Discourse Coherence

Introduction

1. What are a discourse and coherence?
   A discourse is a coherent structured group of sentences (an article, a conversation, a novel); coherence is the relationship between sentences that makes real discourses different from random assemblages of sentences.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 25, Introduction, p. 569
2. Why is “John took a train from Paris to Istanbul. He likes spinach.” incoherent?
   The reader can’t see why the second sentence follows the first, and tries to find a connection (a French spinach shortage?), which shows that comprehension involves establishing coherence. Compare “…She had to attend a conference”, a REASON.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 25, Introduction, p. 569
3. What are the three kinds of local coherence?
   Coherence relations between nearby sentences (e.g. REASON); entity-based coherence (being “about” salient entities rather than swinging between them); topical coherence (nearby sentences on the same topic, shown by lexical cohesion).
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 25, Introduction, p. 570
4. What is lexical cohesion?
   Sharing identical or semantically related words in nearby sentences (Halliday and Hasan 1976), e.g. house, chimney, garret, closet, window and a repeated shingled.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 25, Introduction, p. 570
5. What is global coherence? Give examples.
   Conventional discourse structure of whole texts in a genre: sections like Methodology and Results in academic articles, plotlines in stories, claims and premises in persuasive essays.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 25, Introduction, p. 570
6. What is coherence detection useful for?
   Measuring text quality (essay grading), summarization (choosing information by coherence relations), and mental health tasks like measuring symptoms of schizophrenia or other disordered language.
   • Jurafsky & Martin, Speech and Language Processing, 3rd ed. draft, ch. 25, Introduction, pp. 570–571