Fine-tuning Multi-hop Question Answering with Hierarchical Graph Network [article]

Guanming Xiong
<span title="2020-06-27">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we present a two stage model for multi-hop question answering. The first stage is a hierarchical graph network, which is used to reason over multi-hop question and is capable to capture different levels of granularity using the nature structure(i.e., paragraphs, questions, sentences and entities) of documents. The reasoning process is convert to node classify task(i.e., paragraph nodes and sentences nodes). The second stage is a language model fine-tuning task. In a word, stage
more &raquo; ... e use graph neural network to select and concatenate support sentences as one paragraph, and stage two find the answer span in language model fine-tuning paradigm.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="">arXiv:2004.13821v2</a> <a target="_blank" rel="external noopener" href="">fatcat:cl5z74cbzze2rkwjvqajhhugwe</a> </span>
<a target="_blank" rel="noopener" href="" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> </button> </a> <a target="_blank" rel="external noopener" href="" title=" access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> </button> </a>