""" Defines 100 examples for the travel domain, divided into 75 training examples and 25 test examples. To construct the sample of 100 queries, we: - Began from the set of unique queries in the AOL dataset (10M queries). - Selected queries containing one of the ~600 locations named in Geobase (1M queries). - Selected queries containing "from" or "to" (23K queries). - Selected queries containing a "travel term" (below), or both "from" and "to" (6,600 queries). - Selected queries that appeared at least twice in the AOL dataset. - Selected queries uniformly at random, throwing out just a few that were "too long". The ~60 "travel terms" were: airfare, airfares, airline, airlines, amtrak, auto, bicycle, bicycling, bike, biking, boat, bus, buses, cab, cabs, car, cheap, cheapest, cruise, cruises, cycling, direction, directions, distance, drive, driving, fare, fares, ferry, ferries, flight, flights, fly, how far, how long, how much, miles, mileage, on foot, pedestrian, rail, route, shortest, shuttles, subway, taxi, ticket, tickets, time, train, trains, transit, transportation, travel, trip, walk, walking. """ __author__ = "Bill MacCartney" __copyright__ = "Copyright 2015, Bill MacCartney" __credits__ = [] __license__ = "GNU General Public License, version 2.0" __version__ = "0.9" __maintainer__ = "Bill MacCartney" __email__ = "See the author's website" from example import Example travel_train_examples = [ Example(input='discount tickets to new york city ballet', semantics={'domain': 'other'}), Example(input='travel boston to fr. myers fla', semantics={'domain': 'travel', 'origin': {'id': 4930956, 'name': 'Boston, MA, US'}, 'destination': {'id': 4155995, 'name': 'Fort Myers, FL, US'}}), Example(input='how do i get from tulsa oklahoma to atlantic city. new jersey by air', semantics={'domain': 'travel', 'type': 'directions', 'mode': 'air', 'origin': {'id': 4553433, 'name': 'Tulsa, OK, US'}, 'destination': {'id': 4500546, 'name': 'Atlantic City, NJ, US'}}), Example(input='airbus from boston to europe', # user's intent is unclear semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 4930956, 'name': 'Boston, MA, US'}, 'destination': {'id': 9408659, 'name': 'Western Europe'}}), Example(input='george washington borrows 500 000 from pennsylvania farmer to finance war', semantics={'domain': 'other'}), Example(input='cheap tickets to south carolina', semantics={'domain': 'travel', 'destination': {'id': 4597040, 'name': 'South Carolina, US'}}), Example(input='birmingham al distance from indianapolish in', semantics={'domain': 'travel', 'type': 'distance', 'origin': {'id': 4259418, 'name': 'Indianapolis, IN, US'}, 'destination': {'id': 4049979, 'name': 'Birmingham, AL, US'}}), Example(input='transportation to the philadelphia airport', semantics={'domain': 'travel', 'destination': {'id': 4560342, 'name': 'Philadelphia International Airport, PA, US'}}), Example(input='one day cruise from fort lauderdale florida', semantics={'domain': 'travel', 'mode': 'boat', 'origin': {'id': 4155966, 'name': 'Fort Lauderdale, FL, US'}}), Example(input='directions from washington to canada', semantics={'domain': 'travel', 'type': 'directions', 'origin': {'id': 4140963, 'name': 'Washington, DC, US'}, 'destination': {'id': 6251999, 'name': 'Canada'}}), Example(input='flights from portland or to seattle wa', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 5746545, 'name': 'Portland, OR, US'}, 'destination': {'id': 5809844, 'name': 'Seattle, WA, US'}}), Example(input='honeymoon trip to hawaii', semantics={'domain': 'travel', 'destination': {'id': 5855797, 'name': 'Hawaii, US'}}), Example(input='travel packages from hartford ct. to berlin germany', semantics={'domain': 'travel', 'origin': {'id': 4835797, 'name': 'Hartford, CT, US'}, 'destination': {'id': 2950159, 'name': 'Berlin, DE'}}), Example(input='nyc flights to buffalo ny', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 5128581, 'name': 'New York City, NY, US'}, 'destination': {'id': 5110629, 'name': 'Buffalo, NY, US'}}), Example(input='norwegian cruises lines to alaska combined with land tours to