Natural Language Generation for Spoken Dialogue System using RNN Encoder-Decoder Networks

By Van-Khanh Tran, Le-Minh Nguyen. 2017

41 citations recorded by the source corpus.

Natural language generation (NLG) is a critical component in a spoken dialogue system. This paper presents a Recurrent Neural Network based Encoder-Decoder architecture, in which an LSTM-based decoder is introduced to select, aggregate semantic elements produced by an attention mechanism over the input elements, and to produce the required utterances. The proposed generator can be jointly trained both sentence planning and surface realization to produce natural language sentences. The proposed model was extensively evaluated on four different NLG datasets. The experimental results showed that the proposed generators not only consistently outperform the previous methods across all the NLG domains but also show an ability to generalize from a new, unseen domain and learn from multi-domain datasets.

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

Survey of Hallucination in Natural Language Generation (2022, methodology): “Following previous works such as [38, 203], and [185], Li et al.”
Continual Learning for Natural Language Generation in Task-oriented Dialog Systems (2020, background): “, 2015b), RALSTM (Tran and Nguyen, 2017), SCVAE (Tseng et al.”
Few-shot Natural Language Generation for Task-Oriented Dialog (2020, background): “To ensure diversity, we consider three domains from MultiWOZ: Attraction , Taxi , and Train .”
Slot-consistent NLG for Task-oriented Dialogue Systems with Iterative Rectification Network (2020, methodology): “Each dataset is evaluated with ﬁve strong baseline methods, including HLSTM (Wen et al., 2015a), SC-LSTM (Wen et al., 2015b), TGen (Duˇsek and Jurˇc´ıˇcek, 2016), ARoA (Tran and Nguyen, 2017b) and RALSTM (Tran and Nguyen, 2017a).”
Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems (2019, methodology): “Recently, various neural approaches [Wen et al. , 2015c; Tran and Nguyen, 2017; Tseng et al. , 2018] have been proposed to generate accurate, natural and diverse utterances.”
Adversarial Domain Adaptation for Variational Neural Language Generation in Dialogue Systems (2018, methodology): “(Wen et al., 2015a) 0.8488 2.79% 0.7436 0.85% 0.5240 2.65% 0.5130 1.15% SCLSTM (Wen et al., 2015b) 0.8469 3.12% 0.7543 0.57% 0.5235 2.41% 0.5109 0.89% Enc-Dec (Wen et al., 2016b) 0.8537 4.78% 0.7358 2.98% 0.5142 3.38% 0.5101 4.24% RALSTM (Tran and Nguyen, 2017a) 0.8911 0.48% 0.7739 0.19% 0.5376 0.65”
Dual Latent Variable Model for Low-Resource Natural Language Generation in Dialogue Systems (2018, methodology): “ficient labeled datasets (Wen et al., 2015b,a; Tran et al., 2017; Tran and Nguyen, 2017).”