LUNAR (QA) System
A LUNAR (QA) System is a Question Answering System that was first demonstrated at a lunar science convention in 1971.
- Context:
- It can be interfaced with an Expert System (Expertise Domain) in lunar rock samples.
- It (often) uses an Augmented Finite-State Transition Network grammar (ATN) parser combined with a rule-based semantic interpretation program to guide its question analysis.
- Example(s):
- Examples of requests understood by the LUNAR system are:
- “Give me all analyses for Hydrogen in Sample 10046”.
- “Give me all lunar samples with magnetite.”
- “In which samples has apatite been identified?”
- “What is the specific activity of A126 in soil?”
- “Analyses of strontium in plagioclase.”
- “What are the plag analyses for breccias?”
- “What is the average concentration of olivine in breccias?”
- “What is the average age of the basalts?”
- “What is the average potassiudrubidium ratio in basalts?”
- “In which breccias is the average concentration of titanium greater than 6 percent?"
- Examples of requests understood by the LUNAR system are:
- Counter-Example(s):
- See: Natural Language Processing, Chatterbot, Turing Test, Knowledge Base, Expert System, Computational Linguistics, Augmented Transition Network.
References
2018
- (Wikipedia, 2018) ⇒ https://en.wikipedia.org/wiki/Question_answering#History Retrieved:2018-11-4.
- Two early QA systems were BASEBALL and LUNAR. BASEBALL answered questions about the US baseball league over a period of one year. LUNAR, in turn, answered questions about the geological analysis of rocks returned by the Apollo moon missions. Both QA systems were very effective in their chosen domains. In fact, LUNAR was demonstrated at a lunar science convention in 1971 and it was able to answer 90% of the questions in its domain posed by people untrained on the system. Further restricted-domain QA systems were developed in the following years. The common feature of all these systems is that they had a core database or knowledge system that was hand-written by experts of the chosen domain. The language abilities of BASEBALL and LUNAR used techniques similar to ELIZA and DOCTOR, the first chatterbot programs.
SHRDLU was a highly successful question-answering program developed by Terry Winograd in the late 60s and early 70s. It simulated the operation of a robot in a toy world (the "blocks world"), and it offered the possibility of asking the robot questions about the state of the world. Again, the strength of this system was the choice of a very specific domain and a very simple world with rules of physics that were easy to encode in a computer program.
In the 1970s, knowledge bases were developed that targeted narrower domains of knowledge. The QA systems developed to interface with these expert systems produced more repeatable and valid responses to questions within an area of knowledge. These expert systems closely resembled modern QA systems except in their internal architecture. Expert systems rely heavily on expert-constructed and organized knowledge bases, whereas many modern QA systems rely on statistical processing of a large, unstructured, natural language text corpus.
The 1970s and 1980s saw the development of comprehensive theories in computational linguistics, which led to the development of ambitious projects in text comprehension and question answering. One example of such a system was the Unix Consultant (UC), developed by Robert Wilensky at U.C. Berkeley in the late 1980s. The system answered questions pertaining to the Unix operating system. It had a comprehensive hand-crafted knowledge base of its domain, and it aimed at phrasing the answer to accommodate various types of users. Another project was LILOG, a text-understanding system that operated on the domain of tourism information in a German city. The systems developed in the UC and LILOG projects never went past the stage of simple demonstrations, but they helped the development of theories on computational linguistics and reasoning.
Recently, specialized natural language QA systems have been developed, such as EAGLi for health and life scientists.
- Two early QA systems were BASEBALL and LUNAR. BASEBALL answered questions about the US baseball league over a period of one year. LUNAR, in turn, answered questions about the geological analysis of rocks returned by the Apollo moon missions. Both QA systems were very effective in their chosen domains. In fact, LUNAR was demonstrated at a lunar science convention in 1971 and it was able to answer 90% of the questions in its domain posed by people untrained on the system. Further restricted-domain QA systems were developed in the following years. The common feature of all these systems is that they had a core database or knowledge system that was hand-written by experts of the chosen domain. The language abilities of BASEBALL and LUNAR used techniques similar to ELIZA and DOCTOR, the first chatterbot programs.
1978
- (Woods,1978) ⇒ W. A. Woods (1978). "Semantics and quantification in natural language question answering". In Advances in computers (Vol. 17, pp. 1-87). Elsevier. DOI: 10.1016/S0065-2458(08)60390-3
- QUOTE: The LUNAR system allowed a user to ask questions, compute averages and ratios, and make listings of selected subsets of the data. One could also retrieve references from a keyphrase index and make changes to the data base. The system permitted the user to easily compare the measurements of different researchers, compare the concentrations of elements or isotopes in different types of samples or in different phases of a sample, compute averages over various classes of samples, compute ratios of two constituents of a sample, etc., all in straight forward natural English (...)
The LUNAR system consists of three principal components: a general purpose grammar and parser for a large subset of natural English, a rule driven semantic interpretation component using pattern + action rules for transforming a syntactic representation of an input sentence into a representation of what it means, and a data base retrieval and inference component that stores and manipulates the data base and performs computations on it. The first two components constitute a language understanding component that transforms an input English sentence into a disposable program for carrying out its intent (answering a question or making some change to the data base). The third component executes such programs against the data base to determine the answer to queries and to effect changes in the data base.
The system contains a dictionary of approximately 3500 words, a grammar for a fairly extensive subset of natural English, and two data bases: a table of chemical analyses with 13,000 entries, and a topic index to documents with approximately 10,000 postings. The system also contains facilities for morphological analysis of regularly inflected words, for maintaining a discourse directory of possible antecedents for pronouns and other anaphoric expressions, and for determining how much and what information to display in response to a request.
The grammar used by the parsing component of the system is an augmented transition network (ATN) (...)
A semantic specification of a natural language consists of essentially three parts:
- QUOTE: The LUNAR system allowed a user to ask questions, compute averages and ratios, and make listings of selected subsets of the data. One could also retrieve references from a keyphrase index and make changes to the data base. The system permitted the user to easily compare the measurements of different researchers, compare the concentrations of elements or isotopes in different types of samples or in different phases of a sample, compute averages over various classes of samples, compute ratios of two constituents of a sample, etc., all in straight forward natural English (...)
- a) a meaning representation language (MRL) -- a notation for semantic representation for the meanings of sentences,
- b) a specification of the semantics of the MRL notation, i.e., a specification of what its expressions mean, and
- c) a semantic interpretation procedure, i.e., a procedure to construct the appropriate semantic representations for a given natural language sentence.
- Accordingly, the semantic framework of the LUNAR system consists of three parts: a semantic notation in which to represent the meanings of sentences, a specification of the semantics of this notation (by means of formal procedures), and a procedure for assigning representations in the notation to input sentences.
1977
- (Woods & Kaplan, 1977) ⇒ W. A. Woods, R. Kaplan (1977). “Lunar rocks in natural English: Explorations in natural language question answering”, Linguistic structures processing, 5. 5: 521569.