... PANEL NATURAL LANGUAGEAND DATABASES, AGAIN Karen Sparck Jones Computer Laboratory, University of Cambridge Corn Exchange Street, Cambridge CB2 3QG, England INTRODUCTION Natural Language ... models or databases, and as the solutions tend to be ad hoe and specialised, the issues are essentially diversions from research on more pervasive language phenomena and functions, and hence ... obvious problems of language and knowledge processing. But I believe that database query is reaching the end of its utility for fundamental research on natural language understanding, for two...
... a naturallanguage inter- face to include the programming environment is that if the interface were being developed in such an environment, one could use naturallanguage to develop the natural ... raise include a greater need for some language production capability (where the ordinary database query system can get by with only language un- derstanding), and a greater need for some discourse ... interface of this kind, some dialogue between the user and the system would be useful, especially in cases where a request was too vague, and the system (like an expert system) could present...
... understanding of the cognitive dynamics that shape and evolve natural language, perhaps the one useful naturallanguage interface that migjat be de- veloped would allow individuals and groups ... ideal. Naturallanguage is wordy (redun- dant) and imprecise. Most b,*m,m groups who have a need to communicate quickly and accurately tend to develop a rather well specified subset of naturallanguage ... faces including menus, commands, self-defined commands and self progra,,m4ng of interfaces for individuals and groups. In addition to the standard message, confer- ence and notebook features,...
... experimental systems for natural- language access to databases, with some now going into actual use, many problems in this area remain to be solved. The purpose of this panel is to put some of ... problems before the conference. The panel& apos;s motivation stems partly from the fact that, too often in the past, discussion of natural- language access to databases has focused, at the expense ... languages typically provide some means for counting and totaling that must be invoked for answering "how much" or "how many" questions. The mapping between a natural- language...
... local databases. ) This dlalogue results in extension of the language- processlng and data access components that make it possible for an end user to query the new database in natural language. ... information about the files and fields in the conventlonal database for which a natural- language interface is desired. (Typlcally this database already exists and is populated, but TEAM ... TRANSPORTABLE NATURAL- LANGUAGE INTERFACES: PROBLEMS AND TECHNIQUES Barbara J. Grosz Artificial Intelligence Center SRI International, Menlo Park, CA 94025 Department of Computer and Information...
... basis for handling these and many other problems in natural language access to databases. In addition to considering some subset of the chairman's five problems, each of the panelists ... A.JACCN = C.JACCN AND C.JACCN = D.JACCN AND B.SBLOCK = C.SBLOCK AND D.LUC = '0910' AND B.SUBPLA= '4100'; (We note for the careful reader that '0910' and '4100' ... ISSUES IN NATURALLANGUAGE ACCESS TO DATABASES S. R. Petrick IBM T.J. Watson Research Center INTRODUCTION In responding to the guidelines established by the session chairman of this panel, ...
... issues in naturallanguage (NL) access to databases in the light of an experimental NL questlon-answering system, Chat, which I wrote with Fernando Perelra at Edinburgh University, and which ... AJCL]. 9. Warren D H D, Pereira L M and Perelra F C N. Prolog - the languageand its implementation compared with Lisp. ACM Symposium on AI and Programming Languages, Rochester, New York, Aug ... Machine Intelligence Workshop, Cleveland, Ohio, Nov 1981. 8. Warren D H D and Pereira F C N. An efficient easily adaptable system for interpreting natural language queries. Research Paper 156,...
... R. C. and Birnbaum. Memory, Meaning, and Syntax. Technical Report 189, Yale University, Department of Computer Science, 1980. Sehank, R. C. Dynamic Memory: A Theory of Reminding and Learning ... Report KB-VLS1-81-13, Xerox PARC, 1981. Kaplan, S. J. Cooperative Responses from a Portable Natural Language Query System. Artificial Intelligence 19(1982) :165-187, 1982. Montague, R. Proper ... Flowers and Lawrence Birnbanm of Yale University, Department of Computer Science. References [Bobrow 81] [Kaplan 82] [Montague 74] [Nishida 88] [Schank 80] [Schank 82] Bobrow, D. G. and...
