A Simple Yet Strong Pipeline for HotpotQA
This work challenges the need for complex designs in multi-hop QA, suggesting simpler methods can be effective, which is incremental for researchers and practitioners in natural language processing.
The paper tackled the problem of multi-hop question answering by showing that a simple pipeline based on BERT, named Quark, outperforms more complex models on HotpotQA, achieving strong performance in both question answering and support identification.
State-of-the-art models for multi-hop question answering typically augment large-scale language models like BERT with additional, intuitively useful capabilities such as named entity recognition, graph-based reasoning, and question decomposition. However, does their strong performance on popular multi-hop datasets really justify this added design complexity? Our results suggest that the answer may be no, because even our simple pipeline based on BERT, named Quark, performs surprisingly well. Specifically, on HotpotQA, Quark outperforms these models on both question answering and support identification (and achieves performance very close to a RoBERTa model). Our pipeline has three steps: 1) use BERT to identify potentially relevant sentences independently of each other; 2) feed the set of selected sentences as context into a standard BERT span prediction model to choose an answer; and 3) use the sentence selection model, now with the chosen answer, to produce supporting sentences. The strong performance of Quark resurfaces the importance of carefully exploring simple model designs before using popular benchmarks to justify the value of complex techniques.