# Lingke: A Fine-grained Multi-turn Chatbot for Customer Service

arXiv: https://arxiv.org/abs/1808.03430 · HTML: https://mlsanity.com/paper/1808.03430/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2018.

## Built on by (most cited first, 10 of 10)

- [Structural Pre-training for Dialogue Comprehension](https://mlsanity.com/paper/2105.10956/) (2021)
- [Enhanced Speaker-aware Multi-party Multi-turn Dialogue Comprehension](https://mlsanity.com/paper/2109.04066/) (2021)
- [Multi-turn Dialogue Reading Comprehension with Pivot Turns and Knowledge](https://mlsanity.com/paper/2102.05474/) (2021)
- [Dialogue-oriented Pre-training](https://mlsanity.com/paper/2106.00420/) (2021)
- [Smoothing Dialogue States for Open Conversational Machine Reading](https://mlsanity.com/paper/2108.12599/) (2021)
- [Multi-turn Dialogue Comprehension from a Topic-aware Perspective](https://mlsanity.com/paper/2309.09666/) (2023)
- [Towards End-to-End Open Conversational Machine Reading](https://mlsanity.com/paper/2210.07113/) (2022)
- [Multilingual Coreference Resolution in Low-resource South Asian Languages](https://mlsanity.com/paper/2402.13571/) (2024)
- [Channel-aware Decoupling Network for Multi-turn Dialogue Comprehension](https://mlsanity.com/paper/2301.03953/) (2023)
- [SMDDH: Singleton Mention detection using Deep Learning in Hindi Text](https://mlsanity.com/paper/2301.09361/) (2023)

## Abstract (arXiv)

Traditional chatbots usually need a mass of human dialogue data, especially when using supervised machine learning method. Though they can easily deal with single-turn question answering, for multi-turn the performance is usually unsatisfactory. In this paper, we present Lingke, an information retrieval augmented chatbot which is able to answer questions based on given product introduction document and deal with multi-turn conversations. We will introduce a fine-grained pipeline processing to distill responses based on unstructured documents, and attentive sequential context-response matching for multi-turn conversations.