Text Graph
Jump to navigation
Jump to search
A Text Graph is a graph item that represents a text item.
- Context:
- It can (typically) have Text Graph Nodes to represent Syntactic Items or Semantic Items.
- It can (typically) have Text Graph Edges to represent Syntactic Relations or Semantic Relations.
- It can be an input to a Text Graph-based System (to solve a text graph-based task).
- Example(s):
- a Word Co-Occurrence Text Graph, showing word co-occurrence relations.
- Figure 7 in (Melli, 2010b).
- …
- Counter-Example(s):
- See: TextGraphs Workshop, Ali Baba System, Text Condensation, Term Disambiguation, Text Summarization, Textual Entailment.
References
2014
- (Wikipedia, 2014) ⇒ http://en.wikipedia.org/wiki/Text_graph Retrieved:2014-5-19.
- In natural language processing (NLP), a text graph is a graph representation of a text item (document, passage or sentence). It is typically created as a preprocessing step to support NLP tasks such as
text condensation term disambiguation (topic-based) text summarization[1] , relation extraction and textual entailment
- In natural language processing (NLP), a text graph is a graph representation of a text item (document, passage or sentence). It is typically created as a preprocessing step to support NLP tasks such as
- ↑ Cite error: Invalid
<ref>tag; no text was provided for refs namedmelli&al2006
2010
- (Melli, 2010b) ⇒ Gabor Melli. (2010). “Supervised Ontology to Document Interlinking..” Ph.D. Thesis, Simon Fraser University.
- Figure 7 - A sample of the text graph representation (for a highly summarized document) that SDOIRMI would use to create feature vectors for the task of relation mention identification.
- Figure 7 - A sample of the text graph representation (for a highly summarized document) that SDOIRMI would use to create feature vectors for the task of relation mention identification.
1988
- (Hahn & Reimer, 1988) ⇒ Udo Hahn, and Ulrich Reimer. (1988). “Automatic Generation of Hypertext Knowledge Bases.” In: Proceedings of the ACM SIGOIS and IEEECS TC-OA 1988 conference on Office information systems. ISBN:0-89791-261-6 doi:10.1145/966861.45429
- QUOTE: The topical structure of a text, finally, is represented in a hierarchical text graph which supports variable degrees of abstraction for text summarization as well as content-oriented retrieval of text knowledge. Due to their non-linear organization, text graphs share a lot of similarities with hypertexts.