Metaknowledge Enhanced Open Domain Question Answering with Wiki Documents

Shukan Liu,Ruilin Xu,Mingjie Li,Li Duan,Yiming Liu

doi:10.3390/s21248439

Shukan Liu, Ruilin Xu + Show 3 more

Open Access

https://doi.org/10.3390/s21248439

Copy DOI

Abstract

The commonly-used large-scale knowledge bases have been facing challenges in open domain question answering tasks which are caused by the loose knowledge association and weak structural logic of triplet-based knowledge. To find a way out of this dilemma, this work proposes a novel metaknowledge enhanced approach for open domain question answering. We design an automatic approach to extract metaknowledge and build a metaknowledge network from Wiki documents. For the purpose of representing the directional weighted graph with hierarchical and semantic features, we present an original graph encoder GE4MK to model the metaknowledge network. Then, a metaknowledge enhanced graph reasoning model MEGr-Net is proposed for question answering, which aggregates both relational and neighboring interactions comparing with R-GCN and GAT. Experiments have proved the improvement of metaknowledge over main-stream triplet-based knowledge. We have found that the graph reasoning models and pre-trained language models also have influences on the metaknowledge enhanced question answering approaches.

Highlights

With the rapid development of the artificial intelligence, the voice interaction devices are becoming a significant application of the Internet, and the major Internet enterprises have all launched their own intelligent voice interaction devices
The results show that, with the same data quality, the hierarchical metaknowledge achieves better results than non-hierarchical triplet knowledge in open domain question answering
Ref. [38] proposes an embedding framework MINES for multi-dimensional networks with hierarchical structure, which uses a hierarchical structure for multi-dimensional network embedding; Ref. [37] proposes an open domain question answering method based on hyper-edge fusion

Summary

Introduction

With the rapid development of the artificial intelligence, the voice interaction devices are becoming a significant application of the Internet, and the major Internet enterprises have all launched their own intelligent voice interaction devices. Intelligent voice interaction has already been used as a new generation of Internet portal after the search engine. The prospect of intelligent voice interaction devices is extremely broad. As a pivotal infrastructure of the Metaverse, the future voice interaction devices must support simple information retrieval tasks, and have the capabilities of answering questions with complex semanteme and logicality, whereas current voice interaction devices are not able to deal with the complex application scenarios like open domain question answering. Open domain Question Answering (QA) is a type of language task that asks models to answer the factoid questions described in natural language.

Methods

Results

Discussion

Conclusion