Scaling a natural language generation system

Abstract

A key goal in natural language generation (NLG) is to enable fast generation even with large vocabularies, grammars and worlds. In this work, we build upon a recently proposed NLG system, Sentence Tree Realization with UCT (STRUCT). We describe four enhancements to this system: (i) pruning the grammar based on the world and the communicative goal, (ii) intelligently caching and pruning the combinatorial space of semantic bindings, (iii) reusing the lookahead search tree at different search depths, and (iv) learning and using a search control heuristic. We evaluate the resulting system on three datasets of increasing size and complexity, the largest of which has a vocabulary of about 10K words, a grammar of about 32K lexicalized trees and a world with about 1 1 K entities and 23K relations between them. Our results show that the system has a median generation time of 8.5s and finds the best sentence on average within 25s. These results are based on a sequential, interpreted implementation and are significantly better than the state of the art for planningbased NLG systems.