IBM just lately introduced the open-source library Textual content Extensions for Pandas, which options extensions that flip Pandas DataFrames right into a common knowledge construction that can be utilized in pure language processing (NLP).
Based on the corporate, the objective of this challenge is to make NLP easy. In creating the library, it wished to keep away from creating algorithms that navigate knowledge buildings based mostly on the outputs of NLP fashions, and as a substitute use Pandas DataFrames to signify NLP knowledge.
The library consists of Pandas extension sorts for representing pure language knowledge and library integrations that convert the outputs of NLP libraries into DataFrames.
Textual content Extensions for Pandas gives three key advantages: transparency, simplicity, and compatibility, based on IBM.
“This challenge aligns with IBM’s objective to repeatedly develop and ship new pure language processing improvements, each within the open supply neighborhood and thru merchandise like Watson Discovery and Watson Pure Language Understanding,” Frederick Reiss, chief architect at IBM Heart for Open-Supply Knowledge and AI applied sciences, and Willie M. Tejada, chief developer advocate at IBM, wrote in a publish.
As well as, Textual content Extensions for Pandas integrates with IBM Watson Pure Language Understanding and IBM Watson Uncover.