Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts

Xu, Can; Wu, Wei; Wu, Yu

doi:10.48550/arxiv.1807.07255

Cited by 9 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Explaining dialogue generation models is of high interests to understand if a generated response is reasonably produced rather than being a random guess. Xu et al [41] takes the dialog act in a controllable response generation model as the explanation. On the other hand, some propose to make dialogue response generation models more interpretable through walking on knowledge graphs [17,24,37].…”

Section: Related Work and Discussionmentioning

confidence: 99%

Local Explanation of Dialogue Response Generation

Tuan¹,

Pryor

Chen

et al. 2021

Preprint

View full text Add to dashboard Cite

In comparison to the interpretation of classification models, the explanation of sequence generation models is also an important problem, however it has seen little attention. In this work, we study model-agnostic explanations of a representative text generation task -dialogue response generation. Dialog response generation is challenging with its open-ended sentences and multiple acceptable responses. To gain insights into the reasoning process of a generation model, we propose a new method, local explanation of response generation (LERG) that regards the explanations as the mutual interaction of segments in input and output sentences. LERG views the sequence prediction as uncertainty estimation of a human response and then creates explanations by perturbing the input and calculating the certainty change over the human response. We show that LERG adheres to desired properties of explanations for text generation including unbiased approximation, consistency and cause identification. Empirically, our results show that our method consistently improves other widely used methods on proposed automatic-and human-evaluation metrics for this new task by 4.4-12.8%. Our analysis demonstrates that LERG can extract both explicit and implicit relations between input and output segments.Preprint. Under review.

show abstract

Section: Related Work and Discussionmentioning

confidence: 99%

Local Explanation of Dialogue Response Generation

Tuan¹,

Pryor

Chen

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Implications of this work include 1) help in assessing the response quality of existing social chatbots at a finer granularity, 2) inform social chatbots about the desirable responses given an emotional prompt, and 3) help in the design and development of more controllable and interpretable neural chatbots (Xu et al, 2018). There are some limitations to this approach as well, which include inaccuracies occurring due to automatic turn and dialogue segmentation and annotation with only 9 empathetic response intents, whereas in reality, there can be more and even contrasting intents such as Accusation, and Disagreement.…”

Section: Discussionmentioning

confidence: 99%

Fine-grained Emotion and Intent Learning in Movie Dialogues

Welivita,

Xie,

2020

Preprint

View full text Add to dashboard Cite

We propose a novel large-scale emotional dialogue dataset, consisting of 1M dialogues retrieved from the OpenSubtitles corpus and annotated with 32 emotions and 9 empathetic response intents using a BERT-based finegrained dialogue emotion classifier. This work explains the complex pipeline used to preprocess movie subtitles and select good movie dialogues to annotate. We also describe the semisupervised learning process followed to train a fine-grained emotion classifier to annotate these dialogues. Despite the large set of labels, our dialogue emotion classifier achieved an accuracy of 65% and was used to annotate 1M emotional movie dialogues from OpenSubtitles. This scale of emotional dialogue classification has never been attempted before, both in terms of dataset size and fine-grained emotion and intent categories. Visualization techniques used to analyze the quality of the resultant dataset suggest that it conforms to the patterns of human social interaction.

show abstract

“…Additionally, human evaluation has its inherent limitation of bias, cost and replication difficulty (Tao et al, 2018). Due to this consensus, some used only automatic metrics (Xing and Fernández, 2018;Xu et al, 2018b) and some used only human evaluation (Krause et al, 2017;Fang et al, 2018) while some used both (Shen et al, 2018;Xu et al, 2018a;Baheti et al, 2018;Ram et al, 2018).…”

Section: Evaluation Metricsmentioning

confidence: 99%

WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue

Khandelwal¹

2021

Preprint

View full text Add to dashboard Cite

An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue. Although, the current approaches improved the response quality, but they over-look the training signals present in the dialogue data. We can leverage these signals to generate the weakly supervised training data for learning dialog policy and reward estimator, and make the policy take actions (generates responses) which can foresee the future direction for a successful (rewarding) conversation. We simulate the dialogue between an agent and a user (modelled similar to an agent with supervised learning objective) to interact with each other. The agent uses dynamic blocking to generate ranked diverse responses and explorationexploitation to select among the Top-K responses. Each simulated state-action pair is evaluated (works as a weak annotation) with three quality modules: Semantic Relevant, Semantic Coherence and Consistent Flow. Empirical studies with two benchmarks indicate that our model can significantly out-perform the response quality and lead to a successful conversation on both automatic evaluation and human judgement.

show abstract

Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts

Cited by 9 publications

References 19 publications

Local Explanation of Dialogue Response Generation

Local Explanation of Dialogue Response Generation

Fine-grained Emotion and Intent Learning in Movie Dialogues

WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue

Contact Info

Product

Resources

About