Papers by Ashish Upadhyay

3 papers
News Risk Alerting System (NRAS): A Data-Driven LLM Approach to Proactive Credit Risk Monitoring (2024.emnlp-industry)

Copied to clipboard

Challenge: Credit risk monitoring is an essential process for financial institutions to evaluate the creditworthiness of borrowing entities.
Approach: They propose a system which proactively alerts Credit Officers to credit-relevant news events . the system has been deployed for nearly three years and has an estimated precision of 77% .
Outcome: The new system has alerted Credit Officers to over 2700 credit-relevant events with an estimated precision of 77%.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)

Copied to clipboard

Challenge: Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work.
Approach: They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations.
Outcome: The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work.
Content Type Profiling of Data-to-Text Generation Datasets (2022.coling-1)

Copied to clipboard

Challenge: Data-to-Text Generation (D2T) problems can be seen as a stream of time-stamped events with a textual summary of each event presenting the insights.
Approach: They propose a typology of content types to classify the contents of event summaries using a dataset as the distribution of the aggregated content types.
Outcome: The proposed typology shows that neural systems struggle in generating complex types on different datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations