Capturing the interaction between aggregation and text planning in two generation systems

Abstract

In natural language generation, different generation tasks often interact with each other in a complex way. We think that how to resolve the complex interactions inside and between tasks is more important to the generation of a coherent text than how to model each individual factor. This paper focuses on the interaction between aggregation and text planning, and tries to explore what preferences exist among the features considered by the two tasks. The preferences are implemented in two generation systems, namely ILEX-TS and a text planner using a Genetic Algorithm. The evaluation emphasises the second implementation and shows that capturing these preferences properly can lead to coherent text.

Aggregation via set partitioning for natural language generation

“…Our model is inspired by research on text aggregation in the natural language generation community (Cheng and Mellish, 2000;Shaw, 1998). A common theme across different approaches is the notion of similarity -content elements described in the same sentence should be related to each other in some meaningful way to achieve conciseness and coherence.…”

“…The preference function is learned from a corpus of candidate aggregations marked with human ratings. Another approach is put forward by Cheng and Mellish (2000) who use a genetic algorithm in combination with a hand-crafted preference function to opportunistically find a text that satisfies aggregation and planning constraints.…”

“…The task captures a mechanism for merging together two or more linguistic structures into a single sentence. Aggregated texts tend to be more concise, coherent, and more readable overall (Dalianis, 1999;Cheng and Mellish, 2000). Compare, for example, sentence (2) in Table 1 and its nonaggregated counterpart in sentences (1a)-(1d).…”

Generating Natural Language Descriptions from OWL Ontologies: the NaturalOWL System

“…The aggregation rules apply almost exclusively to sentences that are adjacent in the ordering produced by the text planner; the only exception are aggregation rules that involve sentences about cardinality restrictions. Hence, depending on the ordering of the text planner there may be more or fewer aggregation opportunities; see the work of Cheng and Mellish (2000) for related discussion. Also, the aggregation rules of Naturalowl operate on sentences of the same topical section, because aggregating topically unrelated sentences often sounds unnatural.…”

XExplainer: a tool for generating descriptive text from database

“…For sentence ordering, Mellish [7] attempted stochastic search and it was used in text structuring by Cheng [8] in the form of genetic algorithm. In our approach, we use simulated annealing (SA) to find best sequence of information and, propose four methodologies for energy function in SA.…”