知识图谱(KG)是一个多关系图,其中包含数以百万计的实体,以及连接实体的关系。知识图谱问答(Question Answering over Knowledge Graph, KGQA)是利用知识图谱信息的一项研究领域。给定一个自然语言问题和一个知识图谱,通过分析问题和 KG 中包含的信息,KGQA 系统尝试给出正确的答案。
多跳知识图谱问答指的是,该问答系统需要通过知识图谱上的多条边执行推理,以获得正确答案。
多跳知识图谱问答面临的挑战
知识图谱作为一种知识存储的形式,其中最重要的缺陷之一是它们通常都是不完整的,而这给 KGQA 提出了额外的挑战,尤其是多跳 KGQA。如上图所示,多跳 QA 需要一个长路径,而该路径上任意三元组的缺失都将导致真正的答案无法被搜索到。因此,采取某种方式预测知识图谱中缺失的链接,对于提升多跳 QA 的表现是有帮助的。当前缓解知识图谱不完整性的方法主要有:将 KG 与外部文本语料库结合,或者对知识图谱内的三元组进行补全等。
[1] The ́o Trouillon, Johannes Welbl, Sebastian Riedel, Eric Gaussier, and Guillaume Bouchard. 2016. Com- plex embeddings for simple link prediction. In In- ternational Conference on Machine Learning, pages 2071–2080.[2] Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Man- dar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining ap- proach. arXiv preprint arXiv:1907.11692.[3] Haitian Sun, Tania Bedrax-Weiss, and William W Co- hen. 2019a. Pullnet: Open domain question answer- ing with iterative retrieval on knowledge bases and text. arXiv preprint arXiv:1904.09537.[4] Alexander Miller, Adam Fisch, Jesse Dodge, Amir- Hossein Karimi, Antoine Bordes, and Jason Weston. 2016. Key-value memory networks for directly read- ing documents. arXiv preprint arXiv:1606.03126.[5] Yuyu Zhang, Hanjun Dai, Zornitsa Kozareva, Alexan- der J Smola, and Le Song. 2018. Variational reason- ing for question answering with knowledge graph. In Thirty-Second AAAI Conference on Artificial In- telligence.[6] Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, and William W Co- hen. 2018. Open domain question answering using early fusion of knowledge bases and text. arXiv preprint arXiv:1809.00782.[7] Haitian Sun, Tania Bedrax-Weiss, and William W Co- hen. 2019a. Pullnet: Open domain question answer- ing with iterative retrieval on knowledge bases and text. arXiv preprint arXiv:1904.09537.
[1] The ́o Trouillon, Johannes Welbl, Sebastian Riedel, Eric Gaussier, and Guillaume Bouchard. 2016. Com- plex embeddings for simple link prediction. In In- ternational Conference on Machine Learning, pages 2071–2080.
[2] Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Man- dar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining ap- proach. arXiv preprint arXiv:1907.11692.
[3] Haitian Sun, Tania Bedrax-Weiss, and William W Co- hen. 2019a. Pullnet: Open domain question answer- ing with iterative retrieval on knowledge bases and text. arXiv preprint arXiv:1904.09537.
[4] Alexander Miller, Adam Fisch, Jesse Dodge, Amir- Hossein Karimi, Antoine Bordes, and Jason Weston. 2016. Key-value memory networks for directly read- ing documents. arXiv preprint arXiv:1606.03126.
[5] Yuyu Zhang, Hanjun Dai, Zornitsa Kozareva, Alexan- der J Smola, and Le Song. 2018. Variational reason- ing for question answering with knowledge graph. In Thirty-Second AAAI Conference on Artificial In- telligence.
[6] Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, and William W Co- hen. 2018. Open domain question answering using early fusion of knowledge bases and text. arXiv preprint arXiv:1809.00782.
[7] Haitian Sun, Tania Bedrax-Weiss, and William W Co- hen. 2019a. Pullnet: Open domain question answer- ing with iterative retrieval on knowledge bases and text. arXiv preprint arXiv:1904.09537.