Researchers develop question-answering dataset for evaluating NLP tools for COVID-19

April 28, 2020
by Cole McCollum
Very important

In a preprint paper, researchers from the University of Waterloo and other organizations used the COVID-19 Open Research Dataset (CORD-19) to develop a question answering dataset to evaluate the information retrieval capabilities of NLP tools. The dataset included 124 question-answering pairs, which consisted of keyword searches and natural language questions associated with the text containing the answer in a document. As the dataset was too small for training models from scratch, the best-performing models tested against the benchmark used transfer learning to fine-tune unsupervised NLP models. Clients should expect efforts like these and the forthcoming effort from NIST to play a key role in improving AI tools used for COVID-19 research.

For the original news article, click here .

Further Reading

Tecton raises $20 million to provide a data platform for scaling machine learning

News Commentary | May 11, 2020

Founded by the creators of Uber's machine learning platform, Tecton aims to provide organizations with a similar platform to help them operationalize their data for machine learning applications. One of the most challenging parts of deploying machine learning is building scalable data pipelines and ... Not part of subscription

The role of AI in fighting COVID-19: Sifting through the hype

Analyst Insight | May 12, 2020

Many have identified AI and machine learning as potential tools in the fight against COVID‑19. However, as in most discussions involving AI, there's significant hype around the topic, making it difficult for organizations to determine where to focus their efforts. In this insight, we examine various... Not part of subscription

FedEx partners with Microsoft for the cloud; launches FedEx Surround for logistics visibility

News Commentary | May 19, 2020

FedEx and Microsoft have signed a multiyear agreement for building digital solutions for logistics. The solutions will be hosted on Azure and will leverage FedEx's subject matter expertise and infrastructure for identifying customer pain points and opportunities. The duo also launched their first ... Not part of subscription