Information retrieval with semantic memory model
Psycholinguistic theories of semantic memory form the basis of understanding of natural language concepts. These theories are used here as an inspiration for implementing a computational model of semantic memory in the form of semantic network. Combining this network with a vector-based object-rel...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2013
|
| Online Access: | https://hdl.handle.net/10356/96887 http://hdl.handle.net/10220/13097 |
| _version_ | 1826127217057333248 |
|---|---|
| author | Szymański, Julian. Duch, Włodzisław. |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Szymański, Julian. Duch, Włodzisław. |
| author_sort | Szymański, Julian. |
| collection | NTU |
| description | Psycholinguistic theories of semantic memory form the basis of understanding of natural language concepts. These theories are used
here as an inspiration for implementing a computational model of semantic memory in the form of semantic network. Combining this
network with a vector-based object-relation-feature value representation of concepts that includes also weights for confidence and support,
allows for recognition of concepts by referring to their features, enabling a semantic search algorithm. This algorithm has been used
for word games, in particular the 20-question game in which the program tries to guess a concept that a human player thinks about. The
game facilitates lexical knowledge validation and acquisition through the interaction with humans via supervised dialog templates. The
elementary linguistic competencies of the proposed model have been evaluated assessing how well it can represent the meaning of linguistic
concepts. To study properties of information retrieval based on this type of semantic representation in contexts derived from
on-going dialogs experiments in limited domains have been performed. Several similarity measures have been used to compare the completeness
of knowledge retrieved automatically and corrected through active dialogs to a “golden standard”. Comparison of semantic
search with human performance has been made in a series of 20-question games. On average results achieved by human players were
better than those obtained by semantic search, but not by a wide margin. |
| first_indexed | 2024-10-01T07:05:11Z |
| format | Journal Article |
| id | ntu-10356/96887 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:05:11Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/968872020-05-28T07:17:59Z Information retrieval with semantic memory model Szymański, Julian. Duch, Włodzisław. School of Computer Engineering Psycholinguistic theories of semantic memory form the basis of understanding of natural language concepts. These theories are used here as an inspiration for implementing a computational model of semantic memory in the form of semantic network. Combining this network with a vector-based object-relation-feature value representation of concepts that includes also weights for confidence and support, allows for recognition of concepts by referring to their features, enabling a semantic search algorithm. This algorithm has been used for word games, in particular the 20-question game in which the program tries to guess a concept that a human player thinks about. The game facilitates lexical knowledge validation and acquisition through the interaction with humans via supervised dialog templates. The elementary linguistic competencies of the proposed model have been evaluated assessing how well it can represent the meaning of linguistic concepts. To study properties of information retrieval based on this type of semantic representation in contexts derived from on-going dialogs experiments in limited domains have been performed. Several similarity measures have been used to compare the completeness of knowledge retrieved automatically and corrected through active dialogs to a “golden standard”. Comparison of semantic search with human performance has been made in a series of 20-question games. On average results achieved by human players were better than those obtained by semantic search, but not by a wide margin. 2013-08-15T06:09:49Z 2019-12-06T19:36:20Z 2013-08-15T06:09:49Z 2019-12-06T19:36:20Z 2011 2011 Journal Article Szymański, J.,& Duch, W. (2012). Information retrieval with semantic memory model. Cognitive Systems Research, 14(1), 84-100. 1389-0417 https://hdl.handle.net/10356/96887 http://hdl.handle.net/10220/13097 10.1016/j.cogsys.2011.02.002 en Cognitive systems research |
| spellingShingle | Szymański, Julian. Duch, Włodzisław. Information retrieval with semantic memory model |
| title | Information retrieval with semantic memory model |
| title_full | Information retrieval with semantic memory model |
| title_fullStr | Information retrieval with semantic memory model |
| title_full_unstemmed | Information retrieval with semantic memory model |
| title_short | Information retrieval with semantic memory model |
| title_sort | information retrieval with semantic memory model |
| url | https://hdl.handle.net/10356/96887 http://hdl.handle.net/10220/13097 |
| work_keys_str_mv | AT szymanskijulian informationretrievalwithsemanticmemorymodel AT duchwłodzisław informationretrievalwithsemanticmemorymodel |