Task-Based Support in Search Engines

Slide 1

Slide 1 text

Task-Based Support in Search Engines Darío Garigliotti University of Stavanger, Norway December 4th, 2019

Slide 2

Slide 2 text

Outline • Motivation • Type-Aware Entity Retrieval • Target Entity Type Identiﬁcation • Entity-Oriented Search Intents • Task-Based Query Suggestions • Task Recommendations • Conclusions and Future Directions 2

Slide 3

Slide 3 text

Motivation

Slide 4

Slide 4 text

Motivation • Today's web search experience aims to understand the user query 4

Slide 5

Slide 5 text

Motivation • Today's web search experience aims to understand the user query 5

Slide 6

Slide 6 text

Motivation • Today's web search experience aims to understand the user query 6

Slide 7

Slide 7 text

Motivation • Today's web search experience aims to understand the user query • A way to organize information is via structured knowledge centered around entities • Large knowledge repositories and knowledge bases have become available 7

Slide 8

Slide 8 text

Motivation 8

Slide 9

Slide 9 text

Motivation 9

Slide 10

Slide 10 text

Motivation 10

Slide 11

Slide 11 text

Motivation 11

Slide 12

Slide 12 text

• Underlying search goal is often a complex and knowledge-intensive task Motivation 12

Slide 13

Slide 13 text

Motivation 13

Slide 14

Slide 14 text

Motivation 14

Slide 15

Slide 15 text

• Underlying search goal is often a complex and knowledge-intensive task • For example, to plan a travel - How to get there? - Where to stay? - What to do? • Task completion would provide support for the user when accomplishing complex search tasks Motivation 15

Slide 16

Slide 16 text

Roadmap Type-Aware Entity Retrieval Task-Based Search Entity-Oriented Search Intents 16

Slide 17

Slide 17 text

Type-Aware Entity Retrieval

Slide 18

Slide 18 text

An example • Searching for wedding cakes cake shops Konditoriet i Sandnes Olja's Kake Boutique Baker Corner Lura 18

Slide 19

Slide 19 text

An example • Searching for wedding cakes wedding cake shops Stavanger Conditori Olja's Kake Boutique Gjestalveien Conditori 19

Slide 20

Slide 20 text

• Entity retrieval is the task of obtaining a ranked list of entities relevant to a search query • We investigate the utilization of entity type information for entity retrieval Entity Retrieval 20

Slide 21

Slide 21 text

… Shop … … … Company Organization … Stavanger Conditori Bank Law Firm … Entity types • A characteristic property of entities is that they are typed • Types are organized in hierarchies (or taxonomies) 21

Slide 22

Slide 22 text

… Shop … … … Company Organization … cake shops cake shops Bank Law Firm … • Target types: types of entities sought by the query Target entity types 22

Slide 23

Slide 23 text

Type-aware Entity Retrieval • Type information is known to improve entity retrieval • Yet it is a multifaceted problem query entity wedding cake shops target types Stavanger Conditori term-based similarity type-based similarity … … entity types 23

Slide 24

Slide 24 text

How can entity type information be utilized in ad-hoc entity retrieval? 24

Slide 25

Slide 25 text

• We assume oracle-given type information Type-aware Entity Retrieval … Shop … … … Company Organization … cake shops cake shops Bank Law Firm … 25

Slide 26

Slide 26 text

• We assume oracle-given type information • We identify dimensions in utilizing entity type information - Type taxonomy - Type representation - Retrieval model Type-aware Entity Retrieval 26

Slide 27

Slide 27 text

• Which type taxonomy to use? - DBpedia Ontology (7 levels, 600 types) - Freebase Types (2 levels, 2K types) - Wikipedia Categories (34 levels, 600K types) - YAGO Taxonomy (19 levels, 500K types) • These vary a lot in terms of hierarchical structure and in how entity-type assignments are recorded Type-aware Entity Retrieval 27

