... toboosting. In Proceedings of the Sixteenth Interna-tional Joint Conference on Artificial Intelligence.Hinrich Sch¨utze. 1992. Dimensions of meaning. In Proceedings of Supercomputing, pages ... ComputationalLinguistics, pages 704–710, Montreal.Irene Langkilde and Kevin Knight. 1998b. The practi-cal value of n-grams in generation. In Proceedingsof the International NaturalLanguage Generation Workshop, ... previously seen instances bycounting the number of feature values that the twoinstances had in common. In computing the similarity score, featureswere weighted by their information gain, an in- formation...
... propositions, including in- serting into the instance Ciand separating therest as independent sentence(s).5695. Generate a solution in which ∀pk∈ Ej, insertpkto Ci. All the propositions in ... ofpropositions in P .Revised minimum set covering: we employ agreedy minimum set covering algorithm in whichwe first find the set S in the corpus that maximizesthe overlapping of propositions in the input ... using Ciwith an insertion cost oficost(CH,pj), in which CHis the host sentence in the corpus containing proposition pj. Using an ex-ample from our real-estate domain, assume the inputP...
... chaining Inferencer Is then called to generate any ~nown preconditions for the act INGEST. The primary precondition (causative inference) for drinking is that the person doing the drinking ... establishing containment, since wine is known to be OUTPUTFROM bottles but bottles are not always assumed to hold wine. Another inference made during the initial analysis finds the ... completes the linking of tne causal chain between tne events described in the sentence. Second, it causes the filling of empty slots appearing in either the enabled act or In the enabling act, wherever...
... of set domain relational calculus used in TQA then provides a basis for either taking the initiative in automat- ically printing these implicitly requested values or for engaging in a dialog ... second NP dominates the string "WARD 1 BLOCK 2". The feature + UNIT on a node that dominates PARKING SPACE is not found in the corresponding structure involving PARKINGLOT, and this ... clear in the sequel, the transformational apparatus utilized in the TQA Ques- tion Answering System provides a principled basis for handling these and many other problems in natural language...
... ISSUES INNATURALLANGUAGE ACCESS TO DATABASES FROM A LOGIC PROGRAMMING PERSPECTIVE David H D Warren Artificial Intelligence Center SRI International, Menlo Park, CA 94025, USA I INTRODUCTION ... V. Translating Spanish into logic through loglc. AJCL 7, 3 (Sep 1981), pp. 149- 164. 4. Fuchi K. Aiming for knowledge information vrocessing systems. Intl. Conf. ou Fifth Generation Computer ... within the English subset are answered in well under one second, including queries which involve taking Joins between relations having of the order of a thousand tuples. A disadvantage of much...
... in is interpreted as an entire nucleus, complete with consequent state, for by definition the consequent state includes whatever other events were contingent upon Harry walking in, including ... points or culminations, they can be used to describe extended events such as our processes, in terms of a pair identifying their start- ing point and to the point at which they stop (in ... culmination (in the case of culminated processes). This means that a process expression like John ran will introduce two events, one indicating the start of the pro- cess and one indicating...
... Algorithm for Incremental Singular ValueDecomposition inNaturalLanguage ProcessingGenevieve GorrellDepartment of Computer and Information ScienceLink¨oping University581 83 LINK¨OPINGSwedengengo@ida.liu.seAbstractAn ... sys-tem has seen dur ing training, it will invari-ably see something new at ru n-time in a do-main of any complexity. Any approach to au-tomatic naturallanguage processing will en-counter ... natu-ral language problems involve sparse matrices,since there are many words in a natural lan-guage and the great majority do not appear in, for example, any one document. Domains in which...
