Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators

Oraby, Shereen; Reed, Lena; Tandon, Shubhangi; Sharath, T. S.; Lukin, Stephanie M.; Walker, Marilyn A.

doi:10.48550/arxiv.1805.08352

Cited by 3 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, LIGHT contains far more male-gendered words than female-gendered words rather than an even split between words of both genders. To create models that can generate a gender-balanced number of gendered words, we propose Conditional Training (CT) for controlling generative model output (Kikuchi et al, 2016;Fan et al, 2017;Oraby et al, 2018;See et al, 2019). Previous work proposed a mechanism to train models with specific control tokens so models learn to associate the control token with the desired text properties (Fan et al, 2017), then modifying the control tokens during inference to produce the desired result.…”

Section: Conditional Trainingmentioning

confidence: 99%

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Dinan¹,

Fan²,

Williams³

et al. 2019

Preprint

View full text Add to dashboard Cite

Models often easily learn biases present in the training data, and their predictions directly reflect this bias. We analyze the presence of gender bias in dialogue and examine the subsequent effect on generative chitchat dialogue models. Based on this analysis, we propose a combination of three techniques to mitigate bias: counterfactual data augmentation, targeted data collection, and conditional training. We focus on the multi-player text-based fantasy adventure dataset LIGHT (Urbanek et al., 2019) as a testbed for our work. LIGHT contains gender imbalance between male and female characters with around 1.6× as many male characters, likely because it is entirely collected by crowdworkers and reflects common biases that exist in fantasy or medieval settings. We show that (i) our proposed techniques mitigate gender bias by balancing the genderedness of generated dialogue utterances; and (ii) they work particularly well in combination. Further, we show through various metrics-such as quantity of gendered words, a dialogue safety classifier, and human evaluation-that our models generate less gendered, but still engaging chitchat responses.

show abstract

Section: Conditional Trainingmentioning

confidence: 99%

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Dinan¹,

Fan²,

Williams³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…In NLG for spoken dialogue systems, the trainable sentence planner proposed in (Walker et al, 2002;Stent et al, 2004) provides the flexibility of adapting to different domains. Subsequently, generators that can tailor user preferences (Walker et al, 2007) or learn their personality traits Walker, 2008, 2011;Oraby et al, 2018) were proposed. To achieve multi-domain NLG, exploiting the shared knowledge between domains is important to handle unseen semantics.…”

Section: Related Workmentioning

confidence: 99%

Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation

Tseng¹,

Budzianowski²,

Wu³

et al. 2019

Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue

View full text Add to dashboard Cite

Domain adaptation in natural language generation (NLG) remains challenging because of the high complexity of input semantics across domains and limited data of a target domain. This is particularly the case for dialogue systems, where we want to be able to seamlessly include new domains into the conversation. Therefore, it is crucial for generation models to share knowledge across domains for the effective adaptation from one domain to another. In this study, we exploit a tree-structured semantic encoder to capture the internal structure of complex semantic representations required for multi-domain dialogues in order to facilitate knowledge sharing across domains. In addition, a layer-wise attention mechanism between the tree encoder and the decoder is adopted to further improve the model's capability. The automatic evaluation results show that our model outperforms previous methods in terms of the BLEU score and the slot error rate, in particular when the adaptation data is limited. In subjective evaluation, human judges tend to prefer the sentences generated by our model, rating them more highly on informativeness and naturalness than other systems.

show abstract

Enhancing User Experience in Chinese Initial Text Conversations with Personalised AI-Powered Assistant

Wang,

Ivrissimtzis,

et al. 2024

Extended Abstracts of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators

Cited by 3 publications

References 0 publications

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation

Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation

Enhancing User Experience in Chinese Initial Text Conversations with Personalised AI-Powered Assistant

Contact Info

Product

Resources

About