Leila Kosseim and Guy Lapalme. Content and Rhetorical Status Selection in Instructional Texts. In Proceedings of the Seventh International Workshop on Natural Language Generation, pages 53--60, Kennebunkport, Maine, 1994.  Home/Search   Document Details and Download   Summary   Related Articles   Check

.... developed to support the production of technical documentation (in one language) have also been fully automated systems, bypassing the technical communicator totally, e.g. Wahlster et al. [25] Feiner and McKeown [9] Peter and Rosner [17] Vander Linden [24] Dale [6] Kosseim and Lapalme [15], and Reiter et al. [19] In contrast, our goal within the drafter project [16] is to provide tools to support rather than replace the translator, designed with the benefit of interviews with professional linguists to ascertain their requirements. We have thereby sought to avoid the errors of ....

Leila Kosseim and Guy Lapalme. Content and Rhetorical Status Selection in Instructional Texts. In Proceedings of the Seventh International Workshop on Natural Language Generation, pages 53--60, Kennebunkport, Maine, 1994.

....relations; and few systems use exactly those relations proposed in rst. Departures from rst s original set are of many different types. rst relations have been subdivided for instance, Rosner and Stede s step sequence is a specialisation of the rst relation sequence, as is Kosseim and Lapalme s [18] action sequence. rst relations have also been amalgamated to form new relations; for instance, Scott and Souza combine the relations volitional cause, non volitional cause, volitional result, non volitional result and evidence, for the purposes of textual realisation. Alternative cuts can also ....

L Kosseim and G Lapalme. Content and rhetorical status selection in instructional texts. In Proceedings of the 7th International Workshop on Natural Language Generation, pages 53--60, Kennebunkport, Maine, 1994.

....applicable to our generator. 4 Coding features Our lexico grammatical coding was done using the networks and features of the Nigel grammar [Halliday1985] We focused on four main concerns, guided by previous work on instructional texts, e.g. Lehrberger1986, Plum et al..1990, Ghadessy1993, Kosseim and Lapalme1994] ffl Relations between processes : to determine whether textual cohesion was achieved through conjunctives or through relations implicit in the task structure elements. Among the features considered were clause dependency and conjunction type. ffl Agency : to see whether the actor performing ....

....Each unit is taken to be the expression of a single task element. Our definition of the task elements is based on the concepts and relations commonly chosen to represent a task structure (a goal and its associated plan) e.g. Fikes and Nilsson1971, Sacerdoti1977] and on related research, e.g. Kosseim and Lapalme1994] Our generator produces instructions from an underlying semantic knowledge base which uses this representation [Paris et al..1995] To generate an instruction for performing a task is to chose some task elements to be expressed and linearise them so that they form a coherent set for a given goal ....

[Article contains additional citation context not shown here]

Leila Kosseim and Guy Lapalme. 1994. Content and rhetorical status selection in instructional texts. In Proceedings of the Seventh International Workshop on Natural Language Generation, Kennebunkport, MN, 21--24 June 1994, pages 53--60.

....can be put to other than planning. Because of the severely restricted domain of application of such knowledge, the representations and techniques employed by systems such as PEA leave much to be desired in view of the need for cost effectiveness mentioned in chapter 1. 2.4. 4 Kosseim and Lapalme Kosseim and Lapalme s work (1994) focused on determining the content and structure of instructional texts. Their work emphasized two types of tasks: operator tasks, i.e. procedures on a system or device to accomplish a goal external to that system device (e.g. mowing the lawn) and maintenance repair tasks, i.e. specific ....

Kosseim, L. and Lapalme, G. (1994). Content and rhetorical status selection in instructional texts.

....then the NLG tool can take care of them (producing versions in all supported languages) leaving technical writers and translators to focus their efforts on more varied and difficult passages. By comparison, other recent work on the generation of multilingual instructions (R osner and Stede, 1992; Kosseim and Lapalme, 1994; Bateman, 1996; Kittredge and Polguere, 1991) has not addressed the problem of linking a text generator to a tool for defining the knowledge content. 1 We gratefully acknowledge the contribution of our colleagues Roger Evans, Markus Fischer, Tony Hartley, Cecile Paris, Lyn Pemberton and Keith ....

Leila Kosseim and Guy Lapalme. 1994. Content and rhetorical status selection in instructional texts. In Proceedings of the Seventh International Workshop on Natural Language Generation, Kennebunkport, MN, 21--24 June 1994, pages 53--60.

....by the Engineering and Physical Sciences Research Council (EPSRC) Grant J19221, by BC DAAD ARC Project 293, and by the Commission of the European Union Grant LRE 62009. More recently, there has been an emphasis on the generation of multilingual instructions, e.g. R osner and Stede, 1991; Kosseim and Lapalme, 1994] The latter is not entirely surprising since multilingual manuals are important not only for European manufacturers, who are required to produce manuals in the language of the end user, but also for other multinational companies, whose overseas sales are reported to constitute over half of ....

Kosseim, Leila and Lapalme, Guy 1994. Content and rhetorical status selection in instructional texts. In Proceedings of the Seventh International Workshop on Natural Language Generation, Kennebunkport, ME, 21--24 June 1994. 53--60.

....operations schemas) some planning process selects, links and instantiates knowledge into a conceptual representation of the procedure to be described. This step is generally performed by a task planner similar to noah [Sacerdoti, 1977] cf. Mellish, 1988, Dale, 1992, Vander Linden, 1993, Kosseim and Lapalme, 1994]) This choice follows psychological evidence that a procedure s representation is hierarchical in structure and contains instantiated schemas of operations [Dixon et al. 1988, Britton et al. 1990, Donin et al. 1992] 1 This model assumes a linear generation process. Mapping Process II: ....

....From the conceptual representation of the procedure, the content of the text (what will be included and what will be left unsaid) is selected. This mapping produces a semantic representation of the instructional text. This step has not received much attention in previous work (but see for example [Kosseim and Lapalme, 1994] for an attempt) probably by fear that computational linguists start from rather subjective conceptual representations of procedures. Mapping Process III: From the semantic content of the text, the rhetorical structure is selected. In previous work (e.g. Mellish, 1988, Dale, 1992] this mapping ....

[Article contains additional citation context not shown here]

Kosseim, L. and Lapalme, G. (1994). Content and Rhetorical Status Selection in Instructional Texts. In Proceedings of the 7 th International Workshop on Natural Language Generation, pages 53--60, Kennebunkport, Maine.

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