denali', # It's hard to fully capture the semantics of this input. semantics={'domain': 'travel', 'mode': 'boat', 'destination': {'id': 5879092, 'name': 'Alaska, US'}}), Example(input='direct flights from california to loreto mexico', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 5332921, 'name': 'California, US'}, 'destination': {'id': 8581711, 'name': 'Loreto, MX'}}), Example(input='cheap flights to hawaii', semantics={'domain': 'travel', 'mode': 'air', 'destination': {'id': 5855797, 'name': 'Hawaii, US'}}), Example(input='santiago chile to atlanta ga. airline schedule 3 26 06', semantics={'domain': 'travel', 'type': 'schedule', 'mode': 'air', 'origin': {'id': 3871336, 'name': 'Santiago, Chile'}, 'destination': {'id': 4180439, 'name': 'Atlanta, GA, US'}}), Example(input='directions one address to another in mobile al.', semantics={'domain': 'other'}), Example(input='university of washington transportation to seatac', semantics={'domain': 'travel', 'origin': {'id': 5814448, 'name': 'University of Washington, WA, US'}, 'destination': {'id': 5809805, 'name': 'SeaTac, WA, US'}}), Example(input='buses to sacramento rivercats games', semantics={'domain': 'travel', 'mode': 'bus', 'destination': {'id': 5389489, 'name': 'Sacramento, CA, US'}}), Example(input='cruises departing from norfolk va', semantics={'domain': 'travel', 'mode': 'boat', 'origin': {'id': 4776222, 'name': 'Norfolk, VA, US'}}), Example(input='cruises from new york', semantics={'domain': 'travel', 'mode': 'boat', 'origin': {'id': 5128581, 'name': 'New York, US'}}), Example(input='car service to newark airport', semantics={'domain': 'travel', 'mode': 'taxi', 'destination': {'id': 5101809, 'name': 'Newark Liberty International Airport, NJ, US'}}), Example(input='transatlantic cruise southampton to tampa', semantics={'domain': 'travel', 'mode': 'boat', 'origin': {'id': 2637487, 'name': 'Southampton, GB'}, 'destination': {'id': 4174757, 'name': 'Tampa, FL, US'}}), Example(input='rand mcnally direction to horse shoe casino hammond in', # Horseshoe Casino is not in the GeoNames database. semantics={'domain': 'travel', 'type': 'directions', 'destination': {'id': 4921100, 'name': 'Hammond, IN, US'}}), Example(input='how to apply for uk old age pension from usa', semantics={'domain': 'other'}), Example(input='flight from atlanta to vermont', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 4180439, 'name': 'Atlanta, GA, US'}, 'destination': {'id': 5242283, 'name': 'Vermont, US'}}), Example(input='directions to rupparena in lexington', # Rupp Arena is not in GeoNames database. semantics={'domain': 'travel', 'type': 'directions', 'destination': {'id': 4297983, 'name': 'Lexington, KY, US'}}), Example(input='distance of oxnard ca. to rohnert park ca.', semantics={'domain': 'travel', 'type': 'distance', 'origin': {'id': 5380184, 'name': 'Oxnard, CA, US'}, 'destination': {'id': 5388564, 'name': 'Rohnert Park, CA, US'}}), Example(input='last minute flights to dallas tx from memphis tn', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 4641239, 'name': 'Memphis, TN, US'}, 'destination': {'id': 4684888, 'name': 'Dallas, TX, US'}}), Example(input='driving distance washington dc to niagara falls', semantics={'domain': 'travel', 'type': 'distance', 'mode': 'car', 'origin': {'id': 4140963, 'name': 'Washington, DC, US'}, 'destination': {'id': 5128723, 'name': 'Niagara Falls, NY, US'}}), Example(input='2000 to 2006 time line of tennessee', semantics={'domain': 'other'}), Example(input='jet blue flights to new york', semantics={'domain': 'travel', 'mode': 'air', 'destination': {'id': 5128581, 'name': 'New York, US'}}), Example(input='flights from jacksonville nc to clt', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 4473083, 'name': 'Jacksonville, NC, US'}, 'destination': {'id': 4460310, 'name': 'Charlotte Douglas International Airport, NC, US'}}), Example(input='cost of gas from cedar rapids ia to las vegas', semantics={'domain': 'travel', 'type': 'cost', 'mode': 'car', 'origin': {'id': 4850751, 'name': 'Cedar Rapids, IA, US'}, 'destination': {'id': 5506956, 'name': 'Las