... alignment and consistency (Picker-ing and Garrod, 2004; Halliday and Hasan, 1976) onthe one hand, and variation (to improve text quality and readability) on the other hand (Belz and Reiter,2006; ... (Halliday and Hasan, 1976), and variation,which influence people’s assessment of discourse(Levelt and Kelter, 1982) and generated output (Belz and Reiter, 2006; Foster and Oberlander, 2006).Also, in ... greedy or random baselines.1 IntroductionSurface realisation decisions in a Natural Language Generation (NLG) system are often made accord-ing to a language model of the domain (Langkilde and Knight,...
... lines and j rows with binary values. The value zij = 1 (zij = 0) means that the word i influences (not) the word j. In figure 1 every link stands for zij = l. The models 1, 2 and 2 ~ and ... Conf on Theor. and Method- ological Issues in Machine Translation, pages 240-255, Leuven, Belgium, July. K. Greer, B. Lowerre, and L. Wilcox. 1982. Acoustic Pattern Matching and Beam Search- ... and a probability p(ejlEj). For p(ejle~ -1) we use a class-based polygram language model (Schukat-Talamazzini, 1994). For the transla- tion probability p(ej Id, Z) we use model 1 and...
... Translation and its application to NaturalLanguage Database Interfacing. Ph.D. Thesis, Royal Institute of Technology, Stockholm, Sweden. 316 Semantic Information Preprocessing for NaturalLanguage ... time and may avoid errors introduced by hand- coding selectional restrictions. 1 Introduction An approach is described for supplying selectional restrictions to parsers in naturallanguage ... would like to thank Fred Popowich and Dan Fass for their valuable discussion and sugges- tions. This work was partially supported by the Nat- ural Sciences and Engineering Research Council...
... for natural language interfaces? What standards should he set for naturallanguage systems performance? What kinds of evaluations should be run in the future? How should they be designed and ... user and the requirements of the task. The user brings his own naturallanguageand his own style of interaction to the system. The task brings the questions that must be answered and the ... determine user bias and experience beforehand, and user satisfaction afterward? IIl. On the basis of these evaluations, what should the future look like for natural language access to database?...
... empirical study, and presents our method for handling generalized ellipsis resolution in the XCALIBUR expert system interface. With the exception of inter- sentential metalanguage, and to a lesser ... cognitively less demanding task for a user to correct a previous utterance than to repeat an explicit sequence of commands (or worse yet, to detect and undo explicitly each and every unwanted ... ascertain the most pressing needs of natural language interfaces in interactive apl~lications, The initial objective of this study was to circumscribe the naturallanguage interface task by attempting...
... "Sandy gives a chair to Kim" LISZT (SandyRel [HANDEL h4 ], GiveRel [HANDEL hl], TempOver [HANDEL hl], Some [HANDEL h9], ] ChairReI[HANDEL hlO], To[HANDEL h12], KimRel[HANDEL ... "HANDEL hl INDEX e2 LISZT [.ANDEL hl] ] /EVEN~ ez [RANDEL IHANDEL hi [ACT x5 SandyRel L INST ~5 , |PREPARG x6 ' TempOver [EVENT e2 , GiveRel LUND x7 [HANDEL hl2] [.ANDEL ... Keller, and Kedar-Cabelli, 1986; van Harmelen and Bundy, 1988; Minton et al., 1989) has successfully been applied to control and speeding-up natural language parsing (Rayner, 1988; Samuelsson and...
... insightsthat may lead to a more thorough understanding of language uses and users. Such insights may in factdecisively advance language science and artificial natural language intelligence.AcknowledgmentsI ... (and thus commu-nicatively cumbersome) language. From a practical, application-oriented point ofview, dedicating more resources and efforts to sub-jective naturallanguage problems is a natural ... Incomputational linguistics andnaturallanguage pro-cessing (NLP), current efforts on subjective natural language problems are concentrated on the vibrantfield of opinion mining and sentiment analysis...