R. R. Granger (1977) FOULUP: a program that figures out meanings of words from context. Proc. Fifth Joint International Conference on AI.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....we can teach it strategically. With this knowledge, we could more effectively help students be more aware of context and know better how to use it. There are also computational theories that implement various CVA methods, which do go into much more detail on how to use context to infer meaning [1,7 10,35]. But most of these assume the prior existence of a known concept that the unknown word is to be mapped to; this is especially the case for the large body of research on word sense disambiguation [11] As linguist Ellen Prince has suggested (in conversation) that makes the task more like a ....

Granger, R.H. (1977), "Foul-Up: a Program that Figures Out Meanings of Words from Context", Proc. IJCAI-77 (Los Altos, CA: William Kaufmann): 67--68.

....linguistic context, with no user interaction. This strategy can be used to choose a plausible correction for a misspelled word as well as to parse an expression containing an unknown word. Early research in this area attempted to model human reasoning about unknown words in a script based parser [5], and has since come to encompass a variety of multistrategy, expectation based techniques as ex emplified in the DYPAR [2] and NOMAD [4] systems. This technique shifts the burden of linguistic expertise from the end user to the computer system, but has met so far with only limited success, and ....

Richard H. Granger, Jr. FOUL-UP: A Pro- gram that Figures Out Meanings of Words from Context. In Proceedings of the 5th International Joint Conference on Artificial Intelligence, pages 172-178, 1977. lOO

....constraints which support the heuristics necessary to achieve tractable learning, the limitations of the current theory and the implications of this work for language acquisition research. 1 Introduction Several natural language systems have been reported which learn the meanings of new words[5, 7, 1, 16, 17, 13, 14]. Many of these systems (in particular [5, 7, 1] learn the new meanings based upon expec tations arising from the morphological, syntactic, se Supported by an AT T Bell Laboratories Ph.D. scholarship. Part of this research was performed while the author was visiting Xerox PARC as a research ....

....tractable learning, the limitations of the current theory and the implications of this work for language acquisition research. 1 Introduction Several natural language systems have been reported which learn the meanings of new words[5, 7, 1, 16, 17, 13, 14] Many of these systems (in particular [5, 7, 1]) learn the new meanings based upon expec tations arising from the morphological, syntactic, se Supported by an AT T Bell Laboratories Ph.D. scholarship. Part of this research was performed while the author was visiting Xerox PARC as a research intern and as a consultant. mantic and pragmatic ....

[Article contains additional citation context not shown here]

Richard H. Granger, Jr. FOUL-UP a program that figures out meanings of words from context. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence, pages 172- 178, 1977.

....constraints which support the heuristics necessary to achieve tractable learning, the limitations of the current theory and the implications of this work for language acquisition research. 1 Introduction Several natural language systems have been reported which learn the meanings of new words[5, 7, 1, 16, 17, 13, 14]. Many of these systems (in particular [5, 7, 1] learn the new meanings based upon expectations arising from the morphological, syntactic, se Supported by an AT T Bell Laboratories Ph.D. scholarship. Part of this research was performed while the author was visiting Xerox PARC as a research ....

....tractable learning, the limitations of the current theory and the implications of this work for language acquisition research. 1 Introduction Several natural language systems have been reported which learn the meanings of new words[5, 7, 1, 16, 17, 13, 14] Many of these systems (in particular [5, 7, 1]) learn the new meanings based upon expectations arising from the morphological, syntactic, se Supported by an AT T Bell Laboratories Ph.D. scholarship. Part of this research was performed while the author was visiting Xerox PARC as a research intern and as a consultant. mantic and pragmatic ....

[Article contains additional citation context not shown here]

Richard H. Granger, Jr. FOUL-UP a program that figures out meanings of words from context. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence, pages 172-- 178, 1977.

....He performs no experiment to assess his method s viability, but we will demonstrate that this is not a good approach. The use of all possible parts of speech will cause an exponential increase in the number of parses for a sentence as the number of unknown words increases. The FOUL UP system [6], by Granger, is an example of a method that focuses on the use of context. This method assumes that most words are known, and that all sentences lie in a 262 common semantic domain. In FOUL UP, a strong top down context in the form of a script is needed to provide the expected attributes of ....

