Daniel Marcu. 1997. From local to global coherence: A bottom-up approach to text planning. In Proceedings of Fourteenth National Conference on Artificial Intelligence (AAAI-1997), pages 450--456.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....by the goals and their decom position. That is, a generator needs strategies for decomposing the achievement of complex goals into sequences of utterances, rather than ways of combining sequences of utterances into more complex structures. Generation is top down , rather than bottom up [Marcu 97] Our belief is that there is an important class of NLG problems for which these basic assumptions. are not helpful. These problems all involve situations where semi fixed explanation strategies are less useful than the ability to exploit opportunities. WordNet gives the following definition of ....

....another one that mentions the same entity. Other text planning operations that are opportunistic in nature include aggregation [Dalianis and Hovy 96] and redundancy suppression [McDonald 92] though we will not consider these here. The second step described above is exactly that described by [Marcu 97] That is, one is given a set of facts all of which should be included in a text .and a set of relations between facts, some of which can be included in the text. The task is to produce a legal RS tree using the facts and some relations (or the best: such tree) Marcu s approach first of all ....

Marcu, D., "From local to global .coherence: a bottom-up approach to text Planning", in Pro- ceedings of AAAI-97, pp629-635, American Association for Artificial Intelligence, 1997..

....that a text is coherent just in case it can be analysed .hierarchically in terms of relations between text spans. Much work in NLG makes the assumption that constructing something like an RS tree is a necessary step i n the planning of a text. This work takes as its starting point Marcu s [Marcu 97] excellent formalisation of RST and the problem of building legal RST trees, and for the purposes of this paper the phrase text planning will generally denote the task characterised by him. In this task, one is given a set of facts all of which should be included in a text and a set of ....

....can influence textual decisions. This is not always the case. For instance, in our ILEX domain [Mellish et al. 98] the system s goal is something very general like. say interesting things about item X subject to length and coherence constraints . The third approach, most obviously exemplified by [Marcu 97] is to Use some for m of explicit. search through possible trees, guided by heuristics about tree quality. Marcu first of all attempts to find the best ordering of the facts. For every relation that could be indicated, constraints are generated saying what the order of the two facts involved ....

Marcu, 'D.,."From Local to Global Coherence: A Bottom-up Approach to Text 'Planning", ' Proceedings of AAAI-97, American Association for Artificial Intelligence, 1997, pp629-635.

....artifact, and has a wide coverage grammar; this would allow future stop like projects to use deep techniques for realisation. 3.3 Rhetorical Coherence Another crucial linguistic constraint is that texts should be rhetorically coherent. A variety of deep document structuring algorithms (such as (Marcu, 1997)) have been developed which automatically create rhetorically coherent texts. These algorithms are based on formal definitions of discourse relations such as Contrast and Elaboration. We briefly considered incorporating such an algorithm into stop, but decided against this because we felt that ....

Marcu, Daniel. 1997. From local to global coherence: A bottom-up approach to text planning. In Proceedings of Fourteenth National Conference on Artificial IntelligenceAAAI-1997), pages 629--635.

....by the goals and their decomposition. That is, a generator needs strategies for decomposing the achievement of complex goals into sequences of utterances, rather than ways of combining sequences of utterances into more complex structures. Generation is top down , rather than bottom up [Marcu 97] Our belief is that there is an important class of NLG problems for which these basic assumptions are not helpful. These problems all involve situations where semi fixed explanation strategies are less useful than the ability to exploit opportunities. WordNet gives the following definition of ....

....that includes all the relations linking the selected fact nodes. 2. Produce from this an optimal selection of relations, so as to give rise to an RST tree including all the selected facts. Once the complete subgraph has been obtained, the text planning problem is exactly that described by [Marcu 97] The idea of combining a set of facts together into an optimal text is also compatible with [Hovy 90] and the earlier work of [Mann and Moore 81] Again this involves exploiting opportunities. For instance, in order to avoid an awkward focus shift at some point, one might attempt to include a ....

Marcu, D., "From local to global coherence: a bottom-up approach to text planning", in Proceedings of AAAI-97, American Association for Artificial Intelligence, 1997.

....Structure Theory relations (Mann and Thompson 1988) whose Nucleus and Satellite ordering requirements are implemented as constraints; the module applies a constraint satisfaction algorithm to find all satisfactory ordering(s) of the input expressions. Of these, one is selected at random. See Marcu (1997) for details. In later work, an additional module will be built to determine the linguistic phrasing of the discourse relation. The aggregation module eliminates redundancy in TSL expressions by grouping together entities that are arguments of the same rhetorical relation, verbal process, etc. ....

Marcu, Daniel (1997). "From local to global coherence: A bottom-up approach to text planning." Submitted for publication.

No context found.

Daniel Marcu. 1997. From local to global coherence: A bottom-up approach to text planning. In Proceedings of Fourteenth National Conference on Artificial Intelligence (AAAI-1997), pages 450--456.

No context found.

, AAAI, Providence, RI

No context found.

, AAAI, Providence, RI

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