用可组合框架构建端到端的BERT问答与排序系统。
Composable NLP Workflows for BERT-based Ranking and QA System
- 基于Forte工具构建模块化自然语言处理流水线
- 在MS-MARCO和Covid-19数据集上达到先进性能
- 低延迟重排序器适合构建复杂真实应用
尽管已有大量进展实现多任务可扩展的NLP模型，但实际系统包含多个组件，跨任务交互在不同文本粒度下处理起来繁琐。本文基于Forte工具构建了一个端到端的排名与问答（QA）系统，集成BERT、RoBERTa等前沿深度学习模型，在MS-MARCO和Covid-19数据集上使用BLUE、MRR、F1等指标进行评估，并与基准结果对比。其模块化设计与低延迟重排序器使构建复杂NLP应用更加便捷。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。