Abstract
A distributed neural network model called SPEC for processing sentences with recursive relative clauses is described. The model is based on separating the tasks of segmenting the input word sequence into clauses, forming the case-role representations, and keeping track of the recursive embeddings into different modules. The system needs to be trained only with the basic sentence constructs, and it generalizes not only to new instances of familiar relative clause structures, but to novel structures as well. SPEC exhibits plausible memory degradation as the depth of the center embeddings increases, its memory is primed by earlier constituents, and its performance is aided by semantic constraints between the constituents. The ability to process structure is largely due to a central executive network that monitors and controls the execution of the entire system. This way, in contrast to earlier subsymbolic systems, parsing is modeled as a controlled high-level process rather than one based on automatic reflex responses.
Original language | English |
---|---|
Title of host publication | AAAI'94 |
Subtitle of host publication | Proceedings of the Twelfth AAAI National Conference on Artificial Intelligence |
Publisher | AAAI |
Pages | 858-864 |
Publication status | Published - 15 Dec 1994 |
Event | 12th AAAI National Conference on Artificial Intelligence 1994 - Seattle, United States Duration: 1 Aug 1994 → 4 Aug 1994 Conference number: 12 |
Conference
Conference | 12th AAAI National Conference on Artificial Intelligence 1994 |
---|---|
Country/Territory | United States |
City | Seattle |
Period | 1/08/94 → 4/08/94 |
Keywords
- METIS-119294