Stochastic Language Generation for Spoken Dialogue Systems

By Alice H. Oh, Alexander I. Rudnicky. 2000

188 citations recorded by the source corpus.

The two current approaches to language generation, template-based and rule-based (linguistic) NLG, have limitations when applied to spoken dialogue systems, in part because they were developed for text generation. In this paper, we propose a new corpus-based approach to natural language generation, specifically designed for spoken dialogue systems.

Subfields: Artificial Intelligence, Natural Language Processing, Generative Models

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 Generative Models

Citations in the corpus

Neural Generation for Czech: Data and Baselines (2019, methodology): “A prime example is the delexicalization technique used by most current generators (e.g., Oh and Rudnicky, 2000; Mairesse et al., 2010; Wen et al., 2015a,b; Juraska et al., 2018): It is generally assumed that attribute (slot) values from the input meaning representation (MR) can be replaced by…”
A Knowledge-Grounded Neural Conversation Model (2017, methodology): “In terms of BLEU scores, MT ASK -RF improvements is not signiﬁcant, but it generates the highest chine Translation (Graham et al., 2015), as B LEU and related metrics were originally designed as corpus-level metrics.”
Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems (2015, methodology): “A pi-oneer in this direction is the class-based n-gram language model (LM) approach proposed by Oh and Rudnicky (2000).”
Neural Text Generation from Structured Data with Application to the Biography Domain (2016, background): “It also builds upon older work such as class-based language models for dialog systems (Oh and Rudnicky, 2000).”
A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version (2015, background): “…Henderson et al., 2013; Williams et al., 2013; Henderson et al., 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,…”
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling (2018, background): “Natural Language Generation from a structured meaning representation (Oh and Rudnicky, 2000; Bohus and Rudnicky, 2005) has been a very popular research topic in the community, and the lack of data has been a long standing block for the field to adopt more machine learning methods.”
Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking (2015, methodology): “In order to reduce the amount of handcrafting and make the approach more useful in SDS, Oh and Rudnicky (2000) replaced the handcrafted generator with a set of word-based n-gram LM-based generators, one for each dialogue type and then reranked the generator outputs using a set of rules to produce…”
Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation (2017, background): “In the past, Oh and Rudnicky (2000) proposed a corpus-based approach for Natural Language Generation (NLG) for task-oriented dialogue systems.”
Frames: a corpus for adding memory to goal-oriented dialogue systems (2017, background): “To imitate this behaviour, a natural language generator (Oh and Rudnicky, 2000; Wen et al., 2015; Sharma et al., 2017) would need to reason over the database and decide how to tailor the results to the user and present them in a concise but sufficient way.”
End-to-End Content and Plan Selection for Data-to-Text Generation (2018, methodology): “Early data-driven approach used phrase-based language models for generation (Oh and Rudnicky, 2000; Mairesse and Young, 2014), or aimed to predict the best fitting cluster of semantically similar templates (Kondadadi et al.”
DeepTingle (2017, unknown): “Some effort has been made towards generating the template based on a corpus, using statistical methods (Mairesse et al. 2010; Mairesse and Young 2014; Oh and Rudnicky 2000), but these still require a large amount of time and expertise.”
Incorporating Unstructured Textual Knowledge Sources into Neural Dialogue Systems (2015, methodology): “In practice, these models can be used as re-ranking mechanisms for stochastic generative models [11, 18, 19], or they can be used as a generative model themselves by extending the set of responses to encompass the training set.”
Broad Coverage Multilingual Deep Sentence Generation with a Stochastic Multi-Level Realizer (2010, background): “…(or stochastic) sentence realization , i.e., that part of NLG which deals with mapping of a formal (more or less abstract) sentence plan onto a chain of in-ﬂected words; cf., among others, (Langkilde and Knight, 1998; Oh and Rudnicky, 2000; Bangalore and Rambow, 2000; Wan et al., 2009).”
Collaborative Multi-Agent Dialogue Model Training Via Reinforcement Learning (2019, background): “Machine learning for conversational agents has seen great advances (e.g. Tur and Mori, 2011; Gao et al., 2019; Singh et al., 1999; Young et al., 2013; Oh and Rudnicky, 2000; Zen et al., 2009; Reiter and Dale, 2000; Rieser and Lemon, 2010), especially when adopting deep learning models (Deng”
Plan-then-Generate: Controlled Data-to-Text Generation via Planning (2021, background): “Traditional systems are primarily built on template-based algorithms (Oh and Rudnicky, 2000; Stent et al., 2004; Kondadadi et al., 2013).”
Natural Language Generation for Spoken Dialogue System using RNN Encoder-Decoder Networks (2017, background): “, 2011), corpus-based n-gram models (Oh and Rudnicky, 2000), and a trainable generator (Stent et al.”