Slide 28

Slide 28 text

• How to represent the hierarchical information? Type-aware Entity Retrieval 28

Slide 29

Slide 29 text

• How to use type information into entity retrieval? • Retrieval task is deﬁned in a generative probabilistic framework P(q | e) • Both query and entity are considered in the term space as well as in the type space Type-aware Entity Retrieval 29

Slide 30

Slide 30 text

• (Strict) Filtering model Type-aware Entity Retrieval 30

Slide 31

Slide 31 text

• (Soft) Filtering model Type-aware Entity Retrieval 31

Slide 32

Slide 32 text

• Interpolation model Type-aware Entity Retrieval 32

Slide 33

Slide 33 text

• We assume oracle-given type information • We conduct an evaluation of dimensions in utilizing entity type information - Type taxonomy - Type representation - Retrieval model • We use a strong text-based baseline • We test with the DBpedia Entity collection v2 Type-aware Entity Retrieval 33

Slide 34

Slide 34 text

• Wikipedia, in combination with the most specific type representation, performs best • Hierarchical relationships from ancestor types improve retrieval effectiveness, but most specific types provide the best performance • Results regarding most effective type-aware retrieval model vary across configurations Type-aware Entity Retrieval 34

Slide 35

Slide 35 text

Roadmap Type-Aware Entity Retrieval Utilizing Entity Type Information 35

Slide 36

Slide 36 text

Target Entity Type Identiﬁcation

Slide 37

Slide 37 text

Target Type Identiﬁcation • "We assume oracle-given type information" 37

Slide 38

Slide 38 text

Target Type Identiﬁcation • "We assume oracle-given type information" 38

Slide 39

Slide 39 text

Target Type Identiﬁcation • "We assume oracle-given type information" - How to identify target entity types? - How do these target types automatically identiﬁed perform for type-aware entity retrieval? 39

Slide 40

Slide 40 text

How can we automatically identify target entity types? 40

Slide 41

Slide 41 text

Target Type Identification • We revisit the task of hierarchical target type identification • Task: to find the main target types of a query, from a type taxonomy, such that these are the most specific category of entities that are relevant to the query. If no matching type can be found in the taxonomy then the query is assigned a special NIL-type 41

Slide 42

Slide 42 text

Target Type Identiﬁcation • We develop a Learning-to-Rank approach • We evaluate it using a purpose-built test collection 42

Slide 43

Slide 43 text

Target Type Identiﬁcation 43 • Our method combines baseline, knowledge base, and type label features

Slide 44

Slide 44 text

Target Type Identiﬁcation • We also conduct an evaluation utilizing, rather than a target types oracle, target entity types automatically identiﬁed 44

Slide 45

Slide 45 text

Target Type Identiﬁcation 45

Slide 46

Slide 46 text

We identify and evaluate dimensions in utilizing target entity type information for ad-hoc entity retrieval. We build a test collection for target entity type identiﬁcation, and develop and evaluate a Learning-to-Rank approach for this problem. SUMMARY 46

Slide 47

Slide 47 text

Roadmap Type-Aware Entity Retrieval Utilizing Entity Type Information Identifying Target Entity Type Information 47

Slide 48

Slide 48 text

Entity-Oriented Search Intents

Slide 49

Slide 49 text

Entity-Oriented Search Intents • Intent: the underlying user need in a entity- oriented search query - For example, the intent of booking a hotel room • Reﬁner: a way to express an intent in an entity-oriented query - For example, for booking a hotel room: "booking", "book", "reservation", "rooms" 49

