Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings

By Ondrej Dusek, Filip Jurcícek. 2016

189 citations recorded by the source corpus.

We present a natural language generator based on the sequence-to-sequence approach that can be trained to produce natural language strings as well as deep syntax dependency trees from input dialogue acts, and we use it to directly compare two-step generation with separate sentence planning and surface realization stages to a joint, one-step approach. We were able to train both setups successfully using very little training data. The joint setup offers better performance, surpassing state-of-the-art with regards to n-gram-based scores while providing more relevant outputs.

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

Scaling Neural Machine Translation (2018, methodology): “Similar sequence-to-sequence models are also applied to other natural language processing tasks, such as abstractive summarization (See et al., 2017; Paulus et al., 2018) and dialog (Sordoni et al., 2015; Serban et al., 2017; Dusek and Jurc´ıcek, 2016).”
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics (2021, background): “We additionally train the following baselines on a subset of tasks: TGen (with added language model and lemma tags denoted as TGen+/++) (Dušek and Jurčíček, 2016b), an architecture for generation from dialog acts, an LSTM-based Sequence-to-sequence model with attention (Bahdanau et al., 2015), Dia”
Semantic Noise Matters for Neural Natural Language Generation (2019, methodology): “In this paper, we examine the impact of this type of semantic noise on two state-of-the-art NNLG models with different semantic control mechanisms: TGen (Dušek and Jurčı́ček, 2016) and SCLSTM (Wen et al.”
Neural Generation for Czech: Data and Baselines (2019, methodology): “NLG system (Dušek and Jurčı́ček, 2016) based on the seq2seq architecture, and we implement two extensions for Czech: (1) an RNN LM model to select the correct inflected surface form for slot values and (2) lemma-tag generation mode, where the generator produces an interleaved sequences of base form ”
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…”
Few-shot Natural Language Generation for Task-Oriented Dialog (2020, background): “…and ﬂexibility in NLG. Extensive efforts have been made, including new architecture choices such as RNNs (Wen et al., 2015a), attention RNNs (Duˇsek and Jurˇc´ıˇcek, 2016), SC-LSTM (Wen et al., 2015b) and its variants (Tran et al., 2017; Tran and Nguyen, 2017), as well as learning…”
Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation (2017, methodology): “Research in the task oriented setting has mostly made use of automated metrics such as BLEU and human evaluation (Wen et al., 2015b; Sharma et al., 2017; Dušek and Jurcicek, 2016).”
Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue (2019, background): “…(Seq2Seq) models, have been promoted with great fanfare in recent years (Wen et al., 2015, 2016; Mei et al., 2016; Kiddon et al., 2016; Dušek and Jurcicek, 2016), and avenues like the recent E2E NLG challenge (Dušek et al., 2018, 2019) have made available large datasets to promote the…”
A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, background): “[14] also presented a natural language generator based on the sequence-to-sequence approach that can be trained to produce natural language strings as well as deep syntax dependency trees from input dialogue acts.”
End-to-End Content and Plan Selection for Data-to-Text Generation (2018, methodology): “The parameters were found by grid search starting from the parameters used in the TGEN model by Duˇsek and Jurˇc´ıˇcek (2016).”
Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inference (2020, methodology): “• TGen reranker is an LSTM-based model trained on the E2E training data to rerank outputs of the TGen system (Dušek and Jurčíček, 2016) based on their semantic accuracy.”