Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading
By Lianhui Qin, Michel Galley, Chris Brockett, Xiaodong Liu, Xiang Gao, William B. Dolan, Yejin Choi, Jianfeng Gao. 2019
111 citations recorded by the source corpus.
Although neural conversational models are effective in learning how to produce fluent responses, their primary challenge lies in knowing what to say to make the conversation contentful and non-vacuous. We present a new end-to-end approach to contentful neural conversation that jointly models response generation and on-demand machine reading. The key idea is to provide the conversation model with relevant long-form text on the fly as a source of external knowledge. The model performs QA-style reading comprehension on this text in response to each conversational turn, thereby allowing for more focused integration of external knowledge than has been possible in prior approaches. To support further research on knowledge-grounded conversation, we introduce a new large-scale conversation dataset grounded in external web pages (2.8M turns, 7.4M sentences of grounding). Both human evaluation and automated metrics show that our approach results in more contentful responses compared to a variety of previous methods, improving both the informativeness and diversity of generated output.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Retrieval-Augmented Generation, 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
- Jianfeng Gao
- Mohit Bansal
- Yejin Choi
- Jason Aaron Edward Weston
- Luke S. Zettlemoyer
- Percy Liang
- Hannaneh Hajishirzi
- Noah A. Smith
In Computer Vision and Pattern Recognition
- Jianfeng Gao
- Luc Van Gool
- Mohit Bansal
- Dacheng Tao
- Trevor Darrell
- Xiaogang Wang
- Jason Aaron Edward Weston
- Ming-Hsuan Yang
In Retrieval-Augmented Generation
- Arthur Szlam
- Jianfeng Gao
- Jason Aaron Edward Weston
- Michel Galley
- Hannaneh Hajishirzi
- Eric P. Xing
- Antoine Bordes
- Gunhee Kim
In Natural Language Processing
- Jason Aaron Edward Weston
- Yejin Choi
- Jianfeng Gao
- Mohit Bansal
- Luke S. Zettlemoyer
- Y-Lan Boureau
- Hannaneh Hajishirzi
- Kurt Shuster
Citations in the corpus
- Unified Language Model Pre-training for Natural Language Understanding and Generation (2019, methodology): “We evaluate UNILM on the document-grounded dialog response generation task [30, 15].”
- Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions (2020, background): “…resources have also been invested in developing much larger and more natural crowdsourced benchmarks such as natural language inference (NLI) tasks (Bowman et al., 2015; Williams, Nangia, and Bowman, 2018; Nie et al., 2020) and commonsense reasoning tasks (Zellers et al., 2019; Qin et al., 2019a).”
- Can You Put it All Together: Evaluating Conversational Agents’ Ability to Blend Skills (2020, background): “…performance of open-domain conversational agents along specific axes such as how knowledgeable they are (Dinan et al., 2019b; Moghe et al., 2018; Qin et al., 2019), how well they can display empathy (Rashkin et al., 2019; Lin et al., 2019) or talk about their personal background (Zhang et al.,…”
- The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents (2019, background): “For example, there are additional knowledge tasks (Qin et al., 2019; Moghe et al., 2018; Gopalakrishnan et al., 2019) and image-based datasets (Das et al., 2017) one could use.”
- Challenges in Building Intelligent Open-domain Dialog Systems (2019, background): “Most these studies focus on two problems: (1) knowledge selection—selecting appropriate knowledge to be incorporated in the next response given the dialog context and previously selected knowledge [68, 77, 110, 178] and (2) knowledge-aware generation—injecting the required knowledge into a generated”
- Augmenting Transformers with KNN-Based Composite Memory for Dialog (2020, positive): “We implement the model proposed in Qin et al. (2019), which embeds the conversation history and document contextually before decoding with a biLSTM.”
- Microsoft Icecaps: An Open-Source Toolkit for Conversation Modeling (2019, background): “We provide an extension of stochastic answer networks (Liu et al., 2018), a machine reading comprehension system, that acts as a full knowledge-grounded conversation model (Qin et al., 2019), hybridizing machine reading comprehension with a response generation model.”
- Knowledge-Augmented Methods for Natural Language Processing (2023, methodology): “…sequences, existing methods can be categorized into two methodologies: guiding generation with retrieved information (Ghazvininejad et al., 2018; Lewis et al., 2020; Wang et al., 2021); modeling background knowledge into text generation (Qin et al., 2019; Meng et al., 2020; Zeng et al., 2021).”
- Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features (2021, background): “There are existing knowledge-grounded dialogue datasets (e.g. (Ghazvininejad et al., 2018; Dinan et al., 2019; Qin et al., 2019)) that could be appropriate training resources for such an informative dialogue agent.”
- Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning (2020, methodology): “The associated T IME T RAVEL dataset is based on fictional narratives from ROCStories, for which counterfactual contexts and alternative endings are crowdsourced, yielding 29,849 problem instances.”
- NICE: Neural Image Commenting with Empathy (2021, unknown): “We tested Entropy4 and Distinct2 from Qin et al. (2019).”
- A Controllable Model of Grounded Response Generation (2020, methodology): “Grounded response generation (Ghazvininejad et al. 2018; Dinan et al. 2019; Qin et al. 2019) approaches can inhibit hallucination of facts.”
- Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue (2020, methodology): “Knowledge-based conversations have been studied much including collecting new datasets (Qin et al., 2019; Zhang et al., 2018; Ghazvininejad et al., 2018; Zhou et al., 2018; Dinan et al., 2019; Moghe et al., 2018) or developing new models (Lian et al., 2019; Li et al., 2019b; Yavuz et al., 2019;…”
- Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation (2021, background): “Groundedness As a widely studied aspect of knowledge-based dialog, groundedness measures how well the response refers to the knowledge context (Dinan et al., 2019b; Qin et al., 2019; Mehri and Eskenazi, 2020b).”
- MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation (2022, background): “Later, researchers begin to incorporate knowledge into conversations (Zhang et al., 2018a; Dinan et al., 2018; Zhou et al., 2018b; Gopalakrishnan et al., 2019; Qin et al., 2019; Moon et al., 2019; Rashkin et al., 2019; Tuan et al., 2019; Song et al., 2020).”
- A Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models (2022, unknown): “…Input:dialoguecontent,additionalstructural information(e.g.,persona,emotion,intent,template,etc.) Output:Dialogueresponse Persona[126,127,157,167,168] politeness[36,92],Sentiment[35,113,129,145], Template[55,139], ground-truthreference[97,105,109,147] Storytelling Input:Storyelements”