activity
20152022
most citedTo Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of Dropout

26 citations · 32 across the 5 of their papers we have counts for

collaborators
Showing cs.CLShow all

11 papers · 1 filter

cs.CL20221 cited

NTULM: Enriching Social Media Text Representations with Non-Textual Units

Jinning Li, Shubhanshu Mishra, Ahmed El-Kishky +2

On social media, additional context is often present in the form of annotations and meta-data such as the post's author, mentions, Hashtags, and hyperlinks. We refer to these annot…

cs.CL20221 cited

CTM -- A Model for Large-Scale Multi-View Tweet Topic Classification

Vivek Kulkarni, Kenny Leung, Aria Haghighi

Automatically associating social media posts with topics is an important prerequisite for effective search and recommendation on many social media platforms. However, topic classif…

cs.CL2021

LMSOC: An Approach for Socially Sensitive Pretraining

Vivek Kulkarni, Shubhanshu Mishra, Aria Haghighi

While large-scale pretrained language models have been shown to learn effective linguistic representations for many NLP tasks, there remain many real-world contextual aspects of la…

cs.CL2019

What Should I Ask? Using Conversationally Informative Rewards for Goal-Oriented Visual Dialog

Pushkar Shukla, Carlos Elmadjian, Richika Sharan +3

The ability to engage in goal-oriented conversations has allowed humans to gain knowledge, reduce uncertainty, and perform tasks more efficiently. Artificial agents, however, are s…

cs.CL2018

MOHONE: Modeling Higher Order Network Effects in KnowledgeGraphs via Network Infused Embeddings

Hao Yu, Vivek Kulkarni, William Wang

Many knowledge graph embedding methods operate on triples and are therefore implicitly limited by a very local view of the entire knowledge graph. We present a new framework MOHONE…

cs.CL2018

DOLORES: Deep Contextualized Knowledge Graph Embeddings

Haoyu Wang, Vivek Kulkarni, William Yang Wang

We introduce a new method DOLORES for learning knowledge graph embeddings that effectively captures contextual cues and dependencies among entities and relations. First, we note th…