... 6th International Con-ference on NaturalLanguageGeneration (INLG).Nina Dethlefs, Heriberto Cuay´ahuitl, and Jette Viethen.2011. Optimising NaturalLanguageGeneration De-cision Making for ... Liang, and Dan Klein. 2010. Asimple domain-independent probabilistic approach to generation. In Proceedings of the 2010 Conference onEmpirical Methods inNaturalLanguage Processing,EMNLP ’10, ... generat-ing instructions in virtual environments. In M. The-une and E. Krahmer, editors, Empirical Methodson NaturalLanguage Generation, pages 337–361,Berlin/Heidelberg, Germany. Springer.Irene...
... planning for naturallanguage generation. In ICAPS.Alexander Koller and Matthew Stone. 2007. Sentence generation as planning. In Proceedings of ACL.Oliver Lemon. 2008. Adaptive Natural Language Generation ... 2008a. Does thislist contain what you were searching for? Learn-ing adaptive dialogue strategies for Interactive Ques-tion Answering. J. NaturalLanguage Engineering,15(1):55–72.Verena Rieser ... Natural Language Generationin Dialogue using Reinforcement Learn-ing. In Proceedings of SEMdial.Johanna Moore, Mary Ellen Foster, Oliver Lemon, andMichael White. 2004. Generating tailored, com-parative...
... approach is also very interesting for naturallanguagegeneration (NLG). Informally, NLG is the production of a natural language text from computer-internal representa- tion of information, where ... with the constraints of the terminal elements in the order specified by the terminal yield. We also call this step terminal- matching. In our current system terminal- matching is performed ... the remaining suffix is not empty. In other words, the decision tree is now a finite representation of an infinite structure, because implicitly, each endpoint of an index bears a pointer to...
... "planning unit" in human language generatinn. This has been an important question in psycholinguistic research as well (Garrett [19S2D. This continum our ongoing line of research ... Spring 1984. McDonald,D. & E. I. Conklin (in preparation) "At the Interface of Planning and Realization" in Bloc and McDonald (eds.) Natw 1 LanfuaSe Generation Systems, Springer-Veflag. ... domains, online text generation suffices. This method, in fact, provides us with an interesting diagnostic to test our theory of style: namely, that stylistic rules are meaning-pre~rving,...
... partialderivation in the planning state, and to encode theaction of adding each elementary tree in the plan-ning operators. The encoding of our example as aplanning problem is shown in Fig. 2. In the ... treewe build in this way.3.2 TAG generation as planning In the CRISP system, Koller and Stone (2007)show how this generation problem can be solvedby converting it into a planning problem (Nau ... premodifierindex of zero; adjoining an adjective of a certainclass then raises this number to the index for thatclass. As the operators in Fig. 6 illustrate, color adjectives such as “red” have index...
... main challenges identified so far can be summarized as follows. Simplicity in interacting with user due to limited mental maturity level of users Flexibility in taking input Generating ... tech-nique can increase the communication rate of users during a conversation. 1 Introduction NaturalLanguageGeneration also known as ‘Automated Discourse Generation or simply ‘Text Generation , ... Adjoining Grammar (TAG) struc-ture. The template-based approach that has been taken in the system, enables the basic language generation algorithms application independent and language independent....
... instructions found mainly in the cooking domain. The example used by Karlin is (4). Steam for g minutes or until the mussels (4) open. Karlin asserts that 'the meaning of sentences in ... all processes in the cooking domain must have culminations. The validity of this approach is dis- cussed in the next section. However, before doing that we examine Karlin's final class, ... 1988. [3] Karlin, Robin "Defining the semantics of ver- bal modifiers in the domain of cooking tasks." Proc. 26th Annual Meeting of the Association for Computational Linguistics, Buffalo...
... avoid false implication of a finished topic. These two guidelines for changing and maintaining focus during the process of generating language provide an ordering on the three basic legal ... language text. In the past, researchers have concentrated on local issues concerning the syntactic and lexical choices involved in transforming a pre-determined message into natural language. The ... contains information relevant to the discourse purpose. The focusing mechanism helps maintain discourse coherency. It aids in the organization of the message by constraining the selection of information...