Source PaperYearLineSentence
W98-1415 1998 226
Newer systems, such as [Shaw, 1995, Wanner and Hovy, 1996, Huang and Fiedler, 1997]: use a sentence planner to make decisions at clause level between the strategic and tactical component (self citation)
W98-1415 1998 233
Because sentences with coordination constructions can express a lot of information with few words, many text generation systems have implemented the generation of coordination expres- sions with various ?complexities [Dale, 1992, Dalianis and Hovy, 1993, Huang and Fiedler, 1997, Shaw, 1995, Callaway and Lester, 1997] (self citation)
W00-0405 2000 36
Most of the work in sentence xtraction applied statistical techniques (frequency analysis, variance anal- ysis, etc.) to linguistic units such as tokens, names, anaphora, etc. More recently, other approaches have investigated the utility of discourse structure (Marcu, 1997), the combination of information extraction and language generation (Klavans and Shaw, 1995; McKe- own et al, 1995), and using machine learning to find patterns in text (Teufel and Moens, 1997; Barzilay and Elhadad, 1997; Strzalkowski et al, 1998)
W05-1613 2005 89
In NLG, the process of build ing such complex sentences is known as ?aggregation?[Shaw, 1995]
W05-1602 2005 53
For micro planning, we have implemented the algorithm for referenceplanning described in [Reiter and Dale, 1992] and the ag gregation algorithm described in [Shaw, 1995]
W05-1602 2005 169
Aggregation of utterances which share certain features using the aggregation algorithm described in [Shaw, 1995]