Text Segment

A Text Segment is a contiguous substring of a text item.

• AKA: Chunk, Text Chunk, Text Span.
• Context:
  • It can be detected by a Text Chunking Task.
  • It can be in a Non-Overlapping Relation with other Text Chunks.
  • It can contain a Syntactic Phrase.
  • It can range from being a Short Text Segment (such as an orthographic word) to being a Long Text Segment (such as a passage).
• Example(s):
  • any Word Mention.
  • any Base Syntactic Phrase, such as a BaseNP Text Chunk.
  • any Concept Mention.
  • any Prosodic Text Chunk.
  • …
• Counter-Example(s):
  • a Text Summary.
  • a Semantic Role.
• See: Base NP.

---

---

References

1999

• (Tjong Kim Sang & Veenstra, 1999) ⇒ Erik Tjong Kim Sang, and Jorn Veenstra. (1999). “Representing Text Chunks.” In: Proceedings of EACL Conference (EACL 1999).

1995

• (Ramshaw & Marcus, 1995) ⇒ Lance A. Ramshaw, and Mitch P. Marcus. (1995). “Text Chunking Using Transformation-based Learning.” In: Proceedings of the Third ACL Workshop on Very Large Corpora (WVLC 1995).

1989

• (Abney, 1989) ⇒ Steven P. Abney. (1989). “Parsing By Chunks." The MIT Parsing Volume, 1988-89. Center for Cognitive Science, MIT.
  • I begin with an intuition: when I read a sentence, I read it a chunk at a time. For example, the previous sentence breaks up something like this:

    (1) [I begin] [with an intuition]: [when I read] [a sentence], [I read it] [a chunk] [at a time]

    These chunks correspond in some way to prosodic patterns.

---