| Presentation | 2013-12-14 Inference and Learning in Hierarchical Structured Semantic Space Model Akinori TAKADA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this article I propose a method of inference in "Hierarchical Structured Semantic Space Model" as a method to construct natural language based question-answering system. In rule-based natural language processing, input sentences are needed to be translated into certain types of meta-form. Then, based with the translated meta-form data, system generates some inferences. When we aim to build such inference system, there exist some difficulties in implementing proposed result as it is in the research context of symbolic logics. Especially in dealing concept of instance and class, or in processing conditional sentences or counterfactual sentences, some proposed methods exist but we could not build effective system easily. These difficulties are thought to be a bottleneck in the research of rule-based natural language system. As a solution to the problems, proposed methods are as below : (1) concepts of "instance" and "class" are separately dealt when transforming sentences into meta-form, (2) conditional sentences are classified and transformed into series of logics or facts. Some further problems are discussed along with examples of implemented system. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | natural language processing / question-answering system / semantic space / inference, conditional sentence |
| Paper # | TL2013-48 |
| Date of Issue |
| Conference Information | |
| Committee | TL |
|---|---|
| Conference Date | 2013/12/7(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Thought and Language (TL) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Inference and Learning in Hierarchical Structured Semantic Space Model |
| Sub Title (in English) | |
| Keyword(1) | natural language processing |
| Keyword(2) | question-answering system |
| Keyword(3) | semantic space |
| Keyword(4) | inference, conditional sentence |
| 1st Author's Name | Akinori TAKADA |
| 1st Author's Affiliation | Faculty of Letters, Department of Communication Studies, Ferris University() |
| Date | 2013-12-14 |
| Paper # | TL2013-48 |
| Volume (vol) | vol.113 |
| Number (no) | 354 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |