shriphani

cosine=0.1429   rank=2  qid=1   rel=1   In A.D. 79, long-dormant Mount Vesuvius erupted, burying in volcanic ash the Roman city of Pompeii; an  estimated 20,000 people died. 
cosine=0.1795   rank=2  qid=2   rel=1   When Michael Jordan--one of the greatest basketball player of all time--made what was expected to be his last trip to play in Atlanta last  March, an NBA record 62,046 fans turned out to see him and the  Bulls. 
cosine=0.3333   rank=1  qid=3   rel=1   Alaska was purchased from Russia in year 1867. 
cosine=0.2632   rank=2  qid=4   rel=1   On March 2, 1962, Wilt Chamberlain scored a record 100 points in a   game against the New York Knicks. 
cosine=0.2353   rank=2  qid=5   rel=1   People of China have mixed feelings about  River, which they often call "sorrow of China" 
cosine=0.4118   rank=2  qid=6   rel=1   Roger Bannister was the first to break the four-minute mile barrier. 
cosine=0.1364   rank=2  qid=7   rel=1   And that's not even to mention the breathtaking beauty of Alaska that became, in 195

shriphani

cosine=0.7721   rank=3  qid=1   rel=1   In A.D. 79, long-dormant Mount Vesuvius erupted, burying in volcanic ash the Roman city of Pompeii; an  estimated 20,000 people died. 
cosine=2.4544   rank=2  qid=2   rel=1   When Michael Jordan--one of the greatest basketball player of all time--made what was expected to be his last trip to play in Atlanta last  March, an NBA record 62,046 fans turned out to see him and the  Bulls. 
cosine=5.0231   rank=1  qid=3   rel=1   Alaska was purchased from Russia in year 1867. 
cosine=2.5577   rank=3  qid=4   rel=1   On March 2, 1962, Wilt Chamberlain scored a record 100 points in a   game against the New York Knicks. 
cosine=6.0903   rank=1  qid=5   rel=1   People of China have mixed feelings about  River, which they often call "sorrow of China" 
cosine=4.5554   rank=2  qid=6   rel=1   Roger Bannister was the first to break the four-minute mile barrier. 
cosine=1.8512   rank=2  qid=7   rel=1   And that's not even to mention the breathtaking beauty of Alaska that became, in 195

shriphani

Lingpipe First-Best:

python src/main/resources/precision_recall.py --test src/main/resources/data/hw2-spalakod.out --truth sample.out
Precision: 0.768513928819
Recall: 0.84883657268
F1 Score: 0.806680714899


Lingpipe 5-Best:

shriphani

shriphani

shriphani

shriphani

<?xml version="1.0" encoding="UTF-8"?>
<!-- 
  HERITRIX 3 CRAWL JOB CONFIGURATION FILE
  
   This is a relatively minimal configuration suitable for many crawls.
   
   Commented-out beans and properties are provided as an example; values
   shown in comments reflect the actual defaults which are in effect
   if not otherwise specified specification. (To change from the default 
   behavior, uncomment AND alter the shown values.)   

shriphani

Project run by Carnegie Mellon University.

Contact: http://www.cs.cmu.edu/~./callan/

shriphani

Tools:

Heritrix 3.2.0, Chagatai distribution, running on lenox:8443

Domains:

The current domain set is:

• http://cardomain.com
• http://everydayhealth.com
• http://health.com

shriphani

#!/bin/bash
# searches for KBA hosts and produces a list of
# documents

kba_hosts_fixed="/bos/usr0/spalakod/Documents/clueweb12pp/kba_2012_hosts_components_reversed"

for host in $(cat $kba_hosts_fixed)
do
    echo host:$host >> host_info
    ./COMMON_CRAWL_PY/bin/python common_crawl_index/bin/remote_copy check $host >> host_info