VIP内容

题目

Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings,使用知识库嵌入改进知识图上的多跳问答

摘要

知识图(KG)是由实体作为节点,实体之间的关系作为类型化边组成的多关系图。 KG问答(KGQA)任务的目的是回答对KG提出的自然语言查询。 多跳KGQA要求在KG的多个边缘进行推理,以得出正确的答案。 KG通常缺少许多链接,这给KGQA尤其是多跳KGQA带来了额外的挑战。 最近对多跳KGQA的研究已尝试使用相关的外部文本来处理KG稀疏性,但这种方式并非一帆风顺。 在另一项研究中,提出了KG嵌入方法,以通过执行丢失的链接预测来减少KG稀疏性。 此类KG嵌入方法尽管非常相关,但迄今为止尚未针对多跳KGQA进行探索。 我们在本文中填补了这一空白,并提出了EmbedKGQA。 EmbedKGQA在执行稀疏KG上的多跳KGQA方面特别有效(但是当知识图谱不稀疏时,也应该能够超过基线)。 EmbedKGQA还放宽了从预先指定的邻域中选择答案的要求,这是先前的多跳KGQA方法实施的次优约束。 通过在多个基准数据集上进行的广泛实验,我们证明了EmbedKGQA在其他最新基准上的有效性。

成为VIP会员查看完整内容
翻译-2020使用知识库嵌入改进知识图上的多跳问答.pdf
0
46

最新内容

We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of automated metrics, datasets, and human evaluation standards. Due to this moving target, new models often still evaluate on divergent anglo-centric corpora with well-established, but flawed, metrics. This disconnect makes it challenging to identify the limitations of current models and opportunities for progress. Addressing this limitation, GEM provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested. Regular updates to the benchmark will help NLG research become more multilingual and evolve the challenge alongside models. This paper serves as the description of the data for which we are organizing a shared task at our ACL 2021 Workshop and to which we invite the entire NLG community to participate.

0
0
下载
预览

最新论文

We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of automated metrics, datasets, and human evaluation standards. Due to this moving target, new models often still evaluate on divergent anglo-centric corpora with well-established, but flawed, metrics. This disconnect makes it challenging to identify the limitations of current models and opportunities for progress. Addressing this limitation, GEM provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested. Regular updates to the benchmark will help NLG research become more multilingual and evolve the challenge alongside models. This paper serves as the description of the data for which we are organizing a shared task at our ACL 2021 Workshop and to which we invite the entire NLG community to participate.

0
0
下载
预览
Top