A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models

Zhang, Hanqing; Song, Haolin; Li, Shaoyu; Zhou, Ming; Song, Dandan

doi:10.48550/arxiv.2201.05337

Cited by 21 publications

(26 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Noticeably, the development of this direction relies strongly on the development of controlled text generation techniques where "safety" could be seen as an important desired attribute in dialogue response generation. Similar to the taxonomy described in [164], we classify the safety improvement methods according to the stage that the methods take effect. The stages are classified as "pre-processing phase", "training phase", and "inference phase".…”

Section: Towards E2e Conversational Modelmentioning

confidence: 99%

Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey

Deng¹,

Sun²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

With the development of artificial intelligence, dialogue systems have been endowed with amazing chitchat capabilities, and there is widespread interest and discussion about whether the generated contents are socially beneficial. In this paper, we present a new perspective of research scope towards building a safe, responsible, and modal dialogue system, including 1) abusive and toxic contents, 2) unfairness and discrimination, 3) ethics and morality issues, and 4) risk of misleading and privacy information. Besides, we review the mainstream methods for evaluating the safety of large models from the perspectives of exposure and detection of safety issues. The recent advances in methodologies for the safety improvement of both end-to-end dialogue systems and pipeline-based models are further introduced. Finally, we discussed six existing challenges towards responsible AI: explainable safety monitoring, continuous learning of safety issues, robustness against malicious attacks, multimodal information processing, unified research framework, and multidisciplinary theory integration. We hope this survey will inspire further research toward safer dialogue systems. 1

show abstract

Section: Towards E2e Conversational Modelmentioning

confidence: 99%

Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey

Deng¹,

Sun²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, various studies have been conducted on controllable text generation [15], [16]. Controllable text generation is the task of generating natural sentences with control over various attributes.…”

Section: Related Workmentioning

confidence: 99%

Controllable Text Generation Using Semantic Control Grammar

Seo

Jung

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Controllable text generation is the primary technique for controlling specific attributes such as topic, keywords and obtaining augmented data. This work proposes a novel controllable text generation framework to improve the controllability of generation models. First, we introduce semantic control grammar, a controllable input format to generate sentences that satisfy the constraints. Second, we adopt a generation and rerank method to obtain semantically reranked controlled sentences. Extensive experiments and analyses are conducted on benchmark, natural language understanding, data-to-text generation, and text classification datasets. Through automatic evaluations, we show that our method leads to improvement over strong baselines. The results show that our model can control sentence and word attributes and semantically generate natural sentences. Furthermore, our techniques improve the generation quality of the model.

show abstract

“…The latter approach is very flexible and can automatically generate explanations based on the context, but it is usually not controllable in the sense that meaningless or even inappropriate text may be produced. One important direction is to explore how to control the content, quality, and flexibility of human-understandable explanations in the combined fields of controllable text generation [331] and explainable recommender systems. • Unbiased explanations.…”

Section: Open Problems and Relationship With Other Trustworthy Perspe...mentioning

confidence: 99%

A Survey on Trustworthy Recommender Systems

Ge¹,

Liu²,

Fu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recommender systems (RS), serving at the forefront of Human-centered AI, are widely deployed in almost every corner of the web and facilitate the human decision-making process. However, despite their enormous capabilities and potential, RS may also lead to undesired counter-effects on users, items, producers, platforms, or even the society at large, such as compromised user trust due to non-transparency, unfair treatment of different consumers, or producers, privacy concerns due to extensive use of user's private data for personalization, just to name a few. All of these create an urgent need for Trustworthy Recommender Systems (TRS) so as to mitigate or avoid such adverse impacts and risks. In this survey, we will introduce techniques related to trustworthy and responsible recommendation, including but not limited to explainable recommendation, fairness in recommendation, privacy-aware recommendation, robustness in recommendation, user controllable recommendation, as well as the relationship between these different perspectives in terms of trustworthy and responsible recommendation. Through this survey, we hope to deliver readers with a comprehensive view of the research area and raise attention to the community about the importance, existing research achievements, and future research directions on trustworthy recommendation.

show abstract

A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models

Cited by 21 publications

References 79 publications

Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey

Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey

Controllable Text Generation Using Semantic Control Grammar

A Survey on Trustworthy Recommender Systems

Contact Info

Product

Resources

About