Some computational experiments in summarization
Bibliographic Data
| ID | 11272885 |
|---|---|
| Authors | Richard Alterman (0000-0002-3829-6068, Brandeis University, corresponding author), Lawrence A Bookman (Brandeis University) |
| Year | 1990 |
| Volume | 13 |
| Issue | 2 |
| Pages | 143-174 |
| Publication date | 1990-04-01 |
| Open Access | No |
| Type | ARTICLE |
| Venue | Discourse Processes (JOURNAL) |
| Journal identifiers | ISSN: 0163-853X • E-ISSN: 1532-6950 |
| Publisher | Informa UK Limited (PUBLISHER • GB) |
| DOI | 10.1080/01638539009544751 |
| OpenAlex | W2050387210 |
| Language | EN |
| Citations received | 2 |
| References cited | 23 |
This paper relates the question of narrative summarization to thickness. Roughly, thickness refers to the density of inferred relations between concepts in the narrative as they persist during the reading of the text. We will describe a summarizer, SSS, that takes a piece of text and simplifies it—dethickens it—to produce a description of the events depicted in that text. SSS bases its summary of the story on an event concept coherence (ECC) analysis produced by a program called NEXUS. This program sorts through the events of the story, introducing the implicit ones, grouping together events based largely on their relative positions in an underlying conceptual network. The resulting ECC representation characterizes the complex of relations that exist between the events in the text by a network of instantiated event concepts from which a summary can be produced. In addition to describing some of the inner workings of SSS and the theory of event concept coherence, this paper will develop a quantitative measure for computing the thickness of the text. We will refer to this as a workload measure because thicker text tends to require more work to interpret than less thick text
Automatic summarization · Coherence (philosophical gambling strategy · Data mining · Event (particle physics · Linguistics · Measure (data warehouse · Narrative · Natural language processing · Reading (process · Representation (politics · SSS · Computer Science · Mathematics · Natural Language Processing Techniques · Speech and dialogue systems · Topic Modeling · Artificial Intelligence
GRK 5 Inhibition Attenuates Cartilage Degradation via Decreased NF ‐κB Signaling
The Thread of Discourse
Coherence and Coreference
Remembrance of things parsed
Causal relatedness and importance of story events
Notes on a Schema for Stories
A spreading-activation theory of semantic processing.
Strategies of discourse comprehension
An analysis of narratives
Thematic knowledge structures in the understanding and generation of narratives∗
Story understanding as problem-solving
| Citations per year | 0.08 |
|---|---|
| Citation span | 2002 - 2002 (1) |
| Highly cited | No |