Slide 50

Slide 50 text

• Searching about a fashion designer An example 50

Slide 51

Slide 51 text

vivienne westwood age An example 51

Slide 52

Slide 52 text

vivienne westwood age An example 78 years April 8, 1941 52

Slide 53

Slide 53 text

vivienne westwood age An example 78 years April 8, 1941 53

Slide 54

Slide 54 text

An example 54

Slide 55

Slide 55 text

vivienne westwood instagram An example 55

Slide 56

Slide 56 text

vivienne westwood instagram An example instagram.com/viviennewestwood/ 56

Slide 57

Slide 57 text

vivienne westwood instagram An example instagram.com/viviennewestwood/ 57

Slide 58

Slide 58 text

An example 58

Slide 59

Slide 59 text

vivienne westwood customer care An example 59

Slide 60

Slide 60 text

vivienne westwood customer care An example 60

Slide 61

Slide 61 text

What do entity-oriented queries ask for, and how can they be fulﬁlled? 61

Slide 62

Slide 62 text

instagram Understanding entity- oriented search intents • We obtain a collection of type-level query patterns stella mccartney instagram vivienne westwood instagram 62

Slide 63

Slide 63 text

Understanding entity- oriented search intents • We obtain a collection of type-level query patterns • Pick a Freebase type if it covers 100+ prominent entities • Get query suggestions for top 1000- entities per type • For each query, replace entity by type • Aggregate all frequencies for each (type, refiner) pair • Filter out all type-level refiners with frequency of 4- • Select 50 representative types by stratified sampling 63

Slide 64

Slide 64 text

Understanding entity- oriented search intents • We deﬁne a scheme of intent categories 64

Slide 65

Slide 65 text

Understanding entity- oriented search intents • We deﬁne a scheme of intent categories Website 65

Slide 66

Slide 66 text

Understanding entity- oriented search intents • We deﬁne a scheme of intent categories Property Website 66

Slide 67

Slide 67 text

Understanding entity- oriented search intents • We deﬁne a scheme of intent categories Property Website Service 67

Slide 68

Slide 68 text

Understanding entity- oriented search intents • We deﬁne a scheme of intent categories Property Website Service Other 68

Slide 69

Slide 69 text

Understanding entity- oriented search intents • We deﬁne a scheme of intent categories - Website, Property, Service, Other => Website => Property => Service vivienne westwood age vivienne westwood instagram vivienne westwood customer care 69

Slide 70

Slide 70 text

Understanding entity- oriented search intents • We annotate 2.3K+ unique type-level reﬁners with intent category via crowdsourcing • We observe the proportions of reﬁners in each category Property: 28.6% Service: 54.06% Website: 5.34% Other: 12.08% 70

Slide 71

Slide 71 text

Understanding entity- oriented search intents 71 organization business operation chemical compound film location event food hotel disease restaurant travel destination 0 50 100 150 200 250 university house person newspaper airport basketball player album professional sports team game artwork 0 50 100 150 200 railway human language tv station political party amusement park exhibition venue chef programming language academic institution netflix genre 0 20 40 60 80 100 120 war currency blogger hobby football match sports championship star muscle olympic sport company 0 10 20 30 40 50 WroSicaO cycOone kingdoP PedicaO sSeciaOWy coPic book SubOisher oiO fieOd Wower beer counWry region eOecWion asWeroid beOief 0 10 20 30 40 50 3roSerWy WebsiWe Service 2Wher

Slide 72

Slide 72 text

We propose a scheme of entity-oriented search intent categories. We annotate a collection of query reﬁners using the scheme, and observe that there is a large proportion of service-oriented intents. SUMMARY 72

Slide 73

Slide 73 text

Roadmap Type-Aware Entity Retrieval Entity-Oriented Search Intents Utilizing Entity Type Information Identifying Target Entity Type Information Understanding Entity- Oriented Search Intents 73

Slide 74

Slide 74 text

How can we build a knowledge base of entity-oriented search intents? 74

Slide 75

Slide 75 text

1. Intents searched for a type of entities paris map, sydney map => [city] map 2. Categories assigned to reﬁners vivienne westwood instagram => Website vivienne westwood age => Property vivienne westwood customer care => Service 3. Multiple reﬁners expressing an intent "booking", "book", "make a reservation", "rooms" 75 A knowledge base of entity- oriented search intents

