KeypartX: Graph-based Perception (Text) Representation

@article{Yang2022KeypartXGP,
  title={KeypartX: Graph-based Perception (Text) Representation},
  author={Peng Yang},
  journal={ArXiv},
  year={2022},
  volume={abs/2209.11844}
}
  • Peng Yang
  • Published 23 September 2022
  • Computer Science
  • ArXiv
The availability of big data has opened up big opportunities for individuals, businesses and academics to view big into what is happening in their world. Previous works of text representation mostly focused on informativeness from massive words ’ frequency or cooccurrence. However, big data is a double-edged sword which is big in volume but unstructured in format. The unstructured edge requires specific techniques to transform ‘big’ into meaningful instead of informative alone. This study… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 28 REFERENCES

Graph-based text representation and knowledge discovery

This paper proposes a graph-based text representation, which is capable of capturing Term order, Term frequency, and Term co-occurrence in documents and applies the graph model into the text mining task,Which is to discover unapparent associations between two and more concepts from a large text corpus.

Semantic Representations in Text Data

This article gives a broad and synthesized description of various forms of text representations, presented in their chronological order ranging from BoW models to the most recent embeddings learning, to provide valuable pointers for researchers looking to work in the field of semantic representations.

ENHANCING TEXT REPRESENTATION FOR CLASSIFICATION TASKS WITH SEMANTIC GRAPH STRUCTURES

A novel graph similarity algorithm is developed by extracting the maximum common subgraph between two concerned graphs, which can therefore be used to measure the distance between two graph structures, i.e., two texts, and further be applied to classification tasks.

Measuring Term Informativeness in Context

This paper proposes a new lightweight feature-free approach to encode term informativeness in context by leveraging web knowledge based on semantic similarity between the context and the term’s most featured context in a knowledge base, Wikipedia.

Graph-Based Text Representation and Matching: A Review of the State of the Art and Future Challenges

This study proposes a new taxonomy of graph-based text representation, categorizing the existing studies based on representation characteristics and scheme techniques, and introduces four main types of conceptual graph schemes and summarizes the challenges faced in each scheme.

Learning Semantic Graph Mapping for Document Summarization

We present a method for summarizing document by creating a semantic graph of the original document and identifying the substructure of such a graph that can be used to extract sentences for a

InfraNodus: Generating Insight Using Text Network Analysis

The tool (InfraNodus) can be used by researchers and writers to organize and to better understand their notes, to measure the level of bias in discourse, and to identify the parts of the discourse where there is a potential for insight and new ideas.

Graph based Representation and Analysis of Text Document: A Survey of Techniques

The survey results shows that Graph based representation is appropriate way of representing text document and improved result of analysis over traditional model for different text applications.

Construction of Conceptual Graph Representation of Texts

This paper uses a two-step approach, by firstly identifying the semantic roles in a sentence, and then using these roles, together with semi-automatically compiled domain-specific knowledge to construct the conceptual graph representation.

Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space

This work proposes an approach to adjective-noun composition (AN) for corpus-based distributional semantics that represents nouns as vectors and adjectives as data-induced (linear) functions over nominal vectors, and shows that the model significantly outperforms the rivals on the task of reconstructing AN vectors not seen in training.