Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
Toward a Connectionist Model of Recursion in Human Linguistic Performance |
| Συγγραφείς: |
Morten H. Christiansen, Nick Chater |
| Συνεισφορές: |
The Pennsylvania State University CiteSeerX Archives |
| Πηγή: |
ftp://siva.usc.edu/pub/coglab/morten/nn-rec.ps.Z |
| Έτος έκδοσης: |
1999 |
| Συλλογή: |
CiteSeerX |
| Περιγραφή: |
Naturally occurring speech contains only a limited amount of complex recursive structure, and this is reflected in the empirically documented difficulties that people experience when processing such structures. We present a connectionist model of human performance in processing recursive language structures. The model is trained on simple artificial languages. We find that the qualitative performance profile of the model matches human behavior, both on the relative difficulty of center-embedded and cross-dependency, and between the processing of these complex recursive structures and right-branching recursive constructions. We analyze how these differences in performance are reflected in the internal representations of the model by performing discriminant analyses on these representation both before and after training. Furthermore, we show how a network trained to process recursive structures can also generate such structures in a probabilistic fashion. This work suggests a novel expla. |
| Τύπος εγγράφου: |
Thesis |
| Περιγραφή αρχείου: |
application/postscript |
| Γλώσσα: |
English |
| Relation: |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.48.5731 |
| Διαθεσιμότητα: |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.48.5731 |
| Rights: |
Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
| Αριθμός Καταχώρησης: |
edsbas.5828F06C |
| Βάση Δεδομένων: |
BASE |