Composable NLP Workflows for BERT-based Ranking and QA System
This work addresses the tedious cross-task interaction in real-world NLP systems for developers, though it appears incremental as it applies existing models and toolkits to specific datasets.
The researchers tackled the problem of building complex NLP systems with multiple components by creating an end-to-end ranking and QA system using the Forte toolkit, achieving competitive performance on MS-MARCO and Covid-19 datasets with metrics like MRR and F1.
There has been a lot of progress towards building NLP models that scale to multiple tasks. However, real-world systems contain multiple components and it is tedious to handle cross-task interaction with varying levels of text granularity. In this work, we built an end-to-end Ranking and Question-Answering (QA) system using Forte, a toolkit that makes composable NLP pipelines. We utilized state-of-the-art deep learning models such as BERT, RoBERTa in our pipeline, evaluated the performance on MS-MARCO and Covid-19 datasets using metrics such as BLUE, MRR, F1 and compared the results of ranking and QA systems with their corresponding benchmark results. The modular nature of our pipeline and low latency of reranker makes it easy to build complex NLP applications easily.