activity
20162026
most citedBERT & Family Eat Word Salad: Experiments with Text Understanding

24 citations · 37 across the 31 of their papers we have counts for

collaborators
Showing 2021Show all

8 papers · 1 filter

cs.CL2021

Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords

Taelin Karidi, Yichu Zhou, Nathan Schneider +2

We present a method for exploring regions around individual points in a contextualized vector space (particularly, BERT space), as a way to investigate how these regions correspond…

cs.AI2021

Evaluating Relaxations of Logic for Neural Networks: A Comprehensive Study

Mattia Medina Grespan, Ashim Gupta, Vivek Srikumar

Symbolic knowledge can provide crucial inductive bias for training neural models, especially in low data regimes. A successful strategy for incorporating such knowledge involves re…

cs.CL2021

X-FACT: A New Benchmark Dataset for Multilingual Fact Checking

Ashim Gupta, Vivek Srikumar

In this work, we introduce X-FACT: the largest publicly available multilingual dataset for factual verification of naturally existing real-world claims. The dataset contains short…

cs.DB2021

Database Workload Characterization with Query Plan Encoders

Debjyoti Paul, Jie Cao, Feifei Li +1

Smart databases are adopting artificial intelligence (AI) technologies to achieve {\em instance optimality}, and in the future, databases will come with prepackaged AI models withi…

cs.CL20212 cited

DirectProbe: Studying Representations without Classifiers

Yichu Zhou, Vivek Srikumar

Understanding how linguistic structures are encoded in contextualized embedding could help explain their impressive performance across NLP@. Existing approaches for probing them us…

cs.CL20211 cited

Incorporating External Knowledge to Enhance Tabular Reasoning

J. Neeraja, Vivek Gupta, Vivek Srikumar

Reasoning about tabular information presents unique challenges to modern NLP approaches which largely rely on pre-trained contextualized embeddings of text. In this paper, we study…