Slide 76

Slide 76 text

1. Intents searched for a type of entities paris map, sydney map => [city] map • (intent ID, searchedForType, entity type, confidence) 2. Categories assigned to reﬁners vivienne westwood instagram => Website vivienne westwood age => Property vivienne westwood customer care => Service 3. Multiple reﬁners expressing an intent "booking", "book", "make a reservation", "rooms" 76 A knowledge base of entity- oriented search intents

Slide 77

Slide 77 text

1. Intents searched for a type of entities paris map, sydney map => [city] map • (intent ID, searchedForType, entity type, confidence) 2. Categories assigned to refiners vivienne westwood instagram => Website vivienne westwood age => Property vivienne westwood customer care => Service • (intent ID, ofCategory, intent category, confidence) 3. Multiple refiners expressing an intent "booking", "book", "make a reservation", "rooms" 77 A knowledge base of entity- oriented search intents

Slide 78

Slide 78 text

1. Intents searched for a type of entities paris map, sydney map => [city] map • (intent ID, searchedForType, entity type, confidence) 2. Categories assigned to refiners vivienne westwood instagram => Website vivienne westwood age => Property vivienne westwood customer care => Service • (intent ID, ofCategory, intent category, confidence) 3. Multiple refiners expressing an intent "booking", "book", "make a reservation", "rooms" • (intent ID, expressedBy, refiner, confidence) A knowledge base of entity- oriented search intents 78

Slide 79

Slide 79 text

Approach Refiners acquisition Refiners categorization Intents discovery [hotel] airport [hotel] spa [hotel] booking ... [hotel] airport: Service [hotel] address: Property [hotel] expedia: Website ... taxi arrive Hotel_Arriving booking make a reservation Hotel_Booking address Hotel_Address KB construction Intent ID Predicate Object Confidence Hotel_Booking searchedForType [hotel] c1 Hotel_Booking ofCategory Service c2 Hotel_Booking expressedBy "booking" c3 Hotel_Booking expressedBy "make a reservation" c4 Hotel_Booking expressedBy "rooms" c5 79

Slide 80

Slide 80 text

Approach Refiners acquisition Refiners categorization Intents discovery [hotel] airport [hotel] spa [hotel] booking ... [hotel] airport: Service [hotel] address: Property [hotel] expedia: Website ... taxi arrive Hotel_Arriving booking make a reservation Hotel_Booking address Hotel_Address Intent profile { KB construction Intent ID Predicate Object Confidence Hotel_Booking searchedForType [hotel] c1 Hotel_Booking ofCategory Service c2 Hotel_Booking expressedBy "booking" c3 Hotel_Booking expressedBy "make a reservation" c4 Hotel_Booking expressedBy "rooms" c5 80

Slide 81

Slide 81 text

Knowledge base construction • Application of the pipeline to extract all quadruples from 581 unseen types • 155K quadruples, 31K intent proﬁles - Excerpt of the KB, for intent ID 81

Slide 82

Slide 82 text

Experimental evaluation • Experts judge correctness, ignoring conﬁdence, of around 1.29% of IntentsKB 82 [0, 0.87) [0.87, 0.88) [0.88, 0.9) [0.9, 0.93) [0.93, 1] Conﬁdence intervals according to the splitting percentiles 0% 20% 40% 60% 80% 100% Proportion of triples 6,337 6,370 6,335 6,368 6,314 Correct Incorrect, OFCATEGORY Incorrect, EXPRESSEDBY

Slide 83

Slide 83 text

We design and build a knowledge base of entity- oriented search intents. We evaluate each component in our approach, as well as the correctness of the obtained knowledge base. SUMMARY 83

Slide 84

Slide 84 text

Roadmap Type-Aware Entity Retrieval Entity-Oriented Search Intents Utilizing Entity Type Information Identifying Target Entity Type Information Understanding Entity- Oriented Search Intents Modeling Entity- Oriented Search Intents 84

