Pragmatically Informative Text Generation

Shen, Sheng; Fried, Daniel; Andreas, Jacob; Klein, Dan

doi:10.18653/v1/n19-1410

Cited by 46 publications

(44 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Baselines For generation on E2E, we compare externally against 4 systems: E2E-BENCHMARK (Dušek and Jurčíček, 2016) is an encoder-decoder network followed by a reranker used as the shared task benchmark; NTEMP, a controllable neuralized hidden semi-Markov model; NTEMP+AR, the product of experts of both a NTemp model and an autoregressive LSTM network (Wiseman et al, 2018); SHEN19 (Shen et al, 2019) is an pragmatically informed model, which is the current state-ofthe-art system on E2E dataset.…”

Section: Methodsmentioning

confidence: 99%

Posterior Control of Blackbox Generation

Rushton

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Text generation often requires high-precision output that obeys task-specific rules. This fine-grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we consider augmenting neural generation models with discrete control states learned through a structured latent-variable approach. Under this formulation, task-specific knowledge can be encoded through a range of rich, posterior constraints that are effectively trained into the model. This approach allows users to ground internal model decisions based on prior knowledge, without sacrificing the representational power of neural generative models. Experiments consider applications of this approach for text generation. We find that this method improves over standard benchmarks, while also providing fine-grained control.

show abstract

Section: Methodsmentioning

confidence: 99%

Posterior Control of Blackbox Generation

Rushton

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…numerical comparisons) are needed, augmenting the encoded input by pre-calculating these inferrable facts. Shen et al (2019) used techniques from computational pragmatics and modeled the generation task as a game between speakers and listeners. Despite following the generation-reranking paradigm explored previously in the data-to-text domain (Agarwal et al, 2018;Moryossef et al, 2019a;Dušek et al, 2019), and in other domains including machine translation (Shen et al, 2004), dialogue generation (Wen et al, 2015), and ASR (Morbini et al, 2012), our work has several distinctive aspects compared to previous works.…”

Section: Related Workmentioning

confidence: 99%

Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity

Harkous¹,

Groves²,

Saffari³

2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

End-to-end neural data-to-text (D2T) generation has recently emerged as an alternative to pipeline-based architectures. However, it has faced challenges generalizing to new domains and generating semantically consistent text. In this work, we present DATATUNER, a neural, end-to-end data-to-text generation system that makes minimal assumptions about the data representation and target domain. We take a two-stage generation-reranking approach, combining a fine-tuned language model with a semantic fidelity classifier. Each component is learnt end-toend without needing dataset-specific heuristics, entity delexicalization, or post-processing. We show that DATATUNER achieves state of the art results on automated metrics across four major D2T datasets (LDC2017T10, WebNLG, ViGGO, and Cleaned E2E), with fluency assessed by human annotators as nearing or exceeding the human-written reference texts. Our generated text has better semantic fidelity than the state of the art on these datasets. We further demonstrate that our model-based semantic fidelity scorer is a better assessment tool compared to traditional heuristic-based measures of semantic accuracy.

show abstract

“…Pragmatics. Our approach belongs to the general family of Bayesian Rational Speech Acts (Andreas and Klein, 2016), image captioning (Mao et al, 2016;Vedantam et al, 2017;Cohn-Gordon et al, 2018), instruction following (Fried et al, 2017), navigating (Fried et al, 2018), translation (Cohn-Gordon and Goodman, 2019), summarization (Shen et al, 2019) and referring expression generation (Zarrieß and Schlangen, 2019). However, its application to the dialogue domain remains understudied.…”

Section: Related Workmentioning

confidence: 99%

Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness

Kim

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

We explore the task of improving persona consistency of dialogue agents. Recent models tackling consistency often train with additional Natural Language Inference (NLI) labels or attach trained extra modules to the generative agent for maintaining consistency. However, such additional labels and training can be demanding. Also, we find even the bestperforming persona-based agents are insensitive to contradictory words. Inspired by social cognition and pragmatics, we endow existing dialogue agents with public self-consciousness on the fly through an imaginary listener. Our approach, based on the Rational Speech Acts framework (Frank and Goodman, 2012), can enforce dialogue agents to refrain from uttering contradiction. We further extend the framework by learning the distractor selection, which has been usually done manually or randomly. Results on Dialogue NLI (Welleck et al., 2019) and PersonaChat (Zhang et al., 2018) dataset show that our approach reduces contradiction and improves consistency of existing dialogue models. Moreover, we show that it can be generalized to improve contextconsistency beyond persona in dialogues.

show abstract

Pragmatically Informative Text Generation

Cited by 46 publications

References 31 publications

Posterior Control of Blackbox Generation

Posterior Control of Blackbox Generation

Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity

Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness

Contact Info

Product

Resources

About