Trainable Sentence Planning for Complex Information Presentations in Spoken Dialog Systems

By Amanda Stent, Rashmi Prasad, Marilyn A. Walker. 2004

170 citations recorded by the source corpus.

A challenging problem for spoken dialog systems is the design of utterance generation modules that are fast, flexible and general, yet produce high quality output in particular domains. A promising approach is trainable generation, which uses general-purpose linguistic knowledge automatically adapted to the application domain. This paper presents a trainable sentence planner for the MATCH dialog system. We show that trainable sentence planning can produce output comparable to that of MATCH's template-based generator even for quite complex information presentations.

Subfields: Artificial Intelligence, Natural Language Processing

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

Citations in the corpus

The E2E Dataset: New Challenges For End-to-End Generation (2017, background): “…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).”
Neural Approaches to Conversational AI (2018, neutral): “s or rules, and hand-craft heuristics to select a proper candidate to generate sentences. Even though machine learning can be used to train certain parts of these systems (Langkilde and Knight, 1998; Stent et al., 2004; Walker et al., 2007), the cost to write and maintain templates and rules leads t”
Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems (2015, methodology): “Sentence planning maps input semantic symbols into an intermediary form representing the utterance, e.g. a tree-like or template structure, then surface realisation converts the intermediate structure into the ﬁnal text (Walker et al., 2002; Stent et al., 2004).”
A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version (2015, background): “…2014c; Kim et al., 2015), natural language generation (Langkilde and Knight, 1998; Oh and Rudnicky, 2000; Walker et al., 2002; Ratnaparkhi, 2002; Stent et al., 2004; Rieser and Lemon, 2010; Mairesse et al., 2010; Mairesse and Young, 2014; Wen et al., 2015; Sharma et al., 2016), and dialogue…”
Multi-domain Neural Network Language Generation for Spoken Dialogue Systems (2016, background): “…al., 2015b) is a specialised extension of the LSTM network (Hochreiter and Schmidhuber, 1997) for language generation which has previously been shown capable of learning generation decisions from paired DA-utterances end-to-end without a modular pipeline (Walker et al., 2002; Stent et al., 2004).”
Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge (2019, background): “The majority of our data, however, contains more complex, varied syntactic structures, including phenomena explicitly modelled by early statistical approaches to NLG (Stent, Prasad, and Walker 2004; Walker et al. 2004).”
Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings (2016, methodology): “nd depends on system architecture or particular generation domain. Works using the pipeline approach in SDS tend to focus on sentence planning, improving a handcrafted generator (Walker et al., 2001; Stent et al., 2004; Paiva and Evans, 2005) or using perceptron-guided A* search (Duˇsek and Jurcˇ´ıc”
Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking (2015, background): “Sentence planning maps input semantic symbols into an intermediary tree-like or template structure representing the utterance, then surface realisation converts the intermediate structure into the final text (Walker et al., 2002; Stent et al., 2004; Dethlefs et al., 2013).”
What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment (2015, background): “Walker et al. (2001) and Stent et al. (2004) design trainable sentence planners to generate sentences (and their combinations) for context planning and dialog, relying upon various linguistics features.”
Natural Language Generation as Planning Under Uncertainty for Spoken Dialogue Systems (2009, methodology): “In current work we replace the realizer model with an implemented generator that replicates the variation found in the SPaRKy realizer (Stent et al., 2004).”
Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data (2016, methodology): “Previous papers have explored alternative approaches such as corpus-based n-gram models Oh and Rud-nicky, 2002, tree-based models Stent, Prasad, and Walker, 2004, and Reinforcement Learning models Rieser and Lemon, 2010.”
Training a Natural Language Generator From Unaligned Data (2015, methodology): “Previous trainable methods in sentence planning use in principle two techniques: First, in the overgeneration and ranking approach (Walker et al., 2001; Stent et al., 2004), many sentence plans are generated using a rule-based planner and then the best one is selected by a statistical ranker.”
Individual and Domain Adaptation in Sentence Planning for Dialogue (2007, methodology): “Table 1 shows that a combination of the three feature sets performs significantly better for recommend and compare-3 than the tree features from our earlier work (Walker, Rambow, & Rogati, 2002; Stent, Prasad, & Walker, 2004; Mairesse & Walker, 2005).”
End-to-End Content and Plan Selection for Data-to-Text Generation (2018, background): “Then, the surface realization transforms the intermediary structure into text (Stent et al., 2004).”
Order-Planning Neural Text Generation From Structured Data (2017, background): “Traditionally, text generation can be divided into several steps (Stent, Prassad, and Walker 2004): content planning deﬁnes what information should be conveyed in the generated sentence; (2) sentence planning determines what to generate in each sentence; and (3) surface realization actually…”