Slide 85

Slide 85 text

Task-Based Query Suggestions

Slide 86

Slide 86 text

An example • Planning your wedding 86

Slide 87

Slide 87 text

An example 87

Slide 88

Slide 88 text

low wedding budget An example 88

Slide 89

Slide 89 text

Cheap wedding cake low wedding budget An example 89

Slide 90

Slide 90 text

Cheap wedding cake Make your own invitations low wedding budget An example 90

Slide 91

Slide 91 text

An example Cheap wedding cake Make your own invitations Buy a used wedding gown low wedding budget 91

Slide 92

Slide 92 text

Cheap wedding cake Make your own invitations Buy a used wedding gown low wedding budget An example 92

Slide 93

Slide 93 text

Cheap wedding cake Make your own invitations Buy a used wedding gown Excerpt from TREC Tasks test dataset low wedding budget 1 low budget wedding dresses 0 low wedding budget cars 1 find a gown ... 0 wedding flowers 1 cup cake wedding 1 wedding cakes ... 2 wedding invitation 1 find wedding invitation templates 0 designer dresses wedding ... An example 93

Slide 94

Slide 94 text

Cheap wedding cake Make your own invitations Buy a used wedding gown Excerpt from TREC Tasks test dataset } low wedding budget 1 low budget wedding dresses 0 low wedding budget cars 1 find a gown ... 0 wedding flowers 1 cup cake wedding 1 wedding cakes ... 2 wedding invitation 1 find wedding invitation templates 0 designer dresses wedding ... An example 94

Slide 95

Slide 95 text

Cheap wedding cake Make your own invitations Buy a used wedding gown Excerpt from TREC Tasks test dataset } } low wedding budget 1 low budget wedding dresses 0 low wedding budget cars 1 find a gown ... 0 wedding flowers 1 cup cake wedding 1 wedding cakes ... 2 wedding invitation 1 find wedding invitation templates 0 designer dresses wedding ... An example 95

Slide 96

Slide 96 text

An example Cheap wedding cake Make your own invitations Buy a used wedding gown Excerpt from TREC Tasks test dataset } } } low wedding budget 1 low budget wedding dresses 0 low wedding budget cars 1 find a gown ... 0 wedding flowers 1 cup cake wedding 1 wedding cakes ... 2 wedding invitation 1 find wedding invitation templates 0 designer dresses wedding ... 96

Slide 97

Slide 97 text

How can we generate query suggestions for supporting task-based search? 97

Slide 98

Slide 98 text

• Given an initial query, Suggesting queries to support task-based search wedding cake wedding cake gallery wedding cake recipes wedding cake ﬂavors 98

Slide 99

Slide 99 text

• Given an initial query, to get a ranked list of query suggestions that cover all the possible subtasks related to the task that the user is trying to achieve. Suggesting queries to support task-based search wedding cake wedding cake gallery wedding cake recipes wedding cake ﬂavors 99

Slide 100

Slide 100 text

Slide 101

Slide 101 text

Suggesting queries to support task-based search • We propose an end-to-end generative probabilistic model • We exploit diﬀerent information sources 101

Slide 102

Slide 102 text

Suggesting queries to support task-based search 102 Web snippets Web documents

Slide 103

Slide 103 text

Suggesting queries to support task-based search 103 Query suggestions from search engines

Slide 104

Slide 104 text

Suggesting queries to support task-based search • We propose an end-to-end generative probabilistic model 104

Slide 105

Slide 105 text

• Components: q0 Suggesting queries to support task-based search • We propose an end-to-end generative probabilistic model 105

Slide 106

Slide 106 text

• Components: • Source importance q0 API SUGGS. WEB SNIPPETS WEB DOCS. WH Suggesting queries to support task-based search • We propose an end-to-end generative probabilistic model 106

Slide 107

Slide 107 text

• Components: • Source importance • Document importance q0 API SUGGS. WEB SNIPPETS WEB DOCS. WH Suggesting queries to support task-based search • We propose an end-to-end generative probabilistic model 107