Henry Granger, Jr. FOUL-UP: A program that figures out meanings of words from context. Proceedings of the Fifth International Joint Conicrenee on Atificial Intelligence, pages 172- 178, 1977.

....lexicons are built by hand for most NLP applications, but several techniques have been developed to learn lexical semantic information automatically. Most of these methods learn the meanings of an unknown word by using contextual expectations from the definitions of surrounding words (e.g. (Granger 1977; Carbonell 1979; Jacobs Zernik 1988; Cardie 1993; Hastings Lytinen 1994) An alternative approach is to derive knowledge automatically from on line dictionaries (Dolan, Vanderwende, Richardson 1993) All of these approaches rely on an existing dictionary or knowledge base as a starting ....

Granger, R. H. 1977. FOUL-UP: A Program that Figures Out Meanings of Words from Context. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence, 172--178.

....the MUC 4 terrorism domain [ Riloff, 1993 ] One of the main differences between AutoSlog and previous lexical acquisition systems is that AutoSlog creates new definitions entirely from scratch. In contrast, previous language learning systems (e.g. Jacobs and Zernik, 1988; Carbonell, 1979; Granger, 1977 ] create new definitions based on the definitions of other known words in the context. That is, they assume that some definitions already exist and use those definitions to create new ones. The structures created by AutoSlog are also considerably different than the lexical definitions created ....

Granger, R. H. 1977. FOUL-UP: A Program that Figures Out Meanings of Words from Context. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence. 172--178.

....2 Here Bootstrapping Adults can use knowledge about the meanings of known words in an utterance to help figure out the meaning of an unknown word. For example, an adult hearing the utterance I woke up yesterday, turned off my alarm clock, took a shower, and cooked myself two grimps for breakfast (Granger, 1977) might have a fairly good idea of what grimps are. The context of known words can help determine the meaning of an unknown word, or at least narrow down the possibilities and suggest to the learner which hypotheses to entertain. Granger (1977) Jacobs and Zernik (1988) and Berwick (1983) among ....

....a shower, and cooked myself two grimps for breakfast (Granger, 1977) might have a fairly good idea of what grimps are. The context of known words can help determine the meaning of an unknown word, or at least narrow down the possibilities and suggest to the learner which hypotheses to entertain. Granger (1977), Jacobs and Zernik (1988) and Berwick (1983) among others, describe implemented systems that learn the meanings of new words from the context of known word meanings. While the techniques employed by such systems might account 9 for adult word learning, and perhaps the later stages of child word ....

Granger, Jr., R. H. (1977). FOUL-UP: A Program that Figures Out Meanings of Words from Context. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence, pp. 172--178, Cambridge, MA.

.... automatic induction of a lexicon for i.e. This tradition of work goes back to an AI notion that might be described as lexical tuning, that of adapting a lexicon automatically to new senses in texts, a notion discussed in Wilks and Catizone [15] and going back to work like Wilks [16] and Granger [17] on detecting new preferences of words in texts and interpreting novel lexical items from context and stored knowledge. This notion is important, not only for IE in general but in particular as it adapts to traditional AI tasks like Question Answering, now also coming within the IR remit (see ....

R. Granger, FOULUP: a program that figures out meanings of words from context. In Proceedings of the Fifth Joint International Conference on AI, 1977.

....(1) a computational system which acquires verb meaning from the linguistic context of real world texts, 2) a statistical analysis of the predictiveness of various features of the context to the verb, and (3) two experiments on adults to determine their ability to infer missing verbs from context. Granger (1977) conducted some of the earliest compuational work on verb acquisition from context, and Salveter (1979, 1980) followed close thereafter. However, neither of these systems was tested on real world domains. Zernik s thesis work (1987) concentrated on verb learning, but mainly on verb particle ....

Granger, R. (1977). FOUL-UP: A program that figures out meanings of words from context. In Proceedings of Fifth International Joint Conference on Artificial Intelligence.

