Personalizing Dialogue Agents: I have a dog, do you have pets too?

By Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, Jason Aaron Edward Weston. 2018

1,727 citations recorded by the source corpus.

Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating. In this work we present the task of making chit-chat more engaging by conditioning on profile information. We collect data and train models to (i)condition on their given profile information; and (ii) information about the person they are talking to, resulting in improved dialogues, as measured by next utterance prediction. Since (ii) is initially unknown our model is trained to engage its partner with personal topics, and we show the resulting dialogue can be used to predict profile information about the interlocutors.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

CoQA: A Conversational Question Answering Challenge (2018, background): “Sequence-to-sequence (seq2seq) models have shown promising results for generating conversational responses (Vinyals and Le, 2015; Serban et al., 2016; Zhang et al., 2018).”
LaMDA: Language Models for Dialog Applications (2022, background): “, [25, 26, 17, 18]), which built on earlier research in neural dialog modeling (e.”
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics (2021, background): “PersonaChat (Zhang et al., 2018) 20.”
Towards a Human-like Open-Domain Chatbot (2020, methodology): “…approach to mitigating this problem is to use more sophisticated decoding algorithms, for instance with different forms of re-ranking (Li et al., 2016a; Shao et al., 2017) or conditioning on proﬁles, topics, and styles (Li et al., 2016b; Wang et al., 2017; Xing et al., 2017; Zhang et al., 2018b).”
“I’m sorry to hear that”: Finding New Biases in Language Models with a Holistic Descriptor Dataset (2022, background): “…2.0 has been finetuned on several purpose-built dialogue datasets, including ones designed to teach consistent personas, knowledge, and empathy (Zhang et al., 2018; Dinan et al., 2018; Rashkin et al., 2019; Smith et al., 2020b; Roller et al., 2021), recall of past conversation details across…”
Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models (2021, methodology): “…strings; in order to more closely match the BlenderBot setup, we use the ParlAI platform3 to tune DialoGPT on the ConvAI2 dataset, an extension of the PersonaChat dataset containing conversations in which partners speak in the guise of specific personas (Zhang et al., 2018; Dinan et al., 2019).”
Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling (2021, methodology): “In particular for conversation, Dinan et al. (2019c) apply retrieval over Wikipedia to aid in open-domain dialogs.”
Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions (2020, methodology): “The Persona-Chat dataset directly tries to model this (Zhang et al., 2018).”
ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons (2019, methodology): “• We provide an explicit benchmark comparison between current best performing retrieval and generative models on two recent tasks, PersonaChat (Zhang et al. 2018) and Wizard of Wikipedia (Dinan et al. 2019b) for several question choices, revealing the current state-of-the-art, and to be used for ben”
Wizard of Wikipedia: Knowledge-Powered Conversational agents (2018, methodology): “ction. 2 RELATED WORK Many existing dialogue tasks do not study the use of knowledge explicitly. For example, popular chit-chat datasets such as Open-Subtitles (Vinyals & Le, 2015), Persona-Chat (Zhang et al., 2018) and Twitter (Sordoni et al., 2015) have tested the ability of sequence-to-sequen”
Retrieve and Refine: Improved Sequence Generation Models For Dialogue (2018, methodology): “Following the protocol in Zhang et al. (2018), we asked humans to conduct short dialogues with our models (100 dialogues each of 10-20 turns, so 600 dialogues in total), and then measure the engagingness, consistency, and fluency (all scored out of 5) as well as to try to detect the persona that…”
Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring (2019, methodology): “This has been explored with Sequential Matching Network CNN-based architectures (Wu et al., 2017), Deep Matching Networks (Yang et al., 2018), Gated Self-Attention (Zhang et al., 2018b), and most recently transformers (Wolf et al., 2019; Vig & Ramea, 2019; Urbanek et al., 2019).”
Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion (2022, methodology): “We also employ the Multi-Session Chat (MSC) (Xu et al., 2021) task, using the same approach as for MS MARCO to predict the most similar previous line to the original target (with the same F1 overlap threshold) and setting that as the knowledge target.”
Learning from Dialogue after Deployment: Feed Yourself, Chatbot! (2019, methodology): “Our experiments use the PERSONACHAT distribution that was released as a part of the ConvAI2 (Burtsev et al., 2018) challenge.”
Neural Text Generation with Unlikelihood Training (2019, background): “…conditional story generation (Fan et al., 2018), contextual text completion (Radford et al., 2019), language modeling as the special case of k=0 , and dialogue modeling (Zhang et al., 2018) where x 1: k is a dialogue history and a completion is the dialogue history plus a next utterance.”
BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage (2022, methodology): “We also use PersonaChat (PC) (Zhang et al., 2018), empathetic dialogues (ED) (Rashkin et al.”
Survey of Hallucination in Natural Language Generation (2022, background): “Persona consistency has been the center of attention [104, 228] and it is one of the most obvious cases of self-contradiction regarding the character of the dialogue system.”