Loading...
Please wait, while we are loading the content...
Similar Documents
Natural Language Understanding and World Knowledge 2.1 What Is Natural Language Understanding? Integration of World Knowledge for Natural Language Understanding Integration of World Knowledge for Natural Language Understanding Fig. 2.2 Computational Natural Language Understanding
| Content Provider | Semantic Scholar |
|---|---|
| Abstract | In artificial intelligence and computational linguistics, natural language understanding (NLU) is a subfield of natural language processing that deals with machine reading comprehension. The goal of an NLU system is to interpret an input text fragment. The process of interpretation can be viewed as a translation of the text from a natural language to a representation in an unambiguous formal language. This representation, supposed to express the text's content, is further used for performing concrete tasks implied by a user request. One of the earliest known attempts in natural language understanding is the program STUDENT developed by Bobrow (1964) for his dissertation project. This was a program, which could solve high-school algebra problems posed in a natural language form. For example, STUDENT was able to answer the following query: " If the number of customers Tom gets is twice the square of 20% of the number of advertisements he runs, and the number of advertisements is 45, then what is the numbers of customers Tom gets? " STUDENT was processing queries by doing simple pattern-matching in order to translate the queries into a format suitable for an equation-solving program. A couple of years later, Weizenbaum (1966) created ELIZA, an interactive computer program able to carry on a dialog on any topic. ELIZA was equipped with a simple parser; its " semantic " analysis was based on transformation of key words into canned patterns. Although ELIZA was just a toy project, it has gained an amazing popularity, especially in the area of psychotherapy. The popularization of ELIZA and similar programs has led to the appearance of the term " ELIZA effect " 1 describing the tendency of people to attribute human-like intelligence to chat robots. Indeed, a typical dialog with ELIZA may look quite impressive: 1 See preface in Hofstadter (1996) for a description of ELIZA effect. USER: Men are all alike ELIZA: In what way? USER: They're always bugging us about something or other ELIZA: Can you think of a specific example? USER: My boyfriend made me come here ELIZA: Your boyfriend made you come here USER: He says I'm depressed much of the time ELIZA: I'm sorry to hear you are depressed ... STUDENT and ELIZA were among the first computer programs to approach human intelligence in language comprehension and they were followed by many others. But can we actually say that these programs were able to understand natural … |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.springer.com/cda/content/document/cda_downloaddocument/9789491216527-c2.pdf?SGWID=0-0-45-1307156-p174288092 |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
