Augmenting End-to-End Dialogue Systems With Commonsense Knowledge

By Tom Young, Erik Cambria, Iti Chaturvedi, Hao Zhou, Subham Biswas, Minlie Huang. 2018

203 citations recorded by the source corpus.

Building dialogue systems that can converse naturally with humans is a challenging yet intriguing problem of artificial intelligence. In open-domain human-computer conversation, where the conversational agent is expected to respond to human utterances in an interesting and engaging way, commonsense knowledge has to be integrated into the model effectively. In this paper, we investigate the impact of providing commonsense knowledge about the concepts covered in the dialogue. Our model represents the first attempt to integrating a large commonsense knowledge base into end-to-end conversational models. In the retrieval-based scenario, we propose a model to jointly take into account message content and related commonsense for selecting an appropriate response. Our experiments suggest that the knowledge-augmented models are superior to their knowledge-free counterparts.

Subfields: Artificial Intelligence

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

Citations in the corpus

Knowledge Infused Learning (K-IL): Towards Deep Incorporation of Knowledge in Deep Learning (2019, background): “In another study, (Young et al. 2018) integrated commonsense knowledge into the conversational models selecting the most appropriate response.”
Multimodal Sentiment Analysis using Hierarchical Fusion with Context Modeling (2018, background): “Sentiment analysis has raised growing interest both within the scientific community, leading to many exciting open challenges, as well as in the business world, due to the remarkable benefits to be had from financial [24] and political [25] forecasting, e-health [26] and etourism [27], user profilin”
Advances and Challenges in Conversational Recommender Systems: A Survey (2021, background): “Second, even though the generated response may be grammatically correct, we can still distinguish a machine-generated utterance from a human-generated utterance, since the machine response lacks basic commonsense [200, 220], personality [135, 216] and emotion [219].”
Knowledge Aware Emotion Recognition in Textual Conversations via Multi-Task Incremental Transformer (2020, background): “…in generative conversation systems, including question answering systems (Hao et al., 2017; Mihaylov and Frank, 2018), open-domain dialogue systems (Young et al., 2018; Zhou et al., 2018b; Zhong et al., 2019a), and task-oriented dialogue systems (He et al., 2019; Madotto et al., 2018; Chen et al.,…”
A Compare Aggregate Transformer for Understanding Document-grounded Dialogue (2020, background): “[30] or structured knowledge triples [13, 31, 36] to help open-domain conversation generation by producing responses conditioned on selected knowledge.”
ICON: Interactive Conversational Memory Network for Multimodal Emotion Detection (2018, background): “This can help in creating empathetic dialogue systems, thus improving the overall human-computer interaction experience (Young et al., 2018).”
A Controllable Model of Grounded Response Generation (2020, background): “2018) or commonsense knowledge graphs (Young et al. 2018) to conversational models.”
Knowledge Aware Conversation Generation with Explainable Reasoning over Augmented Graphs (2019, background): “…knowledge, either unstructured knowledge texts (Ghazvininejad et al., 2018; Vougiouklis et al., 2016) or structured knowledge triples (Liu et al., 2018; Young et al., 2018; Zhou et al., 2018) to help open-domain conversation generation by producing responses conditioned on selected knowledge.”
FCM: A Fine-grained Comparison Model for Multi-turn Dialogue Reasoning (2021, unknown): “Previous models (Young et al., 2018; Devlin et al., 2019) ignore the modeling of fine-grained comparison, which leads to the loss of reasoning ability of their models.”
Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks (2021, unknown): “Affective Commonsense Knowledge The significant role of external knowledge in many NLP tasks has been remarked on [32, 33, 34, 35, 36, 37].”
Commonsense Knowledge Mining from Pretrained Models (2019, methodology): “One method for mollifying this issue is directly augmenting models with commonsense knowledge bases (Young et al., 2018), which typically contain high-quality information but with low coverage.”
OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs (2019, background): “• Tri-LSTM (Young et al., 2018): encodes each utterance and all of its related facts within 1-hop from a KG to retrieve a response from a small (N=10) pre-deﬁned sentence bank.”
Commonsense for Generative Multi-Hop Question Answering Tasks (2018, methodology): “, 2013), and more recently, dialogue (Young et al., 2018; Ghazvininejad et al., 2018).”
Conversational Memory Network for Emotion Recognition in Dyadic Dialogue Videos (2018, background): “Emotion detection from such resources can benefit numerous fields like counseling (De Choudhury et al., 2013), public opinion mining (Cambria et al., 2017), financial forecasting (Xing et al., 2018), and intelligent systems such as smart homes and chatbots (Young et al., 2018).”
Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations (2019, background): “…base in generative conversation systems, such as open-domain dialogue systems (Han et al., 2015; Asghar et al., 2018; Ghazvinine-jad et al., 2018; Young et al., 2018; Parthasarathi and Pineau, 2018; Liu et al., 2018; Moghe et al., 2018; Dinan et al., 2019; Zhong et al., 2019), task-oriented…”