Search Results for author:
Found 5 papers, 0 papers with code
NER-MQMRC: Formulating Named Entity Recognition as Multi Question Machine Reading Comprehension
We propose posing NER as a multi-question MRC task, where multiple questions (one question per entity) are considered at the same time for a single text.
Scalable Approach for Normalizing E-commerce Text Attributes (SANTA)
Experiments on a real-world attribute normalization dataset of 50 attributes show that the embeddings trained using our proposed approach obtain 2. 3% improvement over best string matching and 19. 3% improvement over best unsupervised embeddings.
LATEX-Numeric: Language Agnostic Text Attribute Extraction for Numeric Attributes
We propose a multi-task learning architecture to deal with missing labels in the training data, leading to F1 improvement of 9. 2{\%} for numeric attributes over state-of-the-art single-task architecture.
LaTeX-Numeric: Language-agnostic Text attribute eXtraction for E-commerce Numeric Attributes
We propose a multi-task learning architecture to deal with missing labels in the training data, leading to F1 improvement of 9. 2% for numeric attributes over single-task architecture.
Improving Answer Selection and Answer Triggering using Hard Negatives
In this paper, we establish the effectiveness of using hard negatives, coupled with a siamese network and a suitable loss function, for the tasks of answer selection and answer triggering.
