CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Set Generation Networks for End-to-End Knowledge Base Population
Sui DB(隋典伯)1,2; Chenhao Wang1,2; Yubo Chen1,2; Kang Liu1,2; Jun Zhao1,2; Wei Bi3
2021-11
会议名称Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
会议日期2021-11
会议地点Online and Punta Cana, Dominican Republic
摘要

The task of knowledge base population (KBP) aims to discover facts about entities from texts and expand a knowledge base with these facts. Previous studies shape end-to-end KBP as a machine translation task, which is required to convert unordered fact into a sequence according to a pre-specified order. However, the facts stated in a sentence are unordered in essence. In this paper, we formulate end-to-end KBP as a direct set generation problem, avoiding considering the order of multiple facts. To solve the set generation problem, we propose networks featured by transformers with non-autoregressive parallel decoding. Unlike previous approaches that use an autoregressive decoder to generate facts one by one, the proposed networks can directly output the final set of facts in one shot. Furthermore, to train the networks, we also design a set-based loss that forces unique predictions via bipartite matching. Compared with cross-entropy loss that highly penalizes small shifts in fact order, the proposed bipartite matching loss is invariant to any permutation of predictions. Benefiting from getting rid of the burden of predicting the order of multiple facts, our proposed networks achieve state-of-the-art (SoTA) performance on two benchmark datasets.

文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/48934
专题模式识别国家重点实验室_自然语言处理
作者单位1.National Laboratory of Pattern Recognition, Institute of Automation, CAS
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
3.Tencent AI Lab
第一作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
Sui DB,Chenhao Wang,Yubo Chen,et al. Set Generation Networks for End-to-End Knowledge Base Population[C],2021.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
2021.emnlp-main.760.(552KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Sui DB(隋典伯)]的文章
[Chenhao Wang]的文章
[Yubo Chen]的文章
百度学术
百度学术中相似的文章
[Sui DB(隋典伯)]的文章
[Chenhao Wang]的文章
[Yubo Chen]的文章
必应学术
必应学术中相似的文章
[Sui DB(隋典伯)]的文章
[Chenhao Wang]的文章
[Yubo Chen]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 2021.emnlp-main.760.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。