+ All Categories
Home > Documents > An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User...

An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User...

Date post: 20-Sep-2020
Category:
Upload: others
View: 0 times
Download: 0 times
Share this document with a friend
18
An Approach for Ex-Post-Facto Analysis of Knowledge Graph-Driven Chatbots – the DBpedia Chatbot Rricha Jalota , Priyansh Trivedi, Gaurav Maheshwari, Axel-Cyrille Ngonga Ngomo, Ricardo Usbeck November 20, 2019 Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 1 / 17
Transcript
Page 1: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

An Approach for Ex-Post-Facto Analysis of KnowledgeGraph-Driven Chatbots – the DBpedia Chatbot

Rricha Jalota, Priyansh Trivedi, Gaurav Maheshwari, Axel-Cyrille Ngonga Ngomo, RicardoUsbeck

November 20, 2019

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 1 / 17

Page 2: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

Introduction

Figure: U.S. Chatbot Market by Vertical, 2014 - 2025 (USD Million) 1

1Source: https://www.grandviewresearch.com/industry-analysis/chatbot-marketJalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 2 / 17

Page 3: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

IntroductionKnowledge Graphs and Knowledge Graph-Driven Systems

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 3 / 17

Page 4: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

BackgroundKnowledge Graph-Driven Chatbot: The DBpedia Chatbot

Deployed in August 2017

Purpose2

- Answer factual questions- Answer questions related to DBpedia- Expose the research work being done in DBpedia as product features- Casual conversation/banter

Hybrid Chatbot - domain-specific information (DBpedia-centric FAQs) +domain-agnostic factual questions (using DBpedia KG)

2Source: https://wiki.dbpedia.org/blog/meet-dbpedia-chatbotJalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 4 / 17

Page 5: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

BackgroundKnowledge Graph-Driven Chatbot: The DBpedia Chatbot

Deployed in August 2017

Purpose2

- Answer factual questions- Answer questions related to DBpedia- Expose the research work being done in DBpedia as product features- Casual conversation/banter

Hybrid Chatbot - domain-specific information (DBpedia-centric FAQs) +domain-agnostic factual questions (using DBpedia KG)

2Source: https://wiki.dbpedia.org/blog/meet-dbpedia-chatbotJalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 4 / 17

Page 6: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

BackgroundCase Study: The DBpedia Chatbot

Total: 9084 users, 90,800 interactions

Table: Feedback Statistics

Feedback-asked 28953Feedback-received 7561Negative-feedback 4155

Figure: Architecture of the DBpedia Chatbot

Check http://chat.dbpedia.orghttps://github.com/dbpedia/chatbot

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 5 / 17

Page 7: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

Objective of the Ex-Post-Facto Analysis

Understand the nature of user-requests

- query-patterns- user-intentions

Examine whether the chatbot can serve its purpose – satisfy user-requests

Get insights about the conversation flow to improve the chatbot’s architecture

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 6 / 17

Page 8: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

Approach Overview

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 7 / 17

Page 9: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

ApproachRequest Analysis - Intent Analysis

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 8 / 17

Page 10: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

ApproachRequest Analysis - Intent Analysis

Figure: Visualization of clusters obtained via HDBSCAN on sentence embeddings. Each cluster consistsof at least 25 samples. The top 10 clusters out of a total of 33 have been labeled with their top terms.

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 9 / 17

Page 11: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

ApproachRequest Analysis - Complexity of utterances

Complex Query

Example: Can you give me the names of women born in the Country during the 19th century?

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 10 / 17

Page 12: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

ApproachRequest Analysis - Miscellaneous Analysis

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 11 / 17

Page 13: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

Response Analysis

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 12 / 17

Page 14: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

Response AnalysisEntity Types in Utterances prior to Negative Feedback

Figure: Entity type distribution from 1000manually annotated failed utterances.

Table: spaCy-NER and DBpedia Spotlightaccuracy for detecting person and locationmentions.

System Person Location

spaCy-NER 41.3% 42.2%DBpedia Spotlight 69.2% 46.1%

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 13 / 17

Page 15: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

Conversation Analysis

Figure: Topics as identified by DBpedia Spotlight

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 14 / 17

Page 16: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

Implications for DBpedia Chatbot

Adding support for multilingualism

Smart Suggestions

Detecting implicit feedback andout-of-scope queries

Knowledge-based QA

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 15 / 17

Page 17: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

Implications for Knowledge-driven Chatbots

Multilingual Support

Guide User Input

Guiding User Expectations

Adding explainability

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 16 / 17

Page 18: An Approach for Ex-Post-Facto Analysis of Knowledge Graph ......Multilingual Support Guide User Input Guiding User Expectations Adding explainability Jalota et al Analysis of Knowledge

That’s all Folks!

Get in touch:

Rricha JalotaData Science Group, Paderborn University

[email protected]/dice-group/DBpedia-Chatlog-Analysis

Follow us on Twitter: @DiceUPB, @FraunhoferIAIS,@RrichaJalota

Jalota et al Analysis of Knowledge Graph-Driven Chatbots November 20, 2019 17 / 17


Recommended