Shaw, J.: Clause aggregation using linguistic knowledge. In: Proc. of the IWNLG. (1998)  Home/Search   Document Details and Download   Summary   Related Articles   Check

.... constructions (rather than lexical choice) so we map each elementary communicative goal to a canonical lexico syntactic structure (called a DSyntS [11] We then randomly combine these DSyntSs into larger DSyntSs using a set of clause combining operations identified previously in the literature [14, 18, 5], such as RELATIVECLAUSE, CONJUNCTION, and MERGE. 2 The way in which the elementary DSyntSs are combined is represented in a structure called the sp tree. Each sp tree is then realized using an off the shelf realizer, RealPro [9] Some sample realizations for the same text plan are shown in ....

J. Shaw. Clause aggregation using linguistic knowledge. In Proceedings of the 8th International Workshop on Natural Language Generation, Niagara-on-the-Lake, Ontario, 1998.

.... operations that incrementally transform a list of elementary predicate argument representations (lexico structural representations called DSyntS [4] into a list of lexico structural representations of single sentences, by combining them using the operations exemplified in Figure 5[5, 6]. The result of applying the operations is a sentence plan tree (or sp tree for short) which is a binary tree with leaves labeled by the speech acts from the input text plan, and interior nodes labeled with clausecombining operations. The complexity of most sentence planners arises from the ....

J. Shaw. Clause aggregation using linguistic knowledge. In Proceedings of the 8th International Workshop on Natural Language Generation, 1998.

....in the literature. They are listed in Table 1 and are classified in four groups. 1 From each group an exemplar goal is indicated next to the group name which we take to subsume the other goals in the group. Group 1 concise brief [MM81, p. 28] concise [SdS90, p. 61] MKS94, p. 7] Sha95] Sha98a] SdS90, p. 48] condensed [MM81, p. 26] contains no inferable information [DH96b] no previously known information [MM81, p. 24] non redundant [Wil95, p. 11] Wil95, p. 12] MM81, p. 26] DH96b] selective [MM81, p. 26] short [Sha98a] Group 2 coherent clear [SdS90, p. 48] coherent ....

....p. 28] concise [SdS90, p. 61] MKS94, p. 7] Sha95] Sha98a] SdS90, p. 48] condensed [MM81, p. 26] contains no inferable information [DH96b] no previously known information [MM81, p. 24] non redundant [Wil95, p. 11] Wil95, p. 12] MM81, p. 26] DH96b] selective [MM81, p. 26] short [Sha98a] Group 2 coherent clear [SdS90, p. 48] coherent [FH95, p. 1] MKS94, p. 10] easy to decode the intended message [SdS90, p. 47] easy to read [Dal96a] RM96, p. 9] easy to understand [Sha95] supportive of focus structure [Wil95, p. 12] MKS94, p. 10] supportive of rhetorical structure ....

[Article contains additional citation context not shown here]

James Shaw. Clause Aggregation using Linguistic Knowledge. INLGW98.

....Even with a reasonably small inventory, the system can have many good matches, which makes the memory based approach e#ective and attractive. For example, MAGIC employs a flexible advanced sentence generator that produces di#erent sentence structures using opportunistic clause aggregation (Shaw 1998). Even in MAGIC, given two randomly selected systemgenerated patient reports, about 20 of the sentences and 80 of the vocabulary overlap. In this section, we describe the signature feature vector which represents the linguistic features used for matching, followed by the matching algorithm and ....

Shaw, J. 1998 Clause Aggregation using linguistic knowledge. In Proc. 9th Int. Workshop on Natural Language Generation, Niagara-on-the-lake, Canada, 1998, pp. 138--147.

....require the particular treatment given for this hypertensive event to be presented. The sentence planner decides the content of each sentence and the semantic constraints between semantic units in a sentence. It also imposes syntactic constraints between each unit. In MAGIC, the sentence planner [ Shaw, 1998 ] decides how much information can fit into one sentence. Within each sentence, the sentence planner first chooses a core sentence structure and then augments it with additional information, depending on its relations with the core structure and the semantic and syntactic constraints of realizing ....

James Shaw. Clause aggregation using linguistic knowledge. In Proceedings of the 9th International Workshop on Natural Language Generation, Niagara-on-the-Lake, Ontario, Canada, 1998.

No context found.

Shaw, J.: Clause aggregation using linguistic knowledge. In: Proc. of the IWNLG. (1998)

No context found.

James Shaw. 1998a. Clause aggregation using linguistic knowledge. In Proc. of the 9th INLG.

.... 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. Clause Aggregation Using Linguistic Knowledge. In Proceedings of the 9th International Workshop on Natural Language Generation., pages 138--147, 1998.

....in Proc. of COLING ACL,OLIN Segregatory Coordination and Ellipsis in Text Generation James Shaw Dept. of Computer Science Columbia University New York, NY 10027, USA shaw cs.columbia.edu Abstract In this paper, we provide an account of how to generate sentences with coordination constructions from clause sized semantic representations. An algorithm is developed and various examples from ....

James Shaw. 1998. Clause aggregation using linguistic knowledge. In Proc. of the 9th International Workshop on Natural Language Generation.

No context found.

James Shaw. Clause aggregation using linguistic knowledge. In Proceedings of the 8th International Workshop on Natural Language Generation, Niagara-on-the-Lake, Ontario, 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