....semantic, but morphological in nature. Wolff (1987) and Langley (1994) describe a system which learns grammars and syntactic word classes. Like Wolfie, several systems restrict themselves to learning only semantics. These systems differ from Wolfie along two major dimensions. First, many systems (Granger, 1977; Siskind, 1992; Riloff, 1993; Hastings Lytinen, 1994; Haruno, 1995) require background knowledge in order to aid learning. Second, many systems (Brent, 1990, 1991; Siskind, 1994) do not demonstrate the handling of large amounts of ambiguity. Granger (1977) and Hastings and Lytinen (1994) are ....

....major dimensions. First, many systems (Granger, 1977; Siskind, 1992; Riloff, 1993; Hastings Lytinen, 1994; Haruno, 1995) require background knowledge in order to aid learning. Second, many systems (Brent, 1990, 1991; Siskind, 1994) do not demonstrate the handling of large amounts of ambiguity. Granger (1977) and Hastings and Lytinen (1994) are incremental systems that start with lexical knowledge about many words and learn the meanings of unknown words as they are encountered. Haruno (1995) describes a system for learning the semantics of verbs, but requires background knowledge in the form of a ....

Granger, R. (1977). FOUL-UP: a program that figures out meanings of words from context.

....not only was the system able to induce just a rather small set of features, it was also discouragingly slow when parsing sentences containing several unknown words. Lexical Acquisition 195 One of the first systems that aimed at constructing lexical entries automatically from raw text was FOUL UP [Granger 1977]. FOUL UP was an integral part of the SAM system [Schank 1975] developed to extend SAM s lexicon by inferring restrictions placed on unknown words by instantiating scripts that matched the sentences containing the unknown words. This built on a number of assumptions which in general do not hold, ....

R. H. Granger. "FOUL-UP: A Program that Figures out Meanings of Words from Context". In Proceedings of the 5th International Joint Conference on Artificial Intelligence, pp. 172--178, Cambridge, Massachusetts, 1977. IJCAI, Morgan Kaufmann.

....do with tearing. Similarly, one could guess that filp means something like eat upon hearing I filped the delicious sandwich and now I m full. These guesses are cued by the meanings of paper, shreds, sandwich, delicious, full, and the partial syntactic analysis of the utterances that contain them. Granger (1977), Berwick (1983) and Hastings (1994) describe computational systems that implement this approach. However, this approach is hindered by the need for a large amount of initial lexical semantic information and the need for a robust natural language understanding system that produces semantic ....

Granger, R. 1977. Foulup: a program that figures out meanings of words from context. In Proceedings of the 5th International Joint Conference on Artificial Intelligence.

.... more about information extraction techniques and systems, see [47, 36] Several systems have been developed recently that learn dictionaries for information extraction, such as [43, 67, 74] Some older systems that incorporated symbolic learning techniques with natural language processing include [1, 29, 9, 37]. Explanation based learning has also been previously applied to NLP (e.g. see [55] and rule based learning techniques have been used to extract information from on line dictionaries and build knowledge bases automatically [54, 20] 5 Summary and Discussion of General Issues In this section we ....

R. H. Granger. FOUL-UP: A program that figures out meanings of words from context. In Proceedings of the Fifth International Joint Conference on Artificial Intelligence, pages 172--178, 1977.

.... restrictions or thematic relations of verbs) while our focus is on much more fine grained conceptual knowledge (roles, role filler constraints, integrity conditions) and, hence, shares some similarities with work done by [SODE95] Our approach, however, bears a close relationship to the work of [GRAN77], LEBO82] MOON87] JACO88] GOME90] REIM90] HAST96] and [MOOR96] who aim at the automated learning of word meanings from context using a knowledge intensive approach. But our work differs from theirs in that the need to cope with several competing concept hypotheses and to aim at a ....

R. Granger. FOUL-UP: A program that figures out meanings of words from context. In IJCAI'77 - Proc. 5th Intl. Joint Conf. on Artificial Intelligence, pages 172--178, 1977.

....unknown word in different contexts and thus eliminate, or at least substantially reduce, the need for interaction with a domain expert when building a large lexicon. One of the first systems that aimed at constructing lexical entries automatically from raw text was Granger s FOUL UP system [Granger 1977]. FOUL UP was an integral part of the SAM system [Schank 1975] developed to extend SAM s lexicon by inferring restrictions placed on unknown words by instantiating scripts that matched the sentences containing the unknown words. This built on a number of assumptions which in general do not hold, ....

