1 code implementation • 4 Feb 2023 • Yu Meng, Jitin Krishnan, Sinong Wang, Qifan Wang, Yuning Mao, Han Fang, Marjan Ghazvininejad, Jiawei Han, Luke Zettlemoyer
In this work, we offer a new perspective on the consequence of such a discrepancy: We demonstrate empirically and theoretically that MLM pretraining allocates some model dimensions exclusively for representing $\texttt{[MASK]}$ tokens, resulting in a representation deficiency for real tokens and limiting the pretrained model's expressiveness when it is adapted to downstream data without $\texttt{[MASK]}$ tokens.
1 code implementation • 31 Aug 2021 • Jitin Krishnan, Antonios Anastasopoulos, Hemant Purohit, Huzefa Rangwala
Transliteration is very common on social media, but transliterated text is not adequately handled by modern neural models for various NLP tasks.
1 code implementation • EMNLP (MRL) 2021 • Jitin Krishnan, Antonios Anastasopoulos, Hemant Purohit, Huzefa Rangwala
Predicting user intent and detecting the corresponding slots from text are two key problems in Natural Language Understanding (NLU).
1 code implementation • 26 Mar 2020 • Jitin Krishnan, Patrick Coronado, Hemant Purohit, Huzefa Rangwala
We build a common-knowledge concept recognition system for a Systems Engineer's Virtual Assistant (SEVA) which can be used for downstream tasks such as relation extraction, knowledge graph construction, and question-answering.
1 code implementation • 4 Mar 2020 • Jitin Krishnan, Hemant Purohit, Huzefa Rangwala
As deep networks struggle with sparse datasets, we show that this can be improved by sharing a base layer for multi-task learning and domain adversarial training.
1 code implementation • 25 Feb 2020 • Jitin Krishnan, Hemant Purohit, Huzefa Rangwala
At present, the state-of-the-art unsupervised domain adaptation approaches for subjective text classification problems leverage unlabeled target data along with labeled source data.