A 2-phase frame-based knowledge extraction framework

Corcoglioniti, Francesco; Rospocher, Marco; Aprosio, Alessio Palmero

doi:10.1145/2851613.2851845

Cited by 19 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to its use of linguistic resources for ontological purposes, FrameBase has significant potential for text mining and other natural language related tasks. Both pure Semantic Role Labelling (SRL) systems for FrameNet such as SEMAFOR [9] as well as text-toontology systems such as FRED [49] and Pikes [7] could be adapted to produce FrameBase data from natural language text. Similar methods could also enable question answering [38].…”

Section: Resultsmentioning

confidence: 99%

FrameBase: Enabling integration of heterogeneous knowledge

Rouces

Melo

Hose

2017

View full text Add to dashboard Cite

Abstract. Large-scale knowledge graphs such as those in the Linked Open Data cloud are typically stored as subjectpredicate-object triples. However, many facts about the world involve more than two entities. While n-ary relations can be converted to triples in a number of ways, unfortunately, the structurally different choices made in different knowledge sources significantly impede our ability to connect them. They also increase semantic heterogeneity, making it impossible to query the data concisely and without prior knowledge of each individual source. This article presents FrameBase, a wide-coverage knowledge base schema that uses linguistic frames to represent and query n-ary relations from other knowledge bases, providing multiple levels of granularity connected via logical entailment. Overall, this provides a means for semantic integration from heterogeneous sources under a single schema and opens up possibilities to draw on natural language processing techniques for querying and data mining.

show abstract

Section: Resultsmentioning

confidence: 99%

FrameBase: Enabling integration of heterogeneous knowledge

Rouces

Melo

Hose

2017

View full text Add to dashboard Cite

show abstract

“…Since our approach supports both English and Italian, we adopt two different strategies, given that the NLP tools available for the two languages are very different and generally achieve better performance on English data. For English, we use the PIKES suite (Corcoglioniti et al, 2016): it first launches the Stanford Named Entity Recognizer (Finkel et al, 2005) to identify persons' mentions in the documents (e.g., "J. F. Kennedy, " "Lady Gaga, " etc. ), and then the Stanford Deterministic Coreference Resolution System (Manning et al, 2014) to set coreferential chains within each document.…”

Section: Preprocessingmentioning

confidence: 99%

Using Semantic Linking to Understand Persons’ Networks Extracted from Text

Aprosio

Tonelli

Menini

et al. 2017

Front. Digit. Humanit.

View full text Add to dashboard Cite

In this work, we describe a methodology to interpret large persons' networks extracted from text by classifying cliques using the DBpedia ontology. The approach relies on a combination of NLP, Semantic web technologies, and network analysis. The classification methodology that first starts from single nodes and then generalizes to cliques is effective in terms of performance and is able to deal also with nodes that are not linked to Wikipedia. The gold standard manually developed for evaluation shows that groups of co-occurring entities share in most of the cases a category that can be automatically assigned. This holds for both languages considered in this study. The outcome of this work may be of interest to enhance the readability of large networks and to provide an additional semantic layer on top of cliques. This would greatly help humanities scholars when dealing with large amounts of textual data that need to be interpreted or categorized. Furthermore, it represents an unsupervised approach to automatically extend DBpedia starting from a corpus.

show abstract

“…Only in case of text analysers automated entering is applied, but the amount of human participation in this process is not clear [18]- [21].…”

Section: B Related Work On Knowledge Frame Applicationmentioning

confidence: 99%

“…Integration with other knowledge representation systems is possible, e.g., with product rules and business constraints [31], OWL [17], [21], [31], fuzzy logic [26], and modal logic [29]. …”

Section: B Related Work On Knowledge Frame Applicationmentioning

confidence: 99%

The Knowledge Frame System based on Principles of Topological Functioning Model

Nazaruks

2017

Applied Computer Systems

View full text Add to dashboard Cite

-Understanding of domain phenomena and their interrelations is necessary for successful software development. The knowledge frame system based on principles of Topological Functioning Modelling (TFM) can be used for this purpose at the Computation Independent level within Model Driven Development. Research on knowledge formats showed that inferring in the closed world paradigm and similarity to the object-oriented paradigm made frames an attractive candidate to the knowledge representation format. Frames can hold information necessary for generation of the TFM. The knowledge system based on the principles of the TFM does not allow inferring ambiguous facts and leads to the more complete discovery of knowledge.

show abstract

A 2-phase frame-based knowledge extraction framework

Cited by 19 publications

References 10 publications

FrameBase: Enabling integration of heterogeneous knowledge

FrameBase: Enabling integration of heterogeneous knowledge

Using Semantic Linking to Understand Persons’ Networks Extracted from Text

The Knowledge Frame System based on Principles of Topological Functioning Model

Contact Info

Product

Resources

About