Learning word meanings by instruction
Conference
·
OSTI ID:430693
- Univ. of Southern California, Marina del Rey, CA (United States)
We develop techniques for learning the meanings of unknown words in context. Working within a compositional semantics framework, we write down equations in which a sentence`s meaning is some combination function of the meaning of its words. When one of the words is unknown, we ask for a paraphrase of the sentence. We then compute the meaning of the unknown word by inverting parts of the semantic combination function. This technique can be used to learn word-concept mappings, decomposed meanings, and mappings between syntactic and semantic roles. It works for all parts of speech.
- OSTI ID:
- 430693
- Report Number(s):
- CONF-960876--
- Country of Publication:
- United States
- Language:
- English
Similar Records
Getting ahead of yourself: Parafoveal word expectancy modulates the N400 during sentence reading
Semantic role labeling for protein transport predicates
A Computational Theory for the Emergence of Grammatical Categories in Cortical Dynamics
Journal Article
·
Tue Jan 17 23:00:00 EST 2017
· Cognitive, Affective, & Behavioral Neuroscience
·
OSTI ID:1340507
Semantic role labeling for protein transport predicates
Journal Article
·
Wed Jun 11 00:00:00 EDT 2008
· BMC Bioinformatics
·
OSTI ID:1626355
A Computational Theory for the Emergence of Grammatical Categories in Cortical Dynamics
Journal Article
·
Thu Apr 16 00:00:00 EDT 2020
· Frontiers in Neural Circuits
·
OSTI ID:1817166