Abstract
We describe a connectionist model which learns to parse single sentences from sequential word input. A parse in the connectionist network contains information about role assignment, prepositional attachment, relative clause structure, and subordinate clause structure. The trained network displays several interesting types of behavior. These include predictive ability, tolerance to certain corruptions of input word sequences, and some generalization capability. We report on experiments in which a small number of sentence types have been successfully learned by a network. Work is in progress on a larger database. Application of this type of connectionist model to the area of spoken language processing is discussed.- Anthology ID:
- W89-0224
- Volume:
- Proceedings of the First International Workshop on Parsing Technologies
- Month:
- August
- Year:
- 1989
- Address:
- Pittsburgh, Pennsylvania, USA
- Editor:
- Masaru Tomita
- Venue:
- IWPT
- SIG:
- SIGPARSE
- Publisher:
- Carnegy Mellon University
- Note:
- Pages:
- 221–229
- Language:
- URL:
- https://aclanthology.org/W89-0224
- DOI:
- Cite (ACL):
- Ajay Jain and Alex Waibel. 1989. A Connectionist Parser Aimed at Spoken Language. In Proceedings of the First International Workshop on Parsing Technologies, pages 221–229, Pittsburgh, Pennsylvania, USA. Carnegy Mellon University.
- Cite (Informal):
- A Connectionist Parser Aimed at Spoken Language (Jain & Waibel, IWPT 1989)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/W89-0224.pdf