# Prediction, Selection, and Generation: Exploration of Knowledge-Driven Conversation System

arXiv: https://arxiv.org/abs/2104.11454 · HTML: https://mlsanity.com/paper/2104.11454/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 23 Apr 2021.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [ERNIE: Enhanced Language Representation with Informative Entities](https://mlsanity.com/paper/1905.07129/) (2019)
- [ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training](https://mlsanity.com/paper/2001.04063/) (2020)
- [Multi-Stage Document Ranking with BERT](https://mlsanity.com/paper/1910.14424/) (2019)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017)
- [Towards Conversational Recommendation over Multi-Type Dialogs](https://mlsanity.com/paper/2005.03954/) (2020)
- [A Large-Scale Chinese Short-Text Conversation Dataset](https://mlsanity.com/paper/2008.03946/) (2020)
- [Interactive Path Reasoning on Graph for Conversational Recommendation](https://mlsanity.com/paper/2007.00194/) (2020)
- [KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation](https://mlsanity.com/paper/2004.04100/) (2020)
- [A Simple, Fast Diverse Decoding Algorithm for Neural Generation](https://mlsanity.com/paper/1611.08562/) (2016)
- [Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge](https://mlsanity.com/paper/1805.07858/) (2018)
- [GLGE: A New General Language Generation Evaluation Benchmark](https://mlsanity.com/paper/2011.11928/) (2020)
- [Neural Natural Language Inference Models Enhanced with External Knowledge](https://mlsanity.com/paper/1711.04289/) (2017)
- [PiRhDy: Learning Pitch-, Rhythm-, and Dynamics-aware Embeddings for Symbolic Music](https://mlsanity.com/paper/2010.08091/) (2020)
- [Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation](https://mlsanity.com/paper/1808.10596/) (2018)
- [Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation](https://mlsanity.com/paper/2009.09378/) (2020)
- [Let's be Humorous: Knowledge Enhanced Humor Generation](https://mlsanity.com/paper/2004.13317/) (2020)
- [Generating Multiple Diverse Responses with Multi-Mapping and Posterior Mapping Selection](https://mlsanity.com/paper/1906.01781/) (2019)
- [Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation](https://mlsanity.com/paper/2004.03875/) (2020)
- [Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction](https://mlsanity.com/paper/2012.11957/) (2020)

## Abstract (arXiv)

In open-domain conversational systems, it is important but challenging to leverage background knowledge. We can use the incorporation of knowledge to make the generation of dialogue controllable, and can generate more diverse sentences that contain real knowledge. In this paper, we combine the knowledge bases and pre-training model to propose a knowledge-driven conversation system. The system includes modules such as dialogue topic prediction, knowledge matching and dialogue generation. Based on this system, we study the performance factors that maybe affect the generation of knowledge-driven dialogue: topic coarse recall algorithm, number of knowledge choices, generation model choices, etc., and finally made the system reach state-of-the-art. These experimental results will provide some guiding significance for the future research of this task. As far as we know, this is the first work to study and analyze the effects of the related factors.