337 citations · 479 across the 29 of their papers we have counts for
4 papers · 1 filter
GIRNet: Interleaved Multi-Task Recurrent State Sequence Models
Divam Gupta, Tanmoy Chakraborty, Soumen Chakrabarti
In several natural language tasks, labeled sequences are available in separate domains (say, languages), but the goal is to label sequences with mixed domain (such as code-switched…
New Embedded Representations and Evaluation Protocols for Inferring Transitive Relations
Sandeep Subramanian, Soumen Chakrabarti
Beyond word embeddings, continuous representations of knowledge graph (KG) components, such as entities, types and relations, are widely used for entity mention disambiguation, rel…
Generalizing Across Domains via Cross-Gradient Training
Shiv Shankar, Vihari Piratla, Soumen Chakrabarti +3
We present CROSSGRAD, a method to use multi-domain training data to learn a classifier that generalizes to new domains. CROSSGRAD does not need an adaptation phase via labeled or u…
Automated Early Leaderboard Generation From Comparative Tables
Mayank Singh, Rajdeep Sarkar, Atharva Vyas +3
A leaderboard is a tabular presentation of performance scores of the best competing techniques that address a specific scientific problem. Manually maintained leaderboards take tim…