KnowGL Knowledge Generation and Linking from Text Gaetano Rossiello Md. Faisal Mahbub Chowdhury Nandana Mihindukulasooriya Owen Cornec Alﬁo Massimiliano Gliozzo

2025-05-03 0 0 151.9KB 3 页 10玖币

侵权投诉

KnowGL: Knowledge Generation and Linking from Text

Gaetano Rossiello*, Md. Faisal Mahbub Chowdhury*, Nandana Mihindukulasooriya,

Owen Cornec, Alﬁo Massimiliano Gliozzo

IBM Research AI

Thomas J. Watson Research Center, NY

Abstract

We propose KnowGL, a tool that allows converting text into

structured relational data represented as a set of ABox asser-

tions compliant with the TBox of a given Knowledge Graph

(KG), such as Wikidata. We address this problem as a se-

quence generation task by leveraging pre-trained sequence-

to-sequence language models, e.g. BART. Given a sentence,

we ﬁne-tune such models to detect pairs of entity mentions

and jointly generate a set of facts consisting of the full set of

semantic annotations for a KG, such as entity labels, entity

types, and their relationships. To showcase the capabilities of

our tool, we build a web application consisting of a set of

UI widgets that help users to navigate through the semantic

data extracted from a given input text. We make the KnowGL

model available at https://huggingface.co/ibm/knowgl-large.

Introduction and Related Work

A Knowledge Graph (KG) is deﬁned as a semantic net-

work where entities, such as objects, events or concepts, are

connected between them through relationships or properties.

KGs are organized in multi-graph data structures and stored

as a set of triples (or facts), i.e. (SUBJECT, RELATION, OB-

JECT), grounded with a given well-deﬁned ontology (Hogan

et al. 2021). The usage of formal languages to represent

KGs enables unambiguous access to data and facilitates au-

tomatic reasoning capabilities that enhance downstream ap-

plications, such as analytics, knowledge discovery or recom-

mendations (Mihindukulasooriya et al. 2022).

However, building and curating KGs, such as Wiki-

data (Vrandeˇ

ci´

c and Kr¨

otzsch 2014), requires a considerable

human effort. Systems such as, NELL (Carlson et al. 2010),

DeepDive (Niu et al. 2012), Knowledge Vault (Dong et al.

2014), DiffBot (de S´

a Mesquita et al. 2019) implement In-

formation Extraction (IE) methods for automatic knowledge

base population. A standard IE pipeline consists of several

steps, such as co-reference resolution (Dobrovolskii 2021),

named entity recognition (Wang et al. 2021), relation extrac-

tion (Zhong and Chen 2021), and entity liking (Wu et al.

2020), each of which is commonly addressed as a separate

task. A pipeline approach presents several limitations, e.g.

*Equal contributions.

KnowGL Parser

Generation

Ranking

Linking

KnowGL

(Encoder-Decoder)

For the semantic web to function, computers

must have access to structured collections of

information and sets of inference rules.

[{

"subject": {

"mention": "semantic web",

"entity_label": "Semantic Web",

"type_label": "academic discipline",

"entity_link": "Q54837",

"type_link": "Q11862829"

"relation": {

"label": "uses",

"link": "Property:P2283"

"object": {

"mention": "inference rules",

"entity_label": "inference",

"type_label": "process",

"entity_link": "Q408386",

"type_link": "Q619671"

"score": -0.98

}]

Figure 1: KnowGL Parser Framework

error propagation among different IE components and com-

plex deployment procedures. Moreover, each component of

the pipeline is trained independently using different archi-

tectures and training sets.

The ability of generating structured data from text

makes sequence-to-sequence Pre-trained Language Models

(PLMs), such as BART (Lewis et al. 2020) or T5 (Raffel

arXiv:2210.13952v5 [cs.CL] 22 Nov 2022

文档加载中……请稍候！
如果长时间未打开，您也可以点击刷新试试。

下载文档到电脑，查找使用更方便

10 玖币 0人已下载

立即下载

摘要：

KnowGL:KnowledgeGenerationandLinkingfromTextGaetanoRossiello*,Md.FaisalMahbubChowdhury*,NandanaMihindukulasooriya,OwenCornec,AloMassimilianoGliozzoIBMResearchAIThomasJ.WatsonResearchCenter,NYAbstractWeproposeKnowGL,atoolthatallowsconvertingtextintostructuredrelationaldatarepresentedasasetofABoxasse...

展开>> 收起<<

KnowGL Knowledge Generation and Linking from Text Gaetano Rossiello Md. Faisal Mahbub Chowdhury Nandana Mihindukulasooriya Owen Cornec Alﬁo Massimiliano Gliozzo.pdf

共3页,预览1页

还剩页未读，继续阅读

声明：本站为文档C2C交易模式，即用户上传的文档直接被用户下载，本站只是中间服务平台，本站所有文档下载所得的收益归上传人(含作者)所有。玖贝云文库仅提供信息存储空间，仅对用户上传内容的表现方式做保护处理，对上载内容本身不做任何修改或编辑。若文档所含内容侵犯了您的版权或隐私，请立即通知玖贝云文库，我们立即给予删除！

KnowGL Knowledge Generation and Linking from Text Gaetano Rossiello Md. Faisal Mahbub Chowdhury Nandana Mihindukulasooriya Owen Cornec Alﬁo Massimiliano Gliozzo

相关推荐

开通VIP享超值会员特权

作者详情

相关内容

热门标签

举报选择: