A Domain-Specific Statistical Surface Realizer
نویسنده
چکیده
We present a search-based approach to automatic surface realization given a corpus of domain sentences. Using heuristic search based on a statistical language model and a structure we introduce called an inheritance table we overgenerate a set of complete syntactic-semantic trees that are consistent with the given semantic structure and have high likelihood relative to the language model. These trees are then lexicalized, linearized, scored, and ranked. This model is being developed to generate real-time navigation instructions.
منابع مشابه
Evaluating Coverage for Large Symbolic NLG Grammars
After many successes, statistical approaches that have been popular in the parsing community are now making headway into Natural Language Generation (NLG). These systems are aimed mainly at surface realization, and promise the same advantages that make statistics valuable for parsing: robustness, wide coverage and domain independence. A recent experiment aimed to empirically verify the linguist...
متن کاملTemplate-Based Surface Realization for Referring Expression Generation
This paper describes the template-based surface realizer which was used by the GRAPH team in the TUNA-REG Challenge 2009 in combination with an attribute selection algorithm used in previous editions of the TUNA challenges. The new template-based realizer is compared to the realizer used by the GRAPH team in the REG 2008 Challenge and to an improved version of the 2008 realizer. Results show no...
متن کاملPorting to an Italian Surface Realizer: A Case Study
Multilingual generation is becoming an increasingly important aspect of implemented systems that showcase the abilities of generation systems. Most such systems require multiple grammars, one for each language which must be deployed. Yet little is known about the development costs for additional languages which are developed not from scratch, but by adapting existing resources. We ported a stan...
متن کاملRhetorical Goals Surface Generator Functional Realizer Functional Description
In recent years, natural language generation research has begun to mature rapidly. It has witnessed both the appearance of sophisticated oo-the-shelf surface realizations systems and the development in the knowledge representation community of knowledge bases in a variety of domains. However, knowledge bases typically employ a logic formalism while the state-of-the-art surface realizer, Fuf, em...
متن کاملEfficient algorithm for Context Sensitive Aggregation in Natural Language generation
Aggregation is a sub-task of Natural Language Generation (NLG) that improves the conciseness and readability of the text outputted by NLG systems. Till date, approaches towards the aggregation task have been predominantly manual (manual analysis of domain specific corpus and development of rules). In this paper, a new algorithm for aggregation in NLG is proposed, that learns context sensitive a...
متن کامل