Inducing clause-combining operations for natural language generation
نویسندگان
چکیده
Recent work in end-to-end generation has reduced the need for knowledgeengineering, but is insufficiently sensitive to discourse structure. We present a method for inducing clause-combining rules for use in a traditional natural language generation architecture to address this gap. Our algorithm is able to learn all of the clause-combining rules present in the SPaRKy restaurant corpus from exemplary input-output pairs and is currently being extended to include the induction of both lexicalization and referring expression rules. We also describe initial work applying this technique in a new domain.
منابع مشابه
Inducing Clause-Combining Rules: A Case Study with the SPaRKy Restaurant Corpus
We describe an algorithm for inducing clause-combining rules for use in a traditional natural language generation architecture. An experiment pairing lexicalized text plans from the SPaRKy Restaurant Corpus with logical forms obtained by parsing the corresponding sentences demonstrates that the approach is able to learn clause-combining operations which have essentially the same coverage as tho...
متن کاملDeterministic natural language generation from meaning representations for machine translation
This paper describes a deterministic method for generating natural language suited to being part of a machine translation system with meaning representations as the level for language transfer. Starting from Davidsonian/Penman meaning representations, syntactic trees are built following the Penn Parsed Corpus of Modern British English, from which the yield (i.e., the words) can be taken. The no...
متن کاملConstraints on the Generation of Adjunct Clauses
This paper presents an analysis of a family of particular English constructions, all of which roughly express "purpose". In particular we look at the purpose clause, rationale .clause, and infinitival relative clause. We (1) show that couching the analysis in a computational framework, specifically generation, provides a more satisfying account than analyses based strictly on descriptive lingui...
متن کاملCombining Hierarchical Reinforcement Learning and Bayesian Networks for Natural Language Generation in Situated Dialogue
Language generators in situated domains face a number of content selection, utterance planning and surface realisation decisions, which can be strictly interdependent. We therefore propose to optimise these processes in a joint fashion using Hierarchical Reinforcement Learning. To this end, we induce a reward function for content selection and utterance planning from data using the PARADISE fra...
متن کاملChinese Couplet Generation with Neural Network Structures
Part of the unique cultural heritage of China is the Chinese couplet. Given a sentence (namely an antecedent clause), people reply with another sentence (namely a subsequent clause) equal in length. Moreover, a special phenomenon is that corresponding characters from the same position in the two clauses match each other by following certain constraints on semantic and/or syntactic relatedness. ...
متن کامل