Search Results for author:
Found 6 papers, 6 papers with code
Representation Deficiency in Masked Language Modeling
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.
Cross-Lingual Text Classification of Transliterated Hindi and Malayalam
Transliteration is very common on social media, but transliterated text is not adequately handled by modern neural models for various NLP tasks.
Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling
Predicting user intent and detecting the corresponding slots from text are two key problems in Natural Language Understanding (NLU).
Common-Knowledge Concept Recognition for SEVA
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.
Unsupervised and Interpretable Domain Adaptation to Rapidly Filter Tweets for Emergency Services
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.
Diversity-Based Generalization for Unsupervised Text Classification under Domain Shift
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.
