Catherine Faron Zucker & Fabien Gandon, Advisors Elena Cabrio, - - PowerPoint PPT Presentation

▶
catherine faron zucker fabien gandon advisors elena
SMART_READER_LITE
LIVE PREVIEW

Catherine Faron Zucker & Fabien Gandon, Advisors Elena Cabrio, - - PowerPoint PPT Presentation

Feb 20, 2024 357 likes •707 views

Amine Hallili, PhD student Catherine Faron Zucker & Fabien Gandon, Advisors Elena Cabrio, Supervisor 1 Headlines Introduction Motivations Research questions Chatbot Definition Categories Our Chatbot ? Ongoing

slide-1
SLIDE 1

Amine Hallili, PhD student Catherine Faron Zucker & Fabien Gandon, Advisors Elena Cabrio, Supervisor

1

slide-2
SLIDE 2

Headlines

 Introduction

 Motivations  Research questions

 Chatbot

 Definition  Categories  Our Chatbot ?

 Ongoing work

 Our proposal  Knowledge Base  Ontology (Schema.org, GoodRelations)  Pattern Extraction  Property Matching  Response Generation

 Perspectives  References

2

slide-3
SLIDE 3

Introduction

3

slide-4
SLIDE 4

Context & Motivations

 Why ?

 New means of communication

 FAQ  Social Networks  Mobile Applications  Search Engines

 Huge amount of underexploited data especially in

Commercial Domain

 Linked Data  Log files  Raw Text ...

4

slide-5
SLIDE 5

Research questions

 How to construct a Knowledge Base using website APIs ?

 Proposing a platform to extract information

 How to fully understand user’s question ?

 Natural Language Processing

 How to keep users interested in interacting with the

system?

 Natural Language Generation  Friendly interface  Dialog mode

5

slide-6
SLIDE 6

Scenario

6

Give me the price of a Nexus 5!

and who sells it? the price of Nexus 5 is 400$!

several sellers were found. The main one is Google! Do you want to see other sellers? No, show me the white version, sold by Google and located in France! here are the images of Nexus 5 white version, sold by Google and located in France...

slide-7
SLIDE 7

ChatBot

7

slide-8
SLIDE 8

Chatbot – State of the art

 Chatbot, ChatterBot, CleverBot, Chat-Robot (Allen et al) :

Computer program designed to simulate an intelligent conversation with one

  • r more human users via auditory or textual methods, primarily for engaging

in small talk.

 Natural Language Dialog system (NLDs)  Expert System (Liao 2005)  Question Answering system (Hirschman & al)  Multiagent system (Wooldridge 2009)

8

slide-9
SLIDE 9

Chatbot – state of the art

9

slide-10
SLIDE 10

Ongoing work

10

slide-11
SLIDE 11

Our proposal

11

 Combining the benefits of both QA systems & NLDs to

propose :

 A rich KB for data extraction and reasoning  NLP tools to interpret user's question  NLG techniques to generate well-formed sentences.  Integrating Dialog mode to keep user interacting with the

system.

slide-12
SLIDE 12

Our starting point

12

 QAKiS (Cabrio & al 1)

 Question Answering wiKiframework System  Test it at qakis.org

slide-13
SLIDE 13

Our contributions

13

 QAKiS from Open Domain (DBpedia)

=> Closed Domain (Commercial)

 Natural Language Generation  Question with constraints (N-Relations)  Dialog Mode

slide-14
SLIDE 14

14

Question Dialog Manager Response Pattern Finder Triple Feeder Type Recognizer NLP Off–line Feed KB NLG Subject Predicat Value Ontology Triple store Property Recognizer NE Recognizer Query Generator N-Relations Handler Pattern Picker Response Formater

slide-15
SLIDE 15

15

Question Dialog Manager Response Pattern Finder Triple Feeder Type Recognizer NLP Off–line Feed KB NLG Subject Predicat Value Ontology Triple store Property Recognizer NE Recognizer Query Generator N-Relations Handler Pattern Picker Response Formater

slide-16
SLIDE 16

Knowledge Base creation

16

<sbo:Product rdf:about=‘#Nexus_5’ > <sbo:hasPrice>400</sbo:hasPrice> </sbo:Product> Amazon API BestBuy API eBay API

[eBay, Amazon, BestBuy] API Ex : getPrice(Nexus_5) => 400$ Data Transformer RDF Knowledge Base

slide-17
SLIDE 17

Knowledge Base - Example

17

slide-18
SLIDE 18

18

Question Dialog Manager Response Pattern Finder Triple Feeder Type Recognizer NLP Off–line Feed KB NLG Subject Predicat Value Ontology Triple store Property Recognizer NE Recognizer Query Generator N-Relations Handler Pattern Picker Response Formater

slide-19
SLIDE 19

Ontology reuse

19

 Why we need an Ontology ?

Data structuration, Domain representation, Inference.

