Engaging Image Chat: Modeling Personality in Grounded Dialogue

By Kurt Shuster, Samuel Humeau, Antoine Bordes, Jason Aaron Edward Weston. 2018

26 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Recipes for Safety in Open-domain Chatbots (2020, background): “• Style: The work of Shuster et al. (2018) provided data and proposed a multi-classiﬁer involving 215 dialogue styles ranging from positive (calm, cheerful), to neutral (formal, im-passive), to negative (hostile, cruel).”
Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions (2020, methodology): “For example, captions conditioned on a personality were found to be significantly more engaging than neutral captions, with a win rate of 64.5% (Shuster et al., 2018).”
Learning from Dialogue after Deployment: Feed Yourself, Chatbot! (2019, background): “…dialogue agent’s models are built on the Transformer architecture (Vaswani et al., 2017), which has been shown to perform well on a variety of NLP tasks (Devlin et al., 2018; Radford et al., 2018), including multiple persona-based chat applications (Shuster et al., 2018a,b; Rashkin et al., 2018).”
Queens Are Powerful Too: Mitigating Gender Bias in Dialogue Generation (2019, background): “Recent work in dialogue incorporates personas, or personality descriptions that ground speaker’s chat, such as I love fishing (Zhang et al., 2018; Shuster et al., 2018; Mazaré et al., 2018; Olabiyi et al., 2018; Li et al., 2016).”
Multi-Dimensional Gender Bias Classification (2020, background): “, 2019c), ImageChat (chit-chat dialogue about an image) (Shuster et al., 2018), OpenSubtitles (dialogue from”
Learning to Speak and Act in a Fantasy Text Adventure Game (2019, background): “There are also setups that consider static language and perception, for example image captioning (Lin et al., 2014), video captioning (Yu et al., 2016), visual QA (Antol et al., 2015) and visual dialogue (Das et al., 2017; Shuster et al., 2018; Mostafazadeh et al., 2017).”
The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents (2019, methodology): “It can also discuss images, as this is a vital part of human connection (Image Chat, IGC).”
Controlling Style in Generated Dialogue (2020, methodology): “There are many other attributes that could describe a given response, e.g., whether it is polite (Niu and Bansal, 2018), formal (Rao and Tetreault, 2018), empathetic (Rashkin et al., 2019), knowledgeable (Dinan et al., 2019), or associated with a variety of styles (Shuster et al., 2018).”
Augmenting Transformers with KNN-Based Composite Memory for Dialog (2020, methodology): “In both datasets, models must leverage information external to the dialogue history alone — in Wizard of Wikipedia, the chat requires access to a knowledgeable facts and in Engaging Imagechat, discussion about a speciﬁc image.”
Knowledge-Grounded Dialogue Generation with Pre-trained Language Models (2020, methodology): “, 2020), or extracted from visual background (Mostafazadeh et al., 2017; Shuster et al., 2018; Huber et al., 2018).”
All-in-One Image-Grounded Conversational Agents (2019, methodology): “…set of imageand-text tasks have been devised by researchers, covering image captioning [Young et al., 2014; Chen et al., 2015; Shuster et al., 2019a], visual question answering [Goyal et al., 2017; Das et al., 2017], and dialogue based on an image [Mostafazadeh et al., 2017; Shuster et al., 2018].”
Why Build an Assistant in Minecraft? (2019, background): “for image captioning [54], video captioning [98], visual QA [8] or visual dialogue [22, 72].”
Real-time Inference in Multi-sentence Tasks with Deep Pretrained Transformers (2019, background): “We focus on the latter approach in this work, as it remains superior than the former in terms of engagingness (Shuster et al., 2018; Zhang et al., 2018a), and allows for more control over the possible outcomes.”