Christiansen, M. (1992). The (Non) Necessity of Recursion in Natural Language Processing. Proceedings of the 14th Annual Conference of the Cognitive Science Society, p. 665-670. Indiana University, Bloomington.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....Such a performanceoriented approach (as opposed to a competence oriented one) is intentional. There is growing belief that : human parsing resources must be characterized as finite state (Pulman, 1986) and that full recursion, as supported by context free languages, may be unnecessary (Christiansen, 1992; Church, 1982) Simple recurrent networks possess the power of a finite state machine, but as such can approximate, to a finite degree, the processing requirements of a context free language. Unlike recurrent parsing networks described elsewhere (see, for example, Das et al. 1992) our system ....

Christiansen, M. (1992). The (Non) Necessity of Recursion in Natural Language Processing. In Proceedings of the Fourteenth Annual Conference of the Cognitive Science Society (pp. 665--670). Hillsdale, NJ: Lawrence Erlbaum Associates.

.... discussed in [68, 22, 23, 40, 61, 3, 21, 52, 19, 56, 80] Some representative references for semantic and syntactic analysis with connectionist networks can be found in [38, 50, 60, 75, 70, 79] For references on cognitively oriented connectionist natural language processing some references are [14, 78, 69, 42, 12]. 3 Statistical Approaches 3.1 Introduction With the recent trend for learning in natural language processing, statistical methods have gained new popularity, and are being applied to new domains. They are usually characterized by using large text corpora and performing some analysis which uses ....

M. H. Christiansen. The (non)necessity of recursion in natural language processing. In Proceedings of the 14th Annual Conference of the Cognitive Science Society, pages 665--670, Indiana University, Bloomington, 1992.

....from informant judgment have proved to be deeper and more revealing than those based on evidence derived from experiments on processing and the like, although the future may be different in this regard. Chomsky, 1980: p. 200) 1 For a more detailed discussion of this and related points, see Christiansen (1992). 4 In this light, the C PD provides its proponents with a protective belt that surrounds their grammatical theories and makes them empirically impenetrable to psycholinguistic counter evidence. As long as the C PD is upheld, potentially falsifying psycholinguistic evidence can always be ....

Christiansen, M. (1992). The (Non) Necessity of Recursion in Natural Language Processing. Proceedings of the 14th Annual Conference of the Cognitive Science Society, p. 665-670. Indiana University, Bloomington.

....letters denote plural items, and lower case letters denote singular items. One line of defense against the demise of finite state models of language processing is that arbitrarily long center embedded constructions, while allowed by the rules of generative grammar, do not occur in practice (Christiansen, 1992). Indeed, empirical studies (e.g. Bach, Brown Marslen Wilson, 1986) have shown that sentences with either three or more center embeddings or three or more crossdependencies are universally hard to process and understand. Perhaps, then, FSMs, including neural networks, might be able to model ....

Christiansen, M. (1992) The (Non)Necessity of Recursion in Natural Language Processing. In Proceedings of the Fourteenth Annual Meeting of the Cognitive Science Society, Indiana University, Bloomington, July/August.

.... of Recursion Chomsky (1957) proposed that a recursive generative grammar consists of a set of phrase structure rules, complemented by a set of transformational rules (we shall not consider trans 2 The competence performance distinction also leads to certain methodological problems see Christiansen (1992, 1994) for further discussion. formational rules further below) Phrase structure rules have the form A BC, with the interpretation that the symbol A can be replaced by the concatenation of B and C. A phrase structure rule is recursive if a symbol X is replaced by a string of symbols which ....

Christiansen, M.H. (1992). The (non)necessity of recursion in natural language processing.

.... The two different approaches are often construed as two different paradigms (e.g. Schneider, 1987) and as was to be expected (cf. Kuhn, 1972) the proliferation of connectionism in the second half of the 80 s led to much subsequent debate (e.g. Chalmers, 1990b; Chater Oaksford, 1990; Christiansen Chater, 1992, 1994; Fodor Pylyshyn, 1988; Fodor McLaughlin, 1990; Hadley, 1994a, 1994b; Niklasson Sharkey, 1992; Niklasson van Gelder, 1994; Smolensky, 1987, 1988; van Gelder, 1990) In this debate, language has been considered by many to be the largest stumbling block for connectionism. Indeed, ....

.... what key cognitive phenomena must be explained and what counts as a good explanation, have been set in largely symbolic terms (van Gelder, 1991) Thus, if connectionism amounts to a genuinely new paradigm for the understanding of mind, there is a very real danger of falling into what I elsewhere (Christiansen Chater, 1992) have called the incommensurability trap . That is, connectionist models may be unfairly judged either because they fail to fit the classical standards or because when they are made to fit, the resulting explanation looks forced and unattractive. The danger is analogous to that of judging ....

[Article contains additional citation context not shown here]

Christiansen, M. (1992) The (Non)Necessity of Recursion in Natural Language Processing. In Proceedings of the Fourteenth Annual Meeting of the Cognitive Science Society. Hillsdale, NJ: Lawrence Erlbaum Associates.

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