James Shaw. 1998. Segregatory coordination and ellipsis in text generation. In Proc. of the COLING and the ACL., Montreal, Canada.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....a same input data this flexibility is not found in the mentioned alternative approaches (topictree RST) To work together with our discourse organization approach we developed a new content aggregation approach based in a factorization process. Previous aggregation approaches (such as [3] [17]) relies on some linguistic syntactic rhetoric internal representation for clauses. In contrast with previous approaches, our factorization approach works all time on a semantic layer of representation, keeping the same portability of the content matrix. A limitation of the factorization approach ....

Shaw, J.: Segregatory coordination and ellipsis in text generation. In Proc. of the 17 th COLING'98. (1998).

....separations imposed by the narrative segmenter and proceeds to send paragraph sized batches to the revision component (described in the following section) in order to improve overall prose quality. 3. 3 Revision Revision modules [Dalianis and Hovy, 1993; Robin, 1994; Callaway and Lester, 1997; Shaw, 1998 ] take a series of protosentences (simple sentences with limited content, e.g. The wolf saw Little Red Riding Hood ) and rearrange them by aggregation, i.e. combining protosentences in various ways, or by migration, i.e. permuting the order of two adjacent protosentences. The REVISOR component ....

James Shaw. Segregatory coordination and ellipsis in text generation. In COLING-ACL-98: Proceedings of the Joint 36th Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics, pages 1220--1226, Montreal, Canada, 1998.

....an example of (b) is John is tired and hungry from John is tired and John is hungry. There is a relatively large body of literature describing syntactic aggregation including [Hov90] Hov91] Dal92a] Dal92b] Dal95b] Dal95a] Dal96b] Dal97] DH96b] MKS94] Sha95] SM97] Sha98a] Sha98b] Sig92] and [Kem91] The most elaborated examples of this work are those of Dalianis and Hovy and Shaw. Dalianis and Hovy discuss the problems of rule ordering and rule preferences and outline a solution and implementation based on a corpus study. Shaw s work has changed recently ( Sha98a] ....

....[Sig92] and [Kem91] The most elaborated examples of this work are those of Dalianis and Hovy and Shaw. Dalianis and Hovy discuss the problems of rule ordering and rule preferences and outline a solution and implementation based on a corpus study. Shaw s work has changed recently ( Sha98a] Sha98b] Rather than implementing aggregation rules directly in the planner, the planner marks recurring elements and lets the realizer decide which elements to realize or not. 6.5 Lexical aggregation [Cah98] is a study of lexicalisation (lexical choice) in applied NLG systems. There Cahill makes a ....

James Shaw. Segregatory coordination and Ellipsis in Text Generation. COLING-ACL'98.

....are very similar to the muc templates used by summons. Hence one of the main problems for plandoc is to form a grouping that puts the most similar items together, allowing the use of conjunction and ellipsis to delete repetitive material. This task is called aggregation [Dalianis and Hovy, 1993, Shaw, 1998] For summarizing multiple news articles, the task is almost the opposite we need to nd the di erences from one article to the next, to identify how the reported facts have changed. Thus, one of our main problems was to identify summarization strategies which indicate how information is linked ....

....of the activities of telephone planning engineers, using linguis 135 tic summarization to both order its input messages and to combine them into single sentences. Focus has been on the combined use of conjunction, ellipsis and paraphrase to result in concise, yet uent reports [Shaw, 1995, Shaw, 1998] zeddoc [Passonneau et al. 1997, Kukich et al. 1997] generates Web trac summaries for advertisement management software. It makes use of an ontology over the domain to combine information at the conceptual level. All of these systems take tabular data as input. The research focus has been on ....

James Shaw. Segregatory coordination and ellipsis in text generation. In Proceedings of the Joint 17th International Conference on Computational Linguistics 36th Annual Meeting of the Association for Computational Linguistics (COLING-ACL'98), pages 1220-1226, Montreal, Canada, August 1998.

....are very similar to the muc templates used by summons. Hence one of the main problems for plandoc is to form a grouping that puts the most similar items together, allowing the use of conjunction and ellipsis to delete repetitive material. This task is called aggregation [Dalianis and Hovy, 1993, Shaw, 1998] For summarizing multiple news articles, the task is almost the opposite we need to find the di#erences from one article to the next, to identify how the reported facts have changed. Thus, one of our main problems was to identify summarization strategies which indicate how information is ....

