experiments in natural language generation

Ngày tải lên: 31/03/2014, 03:20

... to boosting. In Proceedings of the Sixteenth Interna- tional Joint Conference on Artificial Intelligence. Hinrich Sch ¨ utze. 1992. Dimensions of meaning. In Proceedings of Supercomputing, pages ... Computational Linguistics, pages 704–710, Montreal. Irene Langkilde and Kevin Knight. 1998b. The practi- cal value of n-grams in generation. In Proceedings of the International Natural Language Generation Workshop, ... previously seen instances by counting the number of feature values that the two instances had in common. In computing the similarity score, features were weighted by their information gain, an in- formation...

Ngày tải lên: 08/03/2014, 05:20

Ngày tải lên: 17/03/2014, 19:21

Ngày tải lên: 24/03/2014, 02:20

Ngày tải lên: 31/03/2014, 04:20

... propositions, including in- serting into the instance C i and separating the rest as independent sentence(s). 569 5. Generate a solution in which ∀p k ∈ E j , insert p k to C i . All the propositions in ... of propositions in P . Revised minimum set covering: we employ a greedy minimum set covering algorithm in which we first find the set S in the corpus that maximizes the overlapping of propositions in the input ... using C i with an insertion cost of icost(C H ,p j ), in which C H is the host sentence in the corpus containing proposition p j . Using an ex- ample from our real-estate domain, assume the input P...

Ngày tải lên: 20/02/2014, 15:20

... 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...

Ngày tải lên: 21/02/2014, 20:20

... 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...

Ngày tải lên: 21/02/2014, 20:20

... ISSUES IN NATURAL LANGUAGE 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...

Ngày tải lên: 21/02/2014, 20:20

... 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...

Ngày tải lên: 21/02/2014, 20:20

... Algorithm for Incremental Singular Value Decomposition in Natural Language Processing Genevieve Gorrell Department of Computer and Information Science Link¨oping University 581 83 LINK ¨ OPING Sweden gengo@ida.liu.se Abstract An ... 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 natural language 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...

Ngày tải lên: 22/02/2014, 02:20

... 6th International Con- ference on Natural Language Generation (INLG). Nina Dethlefs, Heriberto Cuay´ahuitl, and Jette Viethen. 2011. Optimising Natural Language Generation De- cision Making for ... Liang, and Dan Klein. 2010. A simple domain-independent probabilistic approach to generation. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, EMNLP ’10, ... generat- ing instructions in virtual environments. In M. The- une and E. Krahmer, editors, Empirical Methods on Natural Language Generation, pages 337–361, Berlin/Heidelberg, Germany. Springer. Irene...

Ngày tải lên: 07/03/2014, 22:20

... planning for natural language generation. In ICAPS. Alexander Koller and Matthew Stone. 2007. Sentence generation as planning. In Proceedings of ACL. Oliver Lemon. 2008. Adaptive Natural Language Generation ... corpora contain data from “overhearer” experiments targeted to Information Presentation in dialogues in the restaurant domain. While we are ultimately interested in how hearers engaged in dialogues ... 2008a. Does this list contain what you were searching for? Learn- ing adaptive dialogue strategies for Interactive Ques- tion Answering. J. Natural Language Engineering, 15(1):55–72. Verena Rieser...

Ngày tải lên: 08/03/2014, 21:20

... approach is also very interesting for natural language generation (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...

Ngày tải lên: 08/03/2014, 21:20

... "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,...

Ngày tải lên: 09/03/2014, 01:20

... partial derivation in the planning state, and to encode the action of adding each elementary tree in the plan- ning operators. The encoding of our example as a planning problem is shown in Fig. 2. In the ... tree we 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 solved by converting it into a planning problem (Nau ... precondition canadjoin(A, u) ad- joins into a node of category A in the elementary tree that was substituted into u. CRISP allows multiple trees to adjoin into the same node. In this case, the...

Ngày tải lên: 17/03/2014, 00:20

... 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 Natural Language Generation 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....

Ngày tải lên: 17/03/2014, 04:20

... 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...

Ngày tải lên: 17/03/2014, 08:20

... 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...

Ngày tải lên: 17/03/2014, 19:21

Ngày tải lên: 17/03/2014, 19:21