Pragmatically Informative Text Generation

We improve the informativeness of models for conditional text generation using techniques from computational pragmatics. These techniques formulate language production as a game between speakers and listeners, in which a speaker should generate output text that a listener can use to correctly identify the original input that the text describes. While such approaches are widely used in cognitive science and grounded language learning, they have received less attention for more standard language generation tasks. We consider two pragmatic modeling methods for text generation: one where pragmatics is imposed by information preservation, and another where pragmatics is imposed by explicit modeling of distractors. We find that these methods improve the performance of strong existing systems for abstractive summarization and generation from structured meaning representations.

PDF Abstract NAACL 2019 PDF NAACL 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Data-to-Text Generation E2E NLG Challenge S_1^R BLEU 68.60 # 1
NIST 8.73 # 1
METEOR 45.25 # 3
ROUGE-L 70.82 # 2
CIDEr 2.37 # 1


No methods listed for this paper. Add relevant methods here