....of the activities of telephone planning engineers, using linguis 135 tic summarization to both order its input messages and to combine them into single sentences. Focus has been on the combined use of conjunction, ellipsis and paraphrase to result in concise, yet fluent reports [Shaw, 1995, Shaw, 1998] zeddoc [Passonneau et al. 1997, Kukich et al. 1997] generates Web tra#c summaries for advertisement management software. It makes use of an ontology over the domain to combine information at the conceptual level. All of these systems take tabular data as input. The research focus has been on ....

James Shaw. Segregatory coordination and ellipsis in text generation. In Proceedings of the Joint 17th International Conference on Computational Linguistics 36th Annual Meeting of the Association for Computational Linguistics (COLING-ACL'98), pages 1220--1226, Montreal, Canada, August 1998.

.... reduction ( Foxes and wolves are animals ) and ellipsis or gapping ( Foxes are larger than birds and smaller than wolves ) Methods addressing these phenomena comprise a structurally motivated set of transformation operators [4] and a procedure oriented on linguistic realization constraints [11]. Especially the last mentioned technique is relevant for our purposes due its systematic and computationally effective organisation. 4 The Functionality of Our Method As already mentioned in the background section, presenting Herbrand models basically is considered as listing a set of partially ....

....methods mentioned in the previous section to the specific requirements of checking models. In doing this, we first address the inferability of facts, which works relatively straightforward in our context. Next, we emphasize and motivate the changes applied to the aggregation procedure adopted from [11]. Finally, we illustrate the extensions we incorporate into this method. 4.1 Exploiting the inferability of facts To start with, facts that constitute part of a problem s definition are omitted, since they are known to the user and they are always validated to true. In addition, we consider a fact ....

[Article contains additional citation context not shown here]

J. Shaw. Segregatory coordination and ellipsis in text generation. In Proc. of the 36th Association for Computational Linguistics and the 17th International Conference on Computational Linguistics. 1998.

No context found.

James Shaw. 1998. Segregatory coordination and ellipsis in text generation. In Proc. of the COLING and the ACL., Montreal, Canada.

No context found.

James Shaw. 1998b. Segregatory coordination and ellipsis in text generation. In Proc. of the 17th COLING and the 36th ACL.

....ARG2: John finished his work and [John] went home. The APG1 in second proposition Johff is deleted. Due to limited space, we only describe the algorithm used in C SPEI to produce sentences .with coordinations. For a more detailed discussion with relevant linguistic motivations; please see [Shaw, 1998]. We have divided the algorithm into four stages: where the first three stages take place in the sentence planner and the last stage takes place in the lexical chooser: Stage 1: group propositions and order them according to their similarities while satisfying pragmatic and contextual ....

Shaw, J. Segregatory coordination and ellipsis in text generation. In To appear in Proc. of the 17th COLINC and the 36th Annual Meeting of the ACL.

....in Proc. of the 1st INLG, Mitzpe0 35 Israel, pp. 100 107, 2000 Generating Referring Quanti ed Expressions James Shaw and Kathleen McKeown Dept. of Computer Science Columbia University New York, NY 10027, USA shaw,kathy cs.columbia.edu Abstract In this paper, we describe how quanti ers can be generated in a text generation system. By taking advantage of discourse and ontological information, quanti ed ....

James Shaw. 1998. Segregatory coordination and ellipsis in text generation. In Proc. of the 17th COLING and the 36th Annual Meeting of the ACL., pages 1220-1226.

....ARG2: John finished his work and [John] went home. 1 The ARG1 in second proposition John is deleted. Due to limited space, we only describe the algorithm used in Casper to produce sentences with coordinations. For a more detailed discussion with relevant linguistic motivations, please see [Shaw, 1998]. We have divided the algorithm into four stages, where the first three stages take place in the sentence planner and the last stage takes place in the lexical chooser: Stage 1: group propositions and order them according to their similarities while satisfying pragmatic and contextual ....

Shaw, J. Segregatory coordination and ellipsis in text generation. In To appear in Proc. of the 17th COLING and the 36th Annual Meeting of the ACL.

.... Among Premodifiers James Shaw and Vasileios Hatzivassiloglou Department of Computer Science Columbia University New York, N.Y. 10027, USA shaw, vh cs.columbia.edu Abstract We present a corpus based study of the sequential ordering among premodifiers in noun phrases. This information is important for the fluency of ....

James Shaw. Segregatory Coordination and Ellipsis in Text Generation. In Proceedings of the 36th Annual Meeting of the ACL and the 17th International Conference on Computational Linguistics (ACL/COLING-98), pages 1220--1226, Montreal, Canada, 1998.

No context found.

James Shaw, "Segregatory Coordination and Ellipsis in Text Generation", Proc. of COLING-ACL, pp. 1220-1226 , 1998.

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