 Existing ontologies on commercial domain

 Schema.org Ontology

 Covers several domains  Used by state of the art search engines  Partial coverage of the commercial domain

 GoodRelations Ontology (Hepp 2008)

 Better coverage of the commercial domain

slide-20
SLIDE 20

GoodRelations Ontology

20

slide-21
SLIDE 21

GoodRelations Ontology

21

slide-22
SLIDE 22

22

Question Dialog Manager Response Pattern Finder Triple Feeder Type Recognizer NLP Off–line Feed KB NLG Subject Predicat Value Ontology Triple store Property Recognizer NE Recognizer Query Generator N-Relations Handler Pattern Picker Response Formater

slide-23
SLIDE 23

Pattern Extraction - Algorithm

API based method

Crawler & annotation based method

 For each property

 Parse product pages

 Get all sentences containing

the domain and range values

 Make generic patterns

- All pages are tested ! + Finds extra patterns + Easy to implement  For each page => {Subject}

 Parse annotation

=> Graph representing the page

 For each property

 Get all sentences containing

the domain and range values

 Make generic patterns

- Requires annotated pages + More efficient + Less time execution

23

slide-24
SLIDE 24

Pattern extraction – API method

24

Subject <sch:hasDimension> <sch:hasDisplay>

slide-25
SLIDE 25

Pattern extraction – Crawler Method

25

Properties metadata Sentences expressing properties

slide-26
SLIDE 26

26

Question Dialog Manager Response Pattern Finder Triple Feeder Type Recognizer NLP Off–line Feed KB NLG Subject Predicat Value Ontology Triple store Property Recognizer NE Recognizer Query Generator N-Relations Handler Pattern Picker Response Formater

slide-27
SLIDE 27

Property Matching Module

27

<sbo:hasPrice>

[Product] price is [Double] The price of [Product] is [Double] [Product] costs [Double] Give me the price of a Nexus 5!

High score

slide-28
SLIDE 28

Property Matching (N-Relation)

28

 2-relations : Give me the address of Nexus 5 seller !

 Give me the Nexus 5 seller !  Give me his address ! => high score  NE : Nexus 5 => [Product]

<hasAddress> Domain : Seller Range : Address <soldBy> Domain : Product Range : Seller

Same type Nexus_5 LaFnac 10 Jean Medecin, 06000, Nice

slide-29
SLIDE 29

Property Matching (N-Relation)

29

Property1 Domain : D1 Range : R1 Property2 Domain : D2 Range : R2 Property4 Domain : D4 Range : R4 Property5 Domain : D5 Range : R5 Property3 Domain : D3 Range : R3

Graph representing the question : Or / And ? Or / And ? No link ??? No domain or no Range ?!

slide-30
SLIDE 30

30

Question Dialog Manager Response Pattern Finder Triple Feeder Type Recognizer NLP Off–line Feed KB NLG Subject Predicat Value Ontology Triple store Property Recognizer NE Recognizer Query Generator N-Relations Handler Pattern Picker Response Formater

slide-31
SLIDE 31

NL Generation

31

<sbo:hasPrice>

{subject} price is {value} {subject} costs {value} Give me the price of a Nexus 5! Nexus 5 costs 400$!

slide-32
SLIDE 32

Give me the price of a Nexus 5! Dialog Manager Nexus 5 costs 400$ Pattern Finder Triple Feeder <sbo:Product> NLP Off–line Feed KB NLG Subject Predicat Value Nexus5 hasPrice 400$ Ontology Triple store <sbo:hasPrice> <sbr:Nexus_5> Query Generator Select ?v where { <sbr:Nexus_5> <sbo:hasPrice> ?v }

{subject} costs {value}

Nexus 5 costs 400$!

slide-33
SLIDE 33

Perspectives

 Short term :

 NE Recognition improvement

 KNN, Similarity, N-Gram, TF-IDF algorithms

 N-Relations Implementation  Scale to a bigger KB

 Middle term :

 Dialog Mode

 Multiagent systems  Conversational behavior systems

 Serendipity

33

slide-34
SLIDE 34

References

(Allen et al) J. F. Allen, D. K. Byron, M. Dzikovska, G. Ferguson, L. Galescu, and A. Stent. Toward conversational human-computer interaction. AI Magazine, 22(4):2738, 2001. (Liao 2005) S.-H. Liao. Expert system methodologies and applications - a decade review from 1995 to 2004. Expert

  • Syst. Appl., 28(1):93-103, 2005.

(Hirschman & al) L. Hirschman and R. J. Gaizauskas. Natural language question answering: the view from here. Natural Language Engineering, 7(4):275300, 2001. (Wooldridge 2009) M. J. Wooldridge. An Introduction to MultiAgent Systems (2. ed.). Wiley, 2009. (Cabrio & al 1) E. Cabrio, J. Cojan, A. P. Aprosio, B. Magnini, A. Lavelli, and F. Gandon. Qakis: an open domain qa system based on relational patterns. In International Semantic Web Conference (Posters & Demos), 2012. (Cabrio & al .2) E. Cabrio, J. Cojan, A. Palmero Aprosio, and F. Gandon. Natural language interaction with the web of data by mining its textual side. Intelligenza Articiale, 6(2):121-133, 2012. (Augello & al .1) A. Augello, G. Pilato, G. Vassallo, and S. Gaglio. A semantic layer on semi-structured data sources for intuitive chatbots. In CISIS, pages 760-765, 2009. (Augello & al .2) A. Augello, G. Pilato, A. Mach, and S. Gaglio. An approach to enhance chatbot semantic power and maintainability: Experiences within the frasi project. In ICSC, pages 186-193. IEEE Computer Society, 2012. (Hepp 2008) M. Hepp. Goodrelations: An ontology for describing products and services offers on the web. In EKAW, pages 329-346, 2008.

34