Microsoft Icecaps: An Open-Source Toolkit for Conversation Modeling

Shiv, Vighnesh Leonardo; Quirk, Chris; Suri, Anshuman; Gao, Xiang; Shahid, Khuram; Govindarajan, Nithya; Zhang, Yizhe; Gao, Jianfeng; Galley, Michel; Brockett, Chris; Menon, Tulasi; Dolan, Bill

doi:10.18653/v1/p19-3021

Cited by 8 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These tasks are proven to improve the performance in human evaluation. Shiv et al [33] propose a multi-task learning toolkit for the personalized dialogue generation, which allows users to design different tasks for better dialogue generation performance. Zheng et al [12] leverage target persona information in generating unilateral persona-consistent responses by designing three different tasks, including the language model, persona routing, and dialogue generation.…”

Section: Multi-task Learningmentioning

confidence: 99%

See 1 more Smart Citation

Bilateral Personalized Dialogue Generation with Contrastive Learning

Li¹,

Deng²

2021

Preprint

View full text Add to dashboard Cite

Generating personalized responses is one of the major challenges in natural human-robot interaction. Current researches in this field mainly focus on generating responses consistent with the robot's pre-assigned persona, while ignoring the user's persona. Such responses may be inappropriate or even offensive, which may lead to the bad user experience. Therefore, we propose a bilateral personalized dialogue generation (BPDG) method with dynamic persona-aware fusion via multi-task transfer learning to generate responses consistent with both personas. The proposed method aims to accomplish three learning tasks: 1) an encoder is trained with dialogue utterances added with corresponded personalized attributes and relative position (language model task), 2) a dynamic persona-aware fusion module predicts the persona presence to adaptively fuse the contextual and bilateral personas encodings (persona prediction task) and 3) a decoder generates natural, fluent and personalized responses (dialogue generation task). To make the generated responses more personalized and bilateral persona-consistent, the Conditional Mutual Information Maximum (CMIM) criterion is adopted to select the final response from the generated candidates. The experimental results show that the proposed method outperforms several state-of-the-art methods in terms of both automatic and manual evaluations.

show abstract

Section: Multi-task Learningmentioning

confidence: 99%

“…In dialogue generation, the BLEU is calculated with the weighted n-gram overlap between the ground-truth response Y and generated responses Y * . The n-gram calculation is shown in the equation (33):…”

Section: A Objective Metrics Introduction 1) Bi-persona Accmentioning

confidence: 99%

Bilateral Personalized Dialogue Generation with Contrastive Learning

Li¹,

Deng²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Other efforts in the software space include RASA (Bocklisch et al, 2017), PolyAI (Henderson et al, 2019), Uber's Plato (Papangelis et al, 2019), Microsoft's IceCaps (Shiv et al, 2019), and Huggingface Transformers library (Wolf et al, 2019a), not focused on dialogue per se, but used as a base in much dialogue work.…”

Section: Shared Tasksmentioning

confidence: 99%

Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions

Roller,

Boureau,

Weston

et al. 2020

Preprint

View full text Add to dashboard Cite

We present our view of what is necessary to build an engaging open-domain conversational agent: covering the qualities of such an agent, the pieces of the puzzle that have been built so far, and the gaping holes we have not filled yet. We present a biased view, focusing on work done by our own group, while citing related work in each area. In particular, we discuss in detail the properties of continual learning, providing engaging content, and being well-behaved -and how to measure success in providing them. We end with a discussion of our experience and learnings, and our recommendations to the community.

show abstract

“…With the rising popularity of chat-bots and the arrival of deep learning, the area of persona-based conversation models (Li et al 2016) is growing by leaps and bounds. The democratization of generative conversational methods provided by open-source libraries such as (Burtsev et al 2018;Shiv et al 2019) fuels further advancements in this field.…”

Section: Related Workmentioning

confidence: 99%

Paranoid Transformer: Reading Narrative of Madness as Computational Approach to Creativity

Agafonova

Tikhonov²,

Yamshchikov

2020

Future Internet

View full text Add to dashboard Cite

This paper revisits the receptive theory in the context of computational creativity. It presents a case study of a Paranoid Transformer—a fully autonomous text generation engine with raw output that could be read as the narrative of a mad digital persona without any additional human post-filtering. We describe technical details of the generative system, provide examples of output, and discuss the impact of receptive theory, chance discovery, and simulation of fringe mental state on the understanding of computational creativity.

show abstract

Microsoft Icecaps: An Open-Source Toolkit for Conversation Modeling

Cited by 8 publications

References 17 publications

Bilateral Personalized Dialogue Generation with Contrastive Learning

Bilateral Personalized Dialogue Generation with Contrastive Learning

Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions

Paranoid Transformer: Reading Narrative of Madness as Computational Approach to Creativity

Contact Info

Product

Resources

About