Theoretical Issues In Natural Language Processing最新文献

{"title":"The Role of Metaphors in Descriptions of Emotions","authors":"A. Ortony, Lynn Fainsilber","doi":"10.3115/980304.980346","DOIUrl":"https://doi.org/10.3115/980304.980346","url":null,"abstract":"Why do we use metaphors? For nearly 2000 years, the most generally accepted answer was that people only use metaphors for rhetorical purposes. Metaphorical language was thought to be merely ornamental -the seasoning of language, exploited for effect by poets and politicians 1, as compared with the cold factual language of the scientist. This view, however, is now no longer accepted (see, for example, Gentner, 1982; Boyd, 1979). It is now assumed, at least by psychologists and linguists, that metaphors, and their close cousins, analogies, are important tools of cognition and communication, providing us with unfamiliar ways of conceptualizing familiar things, and familiar ways of conceptualizing unfamiliar things (Lakoff & Johnson, 1980; Ortony, 1979; Vosniadou & Ortony, in preparation). Yet, what is still assumed, rather than demonstrated, is that nonliteral uses of language are sometimes necessary for accomplishing such goals, rather than merely convenient or elegant ways of doing so. In this paper we present a sort of empirical existence proof that there are some things whose descriptions appear to invoke much more use of metaphorical language than others. This, while not establishing the necessity of metaphors, certainly is a first step.","PeriodicalId":439225,"journal":{"name":"Theoretical Issues In Natural Language Processing","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1987-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127712083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Position Paper on Metaphor","authors":"G. Lakoff","doi":"10.3115/980304.980348","DOIUrl":"https://doi.org/10.3115/980304.980348","url":null,"abstract":"My research has focussed mainly on conventional metaphor built into the conceptual system on which our everyday language is based. What I and others have found is that metaphor plays a major role in semantics. It is the means by which domains of experience that are not highly structured on their own terms get structured on the basis of other, highly-structured domains. Domains need structure so that one can reason about them. The major function of metaphor is thus to supply structure in terms of which reasoning can be done. What we have-found is that an enormous amount of our reasoning is metaphorical (see Lakoff, 1986b; Lakoff and Johnson, 1987; Johnson, 1087; Turner, 1987; Holland and Quinn, 1987; and especially Quinn, in preparation).","PeriodicalId":439225,"journal":{"name":"Theoretical Issues In Natural Language Processing","volume":"636 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1987-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122281786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unification and Some New Grammatical Formalisms","authors":"A. Joshi","doi":"10.3115/980304.980314","DOIUrl":"https://doi.org/10.3115/980304.980314","url":null,"abstract":"The key idea in the unification-based approaches to grammar is that we deal with informational structures (called feature structures) which encode a variety of linguistic information (lexical, syntactic, semantic, discourse, perhaps even cross-linguistic) in a uniform way and then manipulate (combine) these structures by means of a few (one, if possible) welldefined operations (unification being the primary one). The feature structures consist of features and associated values, which can be atomic or complex i.e., feature structures themselves. In other'words, the values can be from a structured set. The unification operation builds new structures and together with some string combining operation (concatenation being the primary one) pairs the feature structures with strings (Schieber, 1986).","PeriodicalId":439225,"journal":{"name":"Theoretical Issues In Natural Language Processing","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1987-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132760580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Rate of Progress in Natural Language Processing","authors":"N. Sondheimer","doi":"10.3115/980304.980330","DOIUrl":"https://doi.org/10.3115/980304.980330","url":null,"abstract":"Abstract : The rate of progress in natural language processing has been disappointing to many, including myself. It is not just that the popular press has had overblown expectations, but that we at this meeting have. The consequences of these errors could be severe. Hopefully, this short note will give an accurate evaluation of our rate of progress, identify what some of the problems have been, and present some reasonable suggestions on what can be done to improve the situation. Given that we want to take our ideas down the chain from theoretical research to empirical study and beyond and that natural language is an extremely difficult task, how can we proceed? There is only one answer: work within our current limits. Let's treat our work as that of successive approximations. Let us forget about the unexplored problems for the time being. Let us see what we can really do with the proposals we have that seem to work. Basically, let us emphasize building systems and full-scale components for a while. For example, why don't a group of us take the best parser, the best semantic interpreter, the