • CL 2018 • Shafiq Joty, Tasnim Mohiuddin
Participants in an asynchronous conversation (e. g., forum, e-mail) interact with each other at different times, performing certain communicative acts, called speech acts (e. g., question, request).
1 code implementation • ACL 2018 • Tasnim Mohiuddin, Shafiq Joty, Dat Tien Nguyen
We propose a novel coherence model for written asynchronous conversations (e. g., forums, emails), and show its applications in coherence assessment and thread reconstruction tasks.