activity
20202022
most citedDQI: Measuring Data Quality in NLP

7 citations · 17 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL20221 cited

Hardness of Samples Need to be Quantified for a Reliable Evaluation System: Exploring Potential Opportunities with a New Task

Swaroop Mishra, Anjana Arunkumar, Chris Bryan +1

Evaluation of models on benchmarks is unreliable without knowing the degree of sample hardness; this subsequently overestimates the capability of AI systems and limits their adopti…

cs.CL20221 cited

A Survey of Parameters Associated with the Quality of Benchmarks in NLP

Swaroop Mishra, Anjana Arunkumar, Chris Bryan +1

Several benchmarks have been built with heavy investment in resources to track our progress in NLP. Thousands of papers published in response to those benchmarks have competed to t…

cs.CL20204 cited

DQI: A Guide to Benchmark Evaluation

Swaroop Mishra, Anjana Arunkumar, Bhavdeep Sachdeva +2

A `state of the art' model A surpasses humans in a benchmark B, but fails on similar benchmarks C, D, and E. What does B have that the other benchmarks do not? Recent research prov…

cs.CL20204 cited

Our Evaluation Metric Needs an Update to Encourage Generalization

Swaroop Mishra, Anjana Arunkumar, Chris Bryan +1

Models that surpass human performance on several popular benchmarks display significant degradation in performance on exposure to Out of Distribution (OOD) data. Recent research ha…

cs.CL20207 cited

DQI: Measuring Data Quality in NLP

Swaroop Mishra, Anjana Arunkumar, Bhavdeep Sachdeva +2

Neural language models have achieved human level performance across several NLP datasets. However, recent studies have shown that these models are not truly learning the desired ta…