EAL: A Toolkit and Dataset for Entity-Aspect Linking

Nanni, Federico; Zhang, Jingyi; Betz, Ferdinand; Gashteovski, Kiril

doi:10.1109/jcdl.2019.00104

Cited by 4 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Open Information Extraction and Knowledge Graphs. The context of OIE facts is used for many tasks for knowledge graphs, such as knowledge graph population (Broscheit et al, 2017;Lin et al, 2020;Zopf and Gashteovski, 2023), (open) link prediction (Broscheit et al, 2020;Kotnis et al, 2023), entity linking (Nanni et al, 2019) and entity alignment (Friede and Gashteovski, 2022). Therefore, the task of OIE fact linking to KGs is of great importance, as OIE facts can provide knowledge that is outside of the KG schema, as well as knowledge that aligns with the KG schema (Gashteovski et al, 2020b).…”

Section: A Detailed Discussion On Related Workmentioning

confidence: 99%

Linking Surface Facts to Large-Scale Knowledge Graphs

Radevski,

Gashteovski,

Hung

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Open Information Extraction (OIE) methods extract facts from natural language text in the form of ("subject"; "relation"; "object") triples. These facts are, however, merely surface forms, the ambiguity of which impedes their downstream usage; e.g., the surface phrase "Michael Jordan" may refer to either the former basketball player or the university professor. Knowledge Graphs (KGs), on the other hand, contain facts in a canonical (i.e., unambiguous) form, but their coverage is limited by a static schema (i.e., a fixed set of entities and predicates). To bridge this gap, we need the best of both worlds: (i) high coverage of free-text OIEs, and (ii) semantic precision (i.e., monosemy) of KGs. In order to achieve this goal, we propose a new benchmark with novel evaluation protocols that can, for example, measure fact linking performance on a granular triple slot level, while also measuring if a system has the ability to recognize that a surface form has no match in the existing KG. Our extensive evaluation of several baselines shows that detection of out-of-KG entities and predicates is more difficult than accurate linking to existing ones, thus calling for more research efforts on this difficult task. We publicly release all resources (data, benchmark and code) 1 .

show abstract

Section: A Detailed Discussion On Related Workmentioning

confidence: 99%

Linking Surface Facts to Large-Scale Knowledge Graphs

Radevski,

Gashteovski,

Hung

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…Their work is accompanied by a manually verified aspect linking dataset of only 201 instances semi-automatically derived from Wikipedia sections. Follow-up work [13] includes an online demo. We complement their work with a large dataset and reproducible evaluation protocol to support more research on entity aspect linking.…”

Section: Related Work and Datasetsmentioning

confidence: 99%

A Large Test Collection for Entity Aspect Linking

Ramsdell

Dietz

2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Given a text with entity links, the task of entity aspect linking is to identify which aspect of an entity is referred to in the context. For example, if a text passage mentions the entity "USA", is USA mentioned in the context of the 2008 financial crisis, American cuisine, or else? Complementing efforts of Nanni et al (2018), we provide a large-scale test collection which is derived from Wikipedia hyperlinks in a dump from 01/01/2020. Furthermore, we offer strong baselines with results and broken-out feature sets to stimulate more research in this area. Data, code, feature sets, runfiles and results are released under a CC-SA license and offered on our aspect linking resource web page

show abstract

“…A."). Such triples are used in downstream tasks, such as word embeddings generation (Stanovsky et al, 2015), information retrieval (Kadry and Dietz, 2017) and entity aspect linking (Nanni et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

On Aligning OpenIE Extractions with Knowledge Bases: A Case Study

Gashteovski¹,

Gemulla²,

Kotnis³

et al. 2020

Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems

Self Cite

View full text Add to dashboard Cite

Open information extraction (OIE) is the task of extracting relations and their corresponding arguments from natural language text in unsupervised manner. Outputs of such systems are used for downstream tasks such as question answering and automatic knowledge base (KB) construction. Many of these downstream tasks rely on aligning OIE triples with reference KBs. Such alignments are usually evaluated w.r.t. a specific downstream task and, to date, no direct manual evaluation of such alignments has been performed. In this paper, we directly evaluate how OIE triples from the OPIEC corpus are related to the DBpedia KB w.r.t. information content. First, we investigate OPIEC triples and DBpedia facts having the same arguments by comparing the information on the OIE surface relation with the KB relation. Second, we evaluate the expressibility of general OPIEC triples in DBpedia. We investigate whether-and, if so, how-a given OIE triple can be mapped to a single KB fact. We found that such mappings are not always possible because the information in the OIE triples tends to be more specific. Our evaluation suggests, however, that significant part of OIE triples can be expressed by means of KB formulas instead of individual facts.

show abstract

EAL: A Toolkit and Dataset for Entity-Aspect Linking

Cited by 4 publications

References 4 publications

Linking Surface Facts to Large-Scale Knowledge Graphs

Linking Surface Facts to Large-Scale Knowledge Graphs

A Large Test Collection for Entity Aspect Linking

On Aligning OpenIE Extractions with Knowledge Bases: A Case Study

Contact Info

Product

Resources

About