R.H. Granger. "FOUL-UP: A program that figures out meanings of words from context". In Proceedings of the 5th International Joint Conference on Artificial Intelligence, pp. 172--178, Cambridge, Massachusetts, 1977.

.... (usually syntactic) lexical knowledge (e.g. Brent 1991; Church Hanks 1990; Hindle 1990; Resnik 1992; Yarowsky 1992; and Zernik 1991) or knowledge intensive methods that acquire syntactic and or semantic lexical knowledge, but rely heavily on handcoded world knowledge (e.g. Berwick 1983; Granger 1977; Hastings et al. 1991; Lytinen Roberts 1989; and Selfridge 1986) or hand coded heuristics that describe how and when to acquire new word definitions (e.g. Jacobs Zernik 1988 and Wilensky 1991) Our approach differs from all of these in that ffl it uses a novel combination of two existing ....

Granger, R. (1977). Foulup: A program that figures out meanings of words from context. Proceedings, Fifth International Joint Conference on Artificial Intelligence, pp. 172-178. Morgan Kaufmann.

.... experiment, the quality based learning system yields competitive accuracy rates (a mean of 87 ) while at the same time it exhibits significant and valid reductions of the predicted concepts (up to two, on the average) 5 Related Work Our approach bears a close relationship to the work of [7], 16] 18] 6] 19] 23] and [12] who aim at the automated learning of word meanings from context using a knowledge intensive approach. But our work differs from theirs in that the need to cope with several competing concept hypotheses and to aim at a reason based selection is not an issue ....

R. Granger. FOUL-UP: A program that figures out meanings of words from context. In IJCAI'77 - Proc. 5th Intl. Joint Conf. on Artificial Intelligence, pages 172--178, 1977.

....text being processed, and allows for the addition of new knowledge to the concept hierarchies. 1.3.1 Knowledge Lean XXXXX is a knowledge lean approach since it only requires a parsed corpus of text and concept hierarchies of nouns and verbs. Other work in acquiring the semantics of unknown words [3, 23, 25, 53] requires much richer information be available either in the lexical entries or in a world knowledge source. XXXXX avoid requiring semantically rich lexical entries and grammar rules sine it automatically constructs real world knowledge from the text being processing by finding relations between ....

....language generation in that it helps avoid unlikely or unusual word pairings. 60] uses local word co occurences to perform sense disambiguation. 50] shows that this technique can be used to resolve syntactic ambiguity. 4. 2 Learning from Context Acquisition of lexical semantics is defined in [3, 23, 25, 53] as the process of classifying a new or unknown word into known semantic classes. These systems use world knowledge that is represented by script like structures or concept hierarchies. The real world knowledge is assumed to be complete and unknown words are regarded as unknown synonyms for known ....

[Article contains additional citation context not shown here]

R. Granger. FOUL-UP: A program that figures out meanings of words from context. In Proceedings of the the 5th International Joint Conference on Artificial Intelligence (IJCAI-77), volume 1, pages 172--178, Cambridge, MA, August 1977.

No context found.

R. R. Granger (1977) FOULUP: a program that figures out meanings of words from context. Proc. Fifth Joint International Conference on AI.

No context found.

Granger, R. H. FOUL-UP: A Program that figures out the meanings of words from context. In the Proceedings of the Fifth International Joint Conference on Artificial Intelligence. Cambridge, MA. 1977.

No context found.

R. Granger. FOUL-UP: A program that figures out meanings of words from context. In Proceedings, IJCAII-77, pp. 172-178, 1977.

No context found.

R.H. Granger , "FOUL-UP: A program that figures out the meanings of words from context", Proceedings of the Fifth International Joint Conference on Artificial Intelligence, pp.172-178, Cambridge, MA. J.R. Hurford , "The evolution of the critical period for language acquisition", Cognition, 40:159-201, 1991.

No context found.

Granger, R.H. [1977] FOUL-UP: a program that figures out meanings of words from context.

No context found.

Granger, R. (1977) FOULUP: a program that figures out meanings of words from context. Proc. Fifth Joint Internat. Conf. on AI.

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC