Natural Language Generation as Incremental Planning Under Uncertainty: Adaptive Information Presentation for Statistical Dialogue Systems

By Verena Rieser, Oliver Lemon, Simon Keizer. 2014

40 citations recorded by the source corpus.

We present and evaluate a novel approach to natural language generation (NLG) in statistical spoken dialogue systems (SDS) using a data-driven statistical optimization framework for incremental information presentation (IP), where there is a trade-off to be solved between presenting “enough" information to the user while keeping the utterances short and understandable. The trained IP model is adaptive to variation from the current generation context (e.g. a user and a non-deterministic sentence planner), and it incrementally adapts the IP policy at the turn level. Reinforcement learning is used to automatically optimize the IP policy with respect to a data-driven objective function. In a case study on presenting restaurant information, we show that an optimized IP strategy trained on Wizard-of-Oz data outperforms a baseline mimicking the wizard behavior in terms of total reward gained. The policy is then also tested with real users, and improves on a conventional hand-coded IP strategy used in a deployed SDS in terms of overall task success. The evaluation found that the trained IP strategy significantly improves dialogue task completion for real users, with up to a 8.2% increase in task success. This methodology also provides new insights into the nature of the IP problem, which has previously been treated as a module following dialogue management with no access to lower-level context features (e.g. from a surface realizer and/or speech synthesizer).

Subfields: Artificial Intelligence, Natural Language Processing, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Model Architectures

Citations in the corpus

The E2E Dataset: New Challenges For End-to-End Generation (2017, methodology): “…work, we hope to collect data with further increased complexity, e.g. asking the user to compare, summarise, or recommend restaurants, in order to replicate previous rule-based and statistical approaches, e.g. (Walker et al., 2004; Stent et al., 2004; Demberg and Moore, 2006; Rieser et al., 2014).”
Why We Need New Evaluation Metrics for NLG (2017, background): “…quality within the dialogue context, e.g. (Dušek and Jurčı́ček, 2016); extrinsic evaluation metrics, such as NLG’s contribution to task success, e.g. (Rieser et al., 2014; Gkatzia et al., 2016; Hastie et al., 2016); building discriminative models, e.g. (Hodosh and Hockenmaier, 2016), (Kannan…”
Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge (2019, neutral): “(Rieser et al., 2014; Gkatzia et al., 2016).”
RankME: Reliable Human Ratings for Natural Language Generation (2018, methodology): “In addition, we aim to investigate additional NLG evaluation methods, such as extrinsic task contributions, e.g. (Rieser et al., 2014; Gkatzia et al., 2016).”
Crowd-sourcing NLG Data: Pictures Elicit Better Data. (2016, methodology): “So far, crowdsourcing is mainly used for evaluation in the NLG community, e.g. (Rieser et al., 2014; Dethlefs et al., 2012).”