Slide 108

Slide 108 text

• Components: • Source importance • Document importance • Keyphrase relevance q0 Keyphrases API SUGGS. WEB SNIPPETS WEB DOCS. WH Suggesting queries to support task-based search • We propose an end-to-end generative probabilistic model 108

Slide 109

Slide 109 text

• Components: • Source importance • Document importance • Keyphrase relevance • Query suggestion • We propose an end-to-end generative probabilistic model Query suggestions q0 Keyphrases API SUGGS. WEB SNIPPETS WEB DOCS. WH Suggesting queries to support task-based search 109

Slide 110

Slide 110 text

• We make use of the 2015 and 2016 TREC Tasks track datasets for the task understanding problem • We conduct a principled estimation of the components, and analyze the best performing estimators per component Suggesting queries to support task-based search 110

Slide 111

Slide 111 text

Suggesting queries to support task-based search 111 • We observe a heavy reliance on query suggestions from suggestion APIs

Slide 112

Slide 112 text

Generating suggestion candidates Query completion Query reﬁnement wedding cake wedding cake gallery wedding cake recipes wedding cake ﬂavors wedding cake beautiful wedding cakes unique wedding cake designs simple wedding cake • Two query suggestion modes 112

Slide 113

Slide 113 text

• How to jointly generate query suggestions in query completion and reﬁnement modes? - Can we do it without relying on log data / API? • We consider a two-step pipeline: - Candidate generation - Candidate ranking • And focus on the ﬁrst component Generating suggestion candidates 113

Slide 114

Slide 114 text

• We study alternative generation methods and information sources - Methods: popular sufﬁx, neural language, sequence- to-sequence - Sources: AOL query log, KnowHow, WikiAnswers • We build a test collection of query suggestion candidates Generating suggestion candidates 114

Slide 115

Slide 115 text

• End-to-end is still the best method overall, but limited as it depends on API suggestions • Log data is the most useful information source, but the other sources provide valuable suggestions too • Diﬀerent method-source conﬁgurations contribute unique suggestions in both modes Generating suggestion candidates 115

Slide 116

Slide 116 text

We propose and evaluate a generative probabilistic model for task-based query suggestions. We further study alternative methods and information sources for suggestion candidate generation, and build a test collection. SUMMARY 116

Slide 117

Slide 117 text

Roadmap Type-Aware Entity Retrieval Task-Based Search Entity-Oriented Search Intents Utilizing Entity Type Information Identifying Target Entity Type Information Understanding Entity- Oriented Search Intents Modeling Entity- Oriented Search Intents Suggesting Queries 117

Slide 118

Slide 118 text

Task Recommendation

Slide 119

Slide 119 text

Task Recommendation • The underlying search goal is often a complex and knowledge-intensive task • We propose to recommend speciﬁc tasks to users, based on their search queries 119

Slide 120

Slide 120 text

An example • Planning a wedding reception wedding reception Plan a wedding reception Recommended Tasks: Plan your wedding reception exit Announce the bridal party at a reception Throw a Hawaiian wedding reception Choose wedding reception activities 120

Slide 121

Slide 121 text

How can we recommend tasks based on search queries and missions? 121

Slide 122

Slide 122 text

Task Recommendation • Some terminology: - Task repository: a catalog of task descriptions - Task description: a semi-structured document that explains the steps involved in how to complete a given task - Search mission: a set of queries that all share the same underlying task 122

Slide 123

Slide 123 text

Task Recommendation • We introduce two problems: 1. Query-based task recommendation Given a query, to return a ranked list of tasks that correspond to the task behind the query 2. Mission-based task recommendation Given a search mission, to return a ranked list of recommended tasks, corresponding to the queries in the mission 123

