Chart generation

Kay, Martin

doi:10.3115/981863.981890

Cited by 74 publications

(87 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Next to their use in parsing, they have also been applied to surface realization (Kay, 1996;Carroll et al, 1999;Kaplan and Wedekind, 2000). To our knowledge, ours is the first work using charts for REG.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Generating effective referring expressions using charts

Engonopoulos

Koller

2014

Proceedings of the INLG and SIGDIAL 2014 Joint Session

View full text Add to dashboard Cite

We present a novel approach for generating effective referring expressions (REs). We define a synchronous grammar formalism that relates surface strings with the sets of objects they describe through an abstract syntactic structure. The grammars may choose to require or not that REs are distinguishing. We then show how to compute a chart that represents, in finite space, the complete (possibly infinite) set of valid REs for a target object. Finally, we propose a probability model that predicts how the listener will understand the RE, and show how to compute the most effective RE according to this model from the chart.

show abstract

Section: Related Workmentioning

confidence: 99%

“…A semantic index indicates the individual in U to which a given constituent is meant to refer, see e.g. (Kay, 1996;Stone et al, 2003). Note that SIGs can be seen as specific Interpreted Regular Tree Grammars (Koller and Kuhlmann, 2011) with a set and a string interpretation.…”

Section: Semantically Interpreted Grammarsmentioning

confidence: 99%

Generating effective referring expressions using charts

Engonopoulos

Koller

2014

Proceedings of the INLG and SIGDIAL 2014 Joint Session

View full text Add to dashboard Cite

show abstract

“…(Wang, 1980) uses hand-written rules to generate sentences from an extended predicate logic formalism; (Shieber et al, 1990) introduces a head-driven algorithm for generating from logical forms; (Kay, 1996) defines a chart based algorithm which enhances efficiency by minimising the number of semantically incomplete phrases being built; and (Shemtov, 1996) presents an extension of the chart based generation algorithm presented in (Kay, 1996) which supports the generation of multiple paraphrases from underspecified semantic input. In all these approaches, grammar and lexicon are developed manually and it is assumed that the lexicon associates semantic sub-formulae with natural language expressions.…”

Section: Related Workmentioning

confidence: 99%

Surface Realisation from Knowledge-Bases

Gyawali¹,

Gardent²

2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

We present a simple, data-driven approach to generation from knowledge bases (KB). A key feature of this approach is that grammar induction is driven by the extended domain of locality principle of TAG (Tree Adjoining Grammar); and that it takes into account both syntactic and semantic information. The resulting extracted TAG includes a unification based semantics and can be used by an existing surface realiser to generate sentences from KB data. Experimental evaluation on the KBGen data shows that our model outperforms a data-driven generate-and-rank approach based on an automatically induced probabilistic grammar; and is comparable with a handcrafted symbolic approach.

show abstract

“…The PCFG-based generation algorithms are implemented in terms of a chart generator (Kay, 1996). In the generation algorithm, each (sub-)f-structure indexes a (sub-)chart.…”

Section: Chart Generation Algorithmmentioning

confidence: 99%

Accurate and robust LFG-based generation for Chinese

Guo

Wang²,

Genabith³

2008

Proceedings of the Fifth International Natural Language Generation Conference on - INLG '08

View full text Add to dashboard Cite

We describe three PCFG-based models for Chinese sentence realisation from LexicalFunctional Grammar (LFG) f-structures. Both the lexicalised model and the history-based model improve on the accuracy of a simple wide-coverage PCFG model by adding lexical and contextual information to weaken inappropriate independence assumptions implicit in the PCFG models. In addition, we provide techniques for lexical smoothing and rule smoothing to increase the generation coverage. Trained on 15,663 automatically LFG fstructure annotated sentences of the Penn Chinese treebank and tested on 500 sentences randomly selected from the treebank test set, the lexicalised model achieves a BLEU score of 0.7265 at 100% coverage, while the historybased model achieves a BLEU score of 0.7245 also at 100% coverage.

show abstract

Chart generation

Abstract: Charts constitute a natural uniform architecture for parsing and generation provided string position is replaced by a notion more appropriate to logical forms and that measures are taken to curtail generation paths containing semantically incomplete phrases.

Cited by 74 publications

References 4 publications

Generating effective referring expressions using charts

Generating effective referring expressions using charts

Surface Realisation from Knowledge-Bases

Accurate and robust LFG-based generation for Chinese

Contact Info

Product

Resources

About