best generator, the best inference system, etc., and tie them together? Then let's pick a domain of discourse and make them work for more than a few sentences. Let's beat on them until they work for as much of language as they appear capable. While we are at it, let's make the system as fast, as robust, as portable, as maintainable, etc., as we possibly can. Similarly, let's beat on individual components in the same way. I know there is no guarantee this approach will produce a useful system or component. But even if we fail to produce something worth going further with, we will have learned a lot about what works and what doesn't. If those results are not allowed to be lost, the next effort can do better. Of course, a problem with this approach lies in the source of our funds.","PeriodicalId":439225,"journal":{"name":"Theoretical Issues In Natural Language Processing","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1987-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116484416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bidirectional Grammars and the Design of Natural Language Generation Systems","authors":"D. Appelt","doi":"10.3115/980304.980352","DOIUrl":"https://doi.org/10.3115/980304.980352","url":null,"abstract":"Intuit ively considered, a grammar is bidirectional if it can be used by processes of approximately equal computat ional complexity to parse and generate sentences of a language. Because we, as computat ional linguists, are concerned with the meaning of the sentences we process, a bidirectional grammar must specify a correspondence between sentences and meaning representations, and this correspondence must be represented in a manner tha t allows one to be computed from the other. Most research in computat ional linguistics has focused on one or the other of the two sides of the problem, with the result tha t relatively little a t tent ion has been given to the issues raised by the incorporation of a single grammar into a system for tasks of both comprehension and generation. Clearly, if it were possible to have t ruly bidirectional grammars in which both parsing and generation processes were efficient, there would be some compelling reasons for adopting them. First , Occam's razor suggests tha t , if language behavior can be explained by hypothesizing only one linguistic representation, such an explanation is clearly preferable to two tha t are applicable in complementary circumstances. Also, from the practical s tandpoint of designing systems tha t will carry on sophisticated dialogues with their users, a single unified formalism for specifying the syntax and semantics of the language is likely to result in a simpler, more robust implementation. The problems of mainta ining consistency between comprehension and generation components when one of them changes have been eliminated. The lexicon is also simpler because its entries need be made but once, and there is no problem of mainta ining consistency between different lexical entries for unders tanding and generation. It is obvious tha t not all grammars are bidirectional. The most fundamental requirement of any bidirectional grammar is tha t it be represented declaratively. If any information is represented procedurally, it must of necessity be represented differently for parsing and generation processes, resulting in an asymmetry between the two. Any change in the grammar would have to be made in two places to mainta in the equivalence between the syntactic and semantic analyses given to sentences by each process. A grammar like DIAGRAM [8] is an example of a grammar for which the encoding of linguistic information","PeriodicalId":439225,"journal":{"name":"Theoretical Issues In Natural Language Processing","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1987-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130954989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generation Systems Should Choose Their Words","authors":"Mitchell P. Marcus","doi":"10.3115/980304.980356","DOIUrl":"https://doi.org/10.3115/980304.980356","url":null,"abstract":"Almost all current natural language generation (NLG) systems, as contrasted with current NL understanding (NLU) systems, have one somewhat surprising property in common: Most current NLG systems don't use words at all. Such systems operate by incrementally specifying fragments of linguistic structure in a top-down fashion, typically inserting specific lexical items only when the frontier of the structure is encountered. In some important sense, these systems have no real knowledge of lexical semantics and only rarely make lexical choices. Instead they choose between one tree fragment or another, only rarely able to see the leaves for the trees. Somehow the fact that particular words have particular meanings is incidental to the operation of these systems; they use fragments of linguistic structure which eventually have words as their frontiers, but they have little or no explicit knowledge of these words and what they mean. At best, these systems assume that each conceptual primitive corresponds to a particular unique lexical item or phrase, trivializing the problem of lexical choice to one of table lookup, and trivializing the problem of lexical semantics to the claim that the meaning of the word can be represented by the same word in upper case, more or less. While this practice may suffice for generation systems for narrow application