Slide 124

Slide 124 text

Task Recommendation • We use a collection of WikiHow articles as our task repository 124 How to Make a Wedding Cake Co-authored by wikiHow Staff ✔ You can make a wedding cake for a customer if you bake for a living, or you might make a cake for loved one’s wedding to help them save money. If you love to bake, then you might even want to make your own wedding cake! Steps 1 Decide on the number and shape of the cake’s layers. Consider how many layers and what shape you want the cake to have. 2 Preheat the oven to the temperature indicated by your recipe. Many recipes call for the oven to be pre-heated to 350 °F (177 °C). 3 Prepare the cake batter according to your recipe’s instructions. Choose a recipe to create the cake batter for your cake. 4 Pour the batter into a greased, parchment-lined cake pan. Spray your cake pan with non-stick cooking spray. Explanation Main Act Detailed Act Title

Slide 125

Slide 125 text

Task Recommendation • We focus on a subset of tasks, the procedural tasks • Procedural task: a search task that can be accomplished by following a sequence of speciﬁc actions or subtasks 125

Slide 126

Slide 126 text

Task Recommendation • From a corpus of search queries and missions, we obtain a set of procedural search missions 126

Slide 127

Slide 127 text

Task Recommendation • We build a test collection for task recommendation 127

Slide 128

Slide 128 text

Query-based task recommendation • We propose a Learning-to-Rank method for query-based task recommendation, that combines a text-based ranking technique with continuous semantic representations • We experiment with diﬀerent word embeddings and word function sets according to POS-tag 128

Slide 129

Slide 129 text

129 Query-based task recommendation

Slide 130

Slide 130 text

130 Query-based task recommendation

Slide 131

Slide 131 text

• To address mission-based task recommendation, we propose methods that aggregate the individual query-based recommendations for each query into mission- level recommended tasks 131 Mission-based task recommendation

Slide 132

Slide 132 text

132 Mission-based task recommendation

Slide 133

Slide 133 text

We introduce the problems of query-based and mission-based task recommendation. We develop a test collection for task recommendation, and propose and evaluate approaches for these problems. SUMMARY 133

Slide 134

Slide 134 text

Slide 135

Slide 135 text

Conclusions and Future Directions

Slide 136

Slide 136 text

Conclusions 136 wedding cake Stavanger Conditori Olja's Kake Boutique Gjestalveien Conditori Cake shops > Wedding cake shops Recommended tasks Make a Chocolate Cake Basic Chocolate Cake Moist & Fluﬀy Chocolate Cake Bake an Easy Applesauce Cake See ingredients See steps Address: Gjesdalveien 27, 4306 Sandnes Hours Today: 9AM-5PM Address: Godesetdalen 10, 4034 Stavanger CALL CALL CALL Decorate a Cake Working with Fondant Adding Quick Decorations Queries suggested for wedding cake wedding cake recipes for beginners best wedding cake recipes wedding cake recipes video chocolate wedding cake recipes homemade wedding cake recipes from scratch

Slide 137

Slide 137 text

Conclusions 137 wedding cake Stavanger Conditori Olja's Kake Boutique Gjestalveien Conditori Cake shops > Wedding cake shops Recommended tasks Make a Chocolate Cake Basic Chocolate Cake Moist & Fluﬀy Chocolate Cake Bake an Easy Applesauce Cake See ingredients See steps Address: Gjesdalveien 27, 4306 Sandnes Hours Today: 9AM-5PM Address: Godesetdalen 10, 4034 Stavanger CALL CALL CALL Decorate a Cake Working with Fondant Adding Quick Decorations Queries suggested for wedding cake wedding cake recipes for beginners best wedding cake recipes wedding cake recipes video chocolate wedding cake recipes homemade wedding cake recipes from scratch Type-Aware Entity Retrieval Entity-Oriented Search Intents Task-Based Query Suggestions Task Recommendations

Slide 138

Slide 138 text

Thank you!

Slide 139

Slide 139 text

Task-Based Support in Search Engines Darío Garigliotti University of Stavanger December 4th, 2019