A Context-aware Natural Language Generator for Dialogue Systems

Dušek, Ondřej; Jurčíček, Filip

doi:10.18653/v1/w16-3622

Cited by 56 publications

(71 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An example MR-reference pair is shown in Figure 1, Table 1 lists all the attributes in our domain. In contrast to previous work (Mairesse et al, 2010;Wen et al, 2015a;Dušek and Jurčíček, 2016), we use different modalities of meaning representation for data collection: textual/logical and pictorial MRs. The textual/logical MRs (see Figure 1) take the form of a sequence with attributevalue pairs provided in a random order.…”

Section: The E2e Nlg Dataset 21 Data Collection Proceduresmentioning

confidence: 99%

Findings of the E2E NLG Challenge

Dušek

Novikova

Rieser

2018

Proceedings of the 11th International Conference on Natural Language Generation

Self Cite

View full text Add to dashboard Cite

This paper summarises the experimental setup and results of the first shared task on end-to-end (E2E) natural language generation (NLG) in spoken dialogue systems. Recent end-to-end generation systems are promising since they reduce the need for data annotation. However, they are currently limited to small, delexicalised datasets. The E2E NLG shared task aims to assess whether these novel approaches can generate better-quality output by learning from a dataset containing higher lexical richness, syntactic complexity and diverse discourse phenomena. We compare 62 systems submitted by 17 institutions, covering a wide range of approaches, including machine learning architectures -with the majority implementing sequence-to-sequence models (seq2seq) -as well as systems based on grammatical rules and templates.

show abstract

Section: The E2e Nlg Dataset 21 Data Collection Proceduresmentioning

confidence: 99%

Findings of the E2E NLG Challenge

Dušek

Novikova

Rieser

2018

Proceedings of the 11th International Conference on Natural Language Generation

Self Cite

View full text Add to dashboard Cite

show abstract

“…These models are completely or partially rule-based and focus on specific aspects of entrainment. Recent work aims at introducing entrainment in a fully trainable natural language system by exploiting the preceding user utterance (Dušek and Jurcıcek, 2016).…”

Section: Related Workmentioning

confidence: 99%

Automatic Measures to Characterise Verbal Alignment in Human-Agent Interaction

Duplessis¹,

Clavel²,

Landragin³

2017

Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue

View full text Add to dashboard Cite

This work aims at characterising verbal alignment processes for improving virtual agent communicative capabilities. We propose computationally inexpensive measures of verbal alignment based on expression repetition in dyadic textual dialogues. Using these measures, we present a contrastive study between Human-Human and Human-Agent dialogues on a negotiation task. We exhibit quantitative differences in the strength and orientation of verbal alignment showing the ability of our approach to characterise important aspects of verbal alignment.

show abstract

“…Figure 1 summarizes the model architecture. This model builds on the open-source sequence-tosequence (seq2seq) TGen system [11], which is implemented in Tensorflow [12]. 2 The system is based on the seq2seq generation method with attention [14,15], and uses a sequence of LSTMs [16] for the encoder and decoder, combined with beamsearch and an n-best list reranker for output tuning.…”

Section: Data and Modelsmentioning

confidence: 99%

“…The inputs to the model are dialog acts for each system action (such as inform) and a set of attribute slots (such as rating) and their values (such as high for attribute rating). To prepro- 2 We refer the reader to TGen publications [11,13] for model details. We encode personality as an additional dialog act, of type CONVERT with personality as the key and the target personality as the value (see Figure 1).…”

Section: Data and Modelsmentioning

confidence: 99%

Neural MultiVoice Models for Expressing Novel Personalities in Dialog

Oraby¹,

Reed²,

Sharath³

et al. 2018

Interspeech 2018

View full text Add to dashboard Cite

Natural language generators for task-oriented dialog should be able to vary the style of the output utterance while still effectively realizing the system dialog actions and their associated semantics. While the use of neural generation for training the response generation component of conversational agents promises to simplify the process of producing high quality responses in new domains, to our knowledge, there has been very little investigation of neural generators for task-oriented dialog that can vary their response style, and we know of no experiments on models that can generate responses that are different in style from those seen during training, while still maintaining semantic fidelity to the input meaning representation. Here, we show that a model that is trained to achieve a single stylistic personality target can produce outputs that combine stylistic targets. We carefully evaluate the multivoice outputs for both semantic fidelity and for similarities to and differences from the linguistic features that characterize the original training style. We show that contrary to our predictions, the learned models do not always simply interpolate model parameters, but rather produce styles that are distinct, and novel from the personalities they were trained on.

show abstract

A Context-aware Natural Language Generator for Dialogue Systems

Cited by 56 publications

References 31 publications

Findings of the E2E NLG Challenge

Findings of the E2E NLG Challenge

Automatic Measures to Characterise Verbal Alignment in Human-Agent Interaction

Neural MultiVoice Models for Expressing Novel Personalities in Dialog

Contact Info

Product

Resources

About