On Enhancing the User Experience

wonderfuldistinctAI and Robotics

Oct 16, 2013 (3 years and 8 months ago)

70 views

On
Enhancing

the User Experience

in Web
Search

Engines

Franco Maria
Nardini

About Me


I joined the HPC Lab in 2006


Master Thesis



Ph.D. in 2011, University of Pisa


Thesis: “Query Log Mining to Enhance
User Experience in Search Engines”



m
ail: francomaria.nardini@isti.cnr.it


w
eb: http://hpc.isti.cnr.it/~nardini


skype: francomaria.nardini




Query
Suggestion

with

Daniele
Broccolo
, Lorenzo
Marcon

Raffaele

Perego
,
Fabrizio

Silvestri

Our Contribution: Search Shortcuts

Our Contribution: Search Shortcuts

Our Contribution: Search Shortcuts


Search

Shortcuts
:


It

u
ses

the “happy
ending
” stories in the
query

log
to help new
users
;


Efficient
:


All

the “
stuff

is

stored

on a
inverted

index
:
retrieval

problem
;


Effective
: (head, torso,
tail
)


New
evaluation

methodology

confirming

this

evidencies
: TREC
Diversity

Track
.


Daniele
Broccolo, Lorenzo Marcon, Franco Maria Nardini, Fabrizio Silvestri, Raffaele
Perego,
Generating

Suggestions

for

Queries

in the Long
Tail

with

an

Inverted

Index
,
IP&M, 2011.

Some Results

What’s

Next
?!


Why

not

to

use

Machine

Learning
?


Machine

learning

is

helping

a
lot

in the IR
community;


Better

and “
fine
-
graned
” ranking
as

it

could

take
into

account
important

signals

that

are
not

fully
-
exploited

nowadays
;


It

may

helps

in
filtering

redundant

suggestions

and
choosing

the “best”
expressive

ones

(for
each

intent
).

u
nder

exploration with

Marcin

Sydow

(PJIIT),

Raffaele

Perego
,
Fabrizio

Silvestri

Signals


Which

signals

we

would

like

to

capture
?


Relevance

to the
given

query
;


Diversity

with
respect

to a
subtopic

list
;


Serendipity

of

suggestions
;


Novelty

with
respect

to news/trends on
Twitter
;


How do
we

catch
them
?


How do
we

combine
them
?


The “training” set
is

a
problem
.

Query

Suggestion
: Ranking



A two
-
step
architecture


First
step

to produce a list of
candidates
;


Second
step

as

a
ML

architecture

composed

of
two

different

(
cascade
)
stages

of ranking:


First round to
rank

suggestions

w.r.t
. the
query
;


Second round to
understand


diversity
”.

Diversification of

Web Search Engine Results


with

Gabriele
Capannini
,
Raffaele

Perego
,
Fabrizio

Silvestri

Our Contribution


We design a method for efficiently diversify
results from Web search engines.


Same effectiveness of other state
-
of
-
the
-
art
approaches;


Extremely fast in doing the “hard” work;


Intents behind “ambiguous” queries are
mined from query logs;


Capannini

G., Nardini F.M.,
Silvestri

F.,
Perego

R.,
A Search Architecture Enabling Efficient Diversification of Search
Results
, Proc. DDR Workshop 2011.

Capannini

G., Nardini F.M.,
Silvestri

F.,
Perego

R.,
Efficient Diversification of Web Search Results
. Proceedings of VLDB
2011 (PVLDB), Volume 4, Issue 7.

Our Contribution

Our Contribution

Some
Results

What’s Next?


A modern ranking architecture:


Effective:


Users should be happy of the results they receive;


Efficient:


Low response times (< 0.1
s
);


Easy to adapt:


Continuous crawling from the Web;


Continuous users’ feedback;

with

Berkant

Barla

Cambazoglu

(Yahoo! Barcelona),

Gabriele
Capannini
,
Raffaele

Perego
,
Fabrizio

Silvestri

Let’s Plug All Together

BM25

Scorer
1



Scorer
n

Query

Index

Second
Phase

First
Phase

Results

Scorer
div

SS


A way for
efficiently

diversifying “ambiguous” queries;


SS teaches how to “diversify” the current user query;


Scorer
div

computes the diversity “signal” of each document and
rerank

the final results list;

Possible intents behind the query

Retrieval over Query Sessions

w
ith

M
-
Dyaa

AlBakour

(University of Glasgow)

Main

Goals


Question

1
)


Can Web
search

engines

improve

their

performance

by

using

previous

user

interactions
?
(
including

previous

queries
,
clicks

on
ranked

results
,
dwell

times
, etc.
)


Question

2
)


How

do
we

evaluate

system performance over an
entire

query

session
instead

of a single
query
?

TREC Session
Track


Two

editions

of the
challenge
: 2010, 2011


query
,
previous

queries
;


urls

+
docs
,
urls

+
docs

+
dwell

time;


Two

different

evaluations
: last
subtop
.,
all

subtop
.


“Query
expansion
” with
Search

Shortcuts
:


w
eighted

by
means

of
user

interaction

data;



history
-
based

recommendation
;


Follow
-
up
with

tuning

of

the
parameters
.

Ibrahim
Adeyanju
,

Franco Maria Nardini,

M
-
Dyaa

Albakour
,

Dawei

Song,

Udo

Kruschwitz
,
RGU
-
ISTI
-
Essex

at TREC 2011
Session Track
, TREC Conference, 2011.

Franco Maria Nardini, M
-
Dyaa

Albakour
, Ibrahim
Adeyanju
,
Udo

Kruschwitz
,
Studying Search Shortcuts in a Query Log
to Improve Retrieval Over Query Sessions
, SIR 2012 in conjunction with ECIR 2012.

Some Results

What’s Next?


Entity
-
based representation of the user
session.


to reduce the “
sparsity
” of the space.


Challenges


How those systems really affect (and modify)
the behavior of the user?


Is it possible to quantify it? (metrics?)


What do we need to observe?


Toward the “perfect result page”:


accurate models for blending different sources of
results
.

Little Announcement

http://tf.isti.cnr.it



Models

and
Techniques

for

Tourist

Facilities


Evaluation

and Test
Collections


User

Interaction

and
Interfaces

Paper Deadline

06/25/2012

Questions!?!