domains, it is most certainly wrong from a cognitive point of view.","PeriodicalId":439225,"journal":{"name":"Theoretical Issues In Natural Language Processing","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1987-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121442915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Position Paper: Event Reference","authors":"B. Webber","doi":"10.3115/980304.980341","DOIUrl":"https://doi.org/10.3115/980304.980341","url":null,"abstract":"1. I n t r o d u c t i o n Developing a computational account of event reference requires solution to a number of difficult problems, not least of which is characterizing the phenomenon itself. From a listener's point of view, eveni reference encompasses both the task of building up a structured model of the events and situations underlying a given text and the task of interpreting subsequent references to these events and situations afterwards. A computational approach to these tasks requires at least (1) a characterization of the information that an individual clause may convey about an event or situation; (2) a characterization of explicit clues a text gives as to how the pieces described in individual clauses fit together (assuming, as I do, that this does not rely solely on world knowledge; (3) an account of what the listener does in processing an explicit event reference; (4) a characterization of what events and situations are available for explicit reference; and (5) a procedure for choosing among possible ways of resolving an explicit event reference.","PeriodicalId":439225,"journal":{"name":"Theoretical Issues In Natural Language Processing","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1987-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122773523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Natural Language Processing: What’s Really Involved?","authors":"R. Schank, A. Kass","doi":"10.3115/980304.980329","DOIUrl":"https://doi.org/10.3115/980304.980329","url":null,"abstract":"The question before us is whether or not NLP has gone anywhere since the last TINLAP. The answer depends strongly on what we take NLP to be. If we accept the common assumption that language processing can be isolated from the rest of cognition, and that the goal of NLP research to study language as a formal system independent of such (admittedly difficult) issues as memory, learning, and explanation, then our conclusion is grim. Not only has this approach failed to make significant progress in the eight years since TINLAP2, it is permanently doomed to failure because it misses the point of what language is all about. It is only possible for research on understanding natural language to make progress when the researchers realize that the heart of NLU is the understanding process, not language per se.","PeriodicalId":439225,"journal":{"name":"Theoretical Issues In Natural Language Processing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1987-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115146354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Discourse Representation Theory and the Semantics of Natural Languages: Contribution to a Panel on “Discourse Theory and Speech Acts” TINLAP3","authors":"F. Guenthner","doi":"10.3115/980304.980327","DOIUrl":"https://doi.org/10.3115/980304.980327","url":null,"abstract":"[1] Is there yet any serious discourse theory with testable computational and empirical consequences? [2] What phenomena ought a processing theory of discourse understanding/generation to address itself that are not already being attended to currently? [3] What aspects of discourse are language problems and which are general AI/KR problems? [4] What makes a theory of discourse a processing theory? [5] Does spoken language affect one's theory of discourse? [6] Is there any real hope that we will be able to recognize the plans/goals etc. of a speaker? [7] How much of conversation is carried on through the linguistic window anyway? [8] Do current theories of text and dialogue mesh, and should they?","PeriodicalId":439225,"journal":{"name":"Theoretical Issues In Natural Language Processing","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1987-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133704806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On keeping logic in its place","authors":"Y. Wilks","doi":"10.3115/980304.980333","DOIUrl":"https://doi.org/10.3115/980304.980333","url":null,"abstract":"There need be no real dispute on this panel about what is meant , in the broades t terms, by formal semant ics (FS) when opposed to c o m m o n s e n s e semant ics (CSS): after registering his complaints and worries, the opposit ion David Israel opts for in his paper is broadly the one adopted here, and the model theore t ic semanticis ts he mentions will do just fine for me, and I suspect for Karen Sparck-Jones in her characterisation of a \" logicis t\" approach to natural language processing. As will appear below, though, I want to list a range of s t rengths of FS c o m m i t m e n t , no t all of which are modeltheoret ic . So, whatever we find to argue about on this panel, it n e e d n ' t be those two terms.","PeriodicalId":439225,"journal":{"name":"Theoretical Issues In Natural Language Processing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1987-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122519536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}