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
09 API Interactions III.
Search
LiLa'16
March 20, 2016
Research
0
50
09 API Interactions III.
LiLa'16
March 20, 2016
Tweet
Share
More Decks by LiLa'16
See All by LiLa'16
01 Introduction
lila16ecir
0
77
02 Online Evaluation
lila16ecir
0
82
03 LL4IR Architecture
lila16ecir
0
66
04 Use-Cases
lila16ecir
0
69
05 API Interactions I.
lila16ecir
0
63
06 Models for Use-Cases
lila16ecir
0
55
07 API Interactions II.
lila16ecir
0
54
08 Interpreting Feedback
lila16ecir
0
93
10 Simulations
lila16ecir
0
74
Other Decks in Research
See All in Research
在庫管理のための機械学習と最適化の融合
mickey_kubo
3
1.1k
20250624_熊本経済同友会6月例会講演
trafficbrain
1
600
NLP Colloquium
junokim
1
200
大規模な2値整数計画問題に対する 効率的な重み付き局所探索法
mickey_kubo
1
360
問いを起点に、社会と共鳴する知を育む場へ
matsumoto_r
PRO
0
610
カスタマーサクセスの視点からAWS Summitの展示を考える~製品開発で活用できる勘所~
masakiokuda
2
190
20250725-bet-ai-day
cipepser
2
420
AIスパコン「さくらONE」のLLM学習ベンチマークによる性能評価 / SAKURAONE LLM Training Benchmarking
yuukit
0
320
[論文紹介] Intuitive Fine-Tuning
ryou0634
0
110
【輪講資料】Moshi: a speech-text foundation model for real-time dialogue
hpprc
3
660
【緊急警告】日本の未来設計図 ~沈没か、再生か。国民と断行するラストチャンス~
yuutakasan
0
150
2021年度-基盤研究B-研究計画調書
trycycle
PRO
0
290
Featured
See All Featured
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
36
2.5k
How To Stay Up To Date on Web Technology
chriscoyier
790
250k
GraphQLの誤解/rethinking-graphql
sonatard
72
11k
Product Roadmaps are Hard
iamctodd
PRO
54
11k
4 Signs Your Business is Dying
shpigford
184
22k
Into the Great Unknown - MozCon
thekraken
40
2k
How to Think Like a Performance Engineer
csswizardry
26
1.9k
How to train your dragon (web standard)
notwaldorf
96
6.2k
A Tale of Four Properties
chriscoyier
160
23k
Measuring & Analyzing Core Web Vitals
bluesmoon
9
580
Testing 201, or: Great Expectations
jmmastey
45
7.6k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
229
22k
Transcript
Anne Schuth (Blendle / University of Amsterdam, The Netherlands) Krisztian
Balog (University of Stavanger, Norway) Tutorial at ECIR 2016 in Padua, Italy API Interactions III.
Outline for API interactions • Obtaining an API key and
signing up for a site • Getting queries and candidate items • Generating and uploading rankings • Obtaining feedback and outcome
Feedback endpoint • GET /api/participant/feedback/(key)/ (qid)[/(runid)] • Returns feedback for
this user on this query • runid is optional • qid can be “all”
Feedback endpoint { "feedback": [ {"qid": "S-q1", "runid": "baseline", "modified_time":
"Sun, 27 Apr 2014 13:46:00 -0000", "doclist": [ { "clicked": false, "docid": "R-d89", "team": "participant" }, { "clicked": false, "docid": "R-d87", "team": "site" }, { "clicked": true, "docid": "R-d88", "team": "site" }, ...
Outcome endpoint • GET /api/participant/outcome/(key)/ (qid) • Returns outcome for
this user on this query • Outcomes are aggregated per test period • qid can be “all”
Outcome endpoint { "outcomes": [ { "impressions": 661, "losses": 103,
"outcome": 0.4690721649484536, "qid": "all", "site_id": "R", "test_period": { "end": "Sat, 16 May 2015 00:00:00 -0000", "name": "CLEF LL4IR Round #1", "start": "Fri, 01 May 2015 00:00:00 -0000" }, "ties": 467, "type": "test", "wins": 91 }, ... ] }
Exercise • Complete 03_feedback.py to obtain feedback and outcome for
the queries from the run(s) you submitted in exercise #2
What to do with this feedback? • You figure it
out… • (That might be your next paper)