… aggregation, we refer to the work of Horacek, (1992). Like Horacek, we believe that aggregation
… In this paper, we concentrate on the third question: how to perform aggregation to avoid …

… We develop further the concept of aggregation and discuss it in … planning phase of natural
language generation systems. … to natural language, specifically the problem of aggregation …

… what it suggests about natural language generation. The focus here will be on the sentence
planning level, and the requirements at this level which the aggregation issue highlights. …

… data-driven method for aggregation in the context of natural language generation. A key
aspect of our approach is the use of global inference for finding aggregations that are maximally …

… 3 Recurrent Neural Language Generator The recurrent language generator proposed in
this paper is based on a neural net language generator (Wen et al., 2016b) which consists of …

… are combined in current aggregated search applications is … marry techniques from natural
language generation, such as … between aggregated search and natural language generation …

… Sentence aggregation Sentence aggregation is the process of grouping messages together
into sentences. In our current example, sentence aggregation could combine the IDENTITY …

… In this paper, a new algorithm for aggregation in NLG is proposed, that learns context …
aggregation algorithm performs better than the deterministic hand crafted aggregation rules. …

… the various treatments of aggregation have di ered on or left vague is at exactly what levels
of language generation aggregation may take place. . . . In fact, aggregation-like phenomena …

… as a result of aggregation at the message level, the system can start converting it into natural
language. In our example (Figure 1c), the outcome of aggregation and lexicalisation are …