A Context-aware Natural Language Generator for Dialogue Systems

By Ondrej Dusek, Filip Jurcícek. 2016

78 citations recorded by the source corpus.

We present a novel natural language generation system for spoken dialogue systems capable of entraining (adapting) to users' way of speaking, providing contextually appropriate responses. The generator is based on recurrent neural networks and the sequence-to-sequence approach. It is fully trainable from data which include preceding context along with responses to be generated. We show that the context-aware generator yields significant improvements over the baseline in both automatic metrics and a human pairwise preference test.

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

Structure-to-Text Generation with Self-Training, Acceptability Classifiers and Context-Conditioning for the GEM Shared Task (2021, methodology): “Duˇsek and Jurˇc´ıˇcek (2016) investigated ways of adapting to the user’s way of speaking with neural models using the previous user turn; more recently, Kale and Rastogi (2020) demonstrated with the SGD dataset that including multiple turns of context in the input to a pretrained model yields…”
Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge (2019, background): “, 2015a) and (Dušek and Jurčı́ček, 2016), have relied on crowdsourcing for collecting training data.”
Findings of the E2E NLG Challenge (2018, methodology): “…costly semantic alignment between meaning representations (MRs) and the corresponding natural language reference texts, e.g. (Duˇsek and Jurˇc´ıˇcek, 2015; Wen et al., 2015b; Mei et al., 2016; Wen et al., 2016; Sharma et al., 2016; Duˇsek and Jurˇc´ıˇcek, 2016a; Lampouras and Vlachos, 2016).”
A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, background): “It was then extended with the preceding user utterance and responses [13].”
Recent advances in deep learning based dialogue systems: a systematic survey (2021, methodology): “Likewise, Dušek and Jurčíček (2016a) concatenated the preceding user utterance with the dialogue action vector and fed it into an LSTM model. Dušek and Jurčíček (2016b) put a syntax constraint upon their neural response generator.”
Few-Shot Natural Language Generation by Rewriting Templates (2020, background): “The utterances in the dialogue context are also important to generate good responses because they can help model conversational phenomena such as entrainment (lexical and syntactic alignment of responses), and can help it avoid repetition (Dušek and Jurcicek, 2016a).”
Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention (2019, background): “Instead of simply feeding such vectorized representation to neural networks like Semantically Controlled LSTM (SCLSTM) (Wen et al., 2015, 2016b; Dusek and Jurcı́cek, 2016), we propose to incorporate this structural prior of dialog act space as an inductive prior for designing the neural architecture”