Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
06 Models for Use-Cases
Search
LiLa'16
March 20, 2016
Research
0
57
06 Models for Use-Cases
LiLa'16
March 20, 2016
Tweet
Share
More Decks by LiLa'16
See All by LiLa'16
01 Introduction
lila16ecir
0
81
02 Online Evaluation
lila16ecir
0
88
03 LL4IR Architecture
lila16ecir
0
69
04 Use-Cases
lila16ecir
0
74
05 API Interactions I.
lila16ecir
0
64
07 API Interactions II.
lila16ecir
0
57
08 Interpreting Feedback
lila16ecir
0
110
09 API Interactions III.
lila16ecir
0
52
10 Simulations
lila16ecir
0
79
Other Decks in Research
See All in Research
病院向け生成AIプロダクト開発の実践と課題
hagino3000
0
530
AIスパコン「さくらONE」の オブザーバビリティ / Observability for AI Supercomputer SAKURAONE
yuukit
2
1.2k
第66回コンピュータビジョン勉強会@関東 Epona: Autoregressive Diffusion World Model for Autonomous Driving
kentosasaki
0
340
世界の人気アプリ100個を分析して見えたペイウォール設計の心得
akihiro_kokubo
PRO
66
37k
世界モデルにおける分布外データ対応の方法論
koukyo1994
7
1.5k
ウェブ・ソーシャルメディア論文読み会 第36回: The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents (EMNLP, 2025)
hkefka385
0
150
J-RAGBench: 日本語RAGにおける Generator評価ベンチマークの構築
koki_itai
0
1.3k
Multi-Agent Large Language Models for Code Intelligence: Opportunities, Challenges, and Research Directions
fatemeh_fard
0
120
都市交通マスタープランとその後への期待@熊本商工会議所・熊本経済同友会
trafficbrain
0
120
An Open and Reproducible Deep Research Agent for Long-Form Question Answering
ikuyamada
0
270
POI: Proof of Identity
katsyoshi
0
140
[Devfest Incheon 2025] 모두를 위한 친절한 언어모델(LLM) 학습 가이드
beomi
2
1.4k
Featured
See All Featured
Amusing Abliteration
ianozsvald
0
100
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
25
1.7k
Tips & Tricks on How to Get Your First Job In Tech
honzajavorek
0
440
Put a Button on it: Removing Barriers to Going Fast.
kastner
60
4.2k
The Invisible Side of Design
smashingmag
302
51k
Collaborative Software Design: How to facilitate domain modelling decisions
baasie
0
140
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
128
55k
Unsuck your backbone
ammeep
671
58k
The Language of Interfaces
destraynor
162
26k
Become a Pro
speakerdeck
PRO
31
5.8k
Utilizing Notion as your number one productivity tool
mfonobong
3
220
Agile Actions for Facilitating Distributed Teams - ADO2019
mkilby
0
110
Transcript
Anne Schuth (Blendle / University of Amsterdam, The Netherlands) Krisztian
Balog (University of Stavanger, Norway) Tutorial at ECIR 2016 in Padua, Italy Models for Use-Cases
Overview • Two use-cases • Product search • Academic literature
search • Simple shared approach • Fielded document representation
Baseline model • Single-field document retrieval • E.g., BM25 score
( d, q ) = X t2q ft,d · (1 + k1) ft,d + k1(1 b + b |d| avgdl ) · idft
Single-field document represenation • Using only product name field •
Using catchall field docid R-d3504 product_name LEGO DUPLO Kreatív láda 10817 docid R-d3504 catchall LEGO DUPLO Kreatív láda 10817 Építőjáték, LEGO LEGO Éld ki kreativitásod minden évszakban LEGO DUPLO elemekkel!
Fielded extension • Multi-field document retrieval, e.g., BM25F score (
d, q ) = X t2q ˜ ft,d k1 + ˜ ft,d · idft ˜ ft,d = X i wi ft,di Bi Combining term frequencies across fields Field weight Soft normalization for field i
Multi-field document representation docid R-d3504 product_name LEGO DUPLO Kreatív láda
10817 brand LEGO DUPLO short_description Éld ki kreativitásod minden évszakban LEGO DUPLO elemekkel! catchall LEGO DUPLO Kreatív láda 10817 Építőjáték, LEGO LEGO Éld ki kreativitásod minden évszakban LEGO DUPLO elemekkel!
Incorporating historical feedback • Combining historical score with retrieval score
• A simple approach: • or