Vegas, NV, US'}}), Example(input='one way air fare to chicago', semantics={'domain': 'travel', 'mode': 'air', 'destination': {'id': 4887398, 'name': 'Chicago, IL, US'}}), Example(input='distance cunmming georgia to chattanooga', semantics={'domain': 'travel', 'type': 'distance', 'origin': {'id': 4190396, 'name': 'Cumming, GA, US'}, 'destination': {'id': 4612862, 'name': 'Chattanooga, TN, US'}}), Example(input='cheapest place to live in florida', semantics={'domain': 'other'}), Example(input='cheap flights from orlando to st maarten', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 4167147, 'name': 'Orlando, FL, US'}, 'destination': {'id': 7609695, 'name': 'Sint Maarten'}}), Example(input='cheap flights to detroit michigan from new york', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 5128581, 'name': 'New York, US'}, 'destination': {'id': 4990729, 'name': 'Detroit, MI, US'}}), Example(input='train from pontiac mi to chicago', semantics={'domain': 'travel', 'mode': 'train', 'origin': {'id': 5006166, 'name': 'Pontiac, MI, US'}, 'destination': {'id': 4887398, 'name': 'Chicago, IL, US'}}), Example(input='travel by train from bakersfield ca', semantics={'domain': 'travel', 'mode': 'train', 'origin': {'id': 5325738, 'name': 'Bakersfield, CA, US'}}), Example(input='how to get a oklahoma vehicle accident report from police agency', semantics={'domain': 'other'}), Example(input='bike riding-seattle to portland', semantics={'domain': 'travel', 'mode': 'bike', 'origin': {'id': 5809844, 'name': 'Seattle, WA, US'}, 'destination': {'id': 5746545, 'name': 'Portland, OR, US'}}), Example(input='photos at las vegas nevada from april 1 to april 5 2006', semantics={'domain': 'other'}), Example(input='shoreline train to chicago', semantics={'domain': 'travel', 'mode': 'train', 'destination': {'id': 4887398, 'name': 'Chicago, IL, US'}}), Example(input='all airlines from memphis to mcallen', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 4641239, 'name': 'Memphis, TN, US'}, 'destination': {'id': 4709796, 'name': 'McAllen, TX, US'}}), Example(input='what is 1500 miles away from texas city', semantics={'domain': 'other'}), Example(input='delta flights to oakland', semantics={'domain': 'travel', 'mode': 'air', 'destination': {'id': 5378538, 'name': 'Oakland, CA, US'}}), Example(input='public transportation to new jersey', semantics={'domain': 'travel', 'mode': 'transit', 'destination': {'id': 5101760, 'name': 'New Jersey, US'}}), Example(input='shutle from seatle airport to vancouver airport', semantics={'domain': 'travel', 'mode': 'bus', 'origin': {'id': 5809876, 'name': 'Seattle-Tacoma International Airport, WA, US'}, 'destination': {'id': 6301485, 'name': 'Vancouver International Airport, CA'}}), Example(input='hotels close to 10 manhattan square drive rochester ny 14607', semantics={'domain': 'other'}), Example(input='cruise from new york to canada', semantics={'domain': 'travel', 'mode': 'boat', 'origin': {'id': 5128581, 'name': 'New York, US'}, 'destination': {'id': 6251999, 'name': 'Canada'}}), Example(input='discount travel flights to austin texas', semantics={'domain': 'travel', 'mode': 'air', 'destination': {'id': 4671654, 'name': 'Austin, TX, US'}}), Example(input='book a trip to chicago', semantics={'domain': 'travel', 'destination': {'id': 4887398, 'name': 'Chicago, IL, US'}}), Example(input='rochester ny bus tours to yankees stadium', # Yankees Stadium is not in GeoNames database. semantics={'domain': 'travel', 'mode': 'bus', 'origin': {'id': 5134086, 'name': 'Rochester, NY, US'}, 'destination': {'id': 5128581, 'name': 'New York City, NY, US'}}), Example(input='airfares to honolulu hawaii', semantics={'domain': 'travel', 'mode': 'air', 'destination': {'id': 5856195, 'name': 'Honolulu, HI, US'}}), Example(input='fly boston to myrtle beach spirit airlines', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 4930956, 'name': 'Boston, MA, US'}, 'destination': {'id': 4588718, 'name': 'Myrtle Beach, SC, US'}}), Example(input='distance usa to peru', semantics={'domain': 'travel', 'type': 'distance', 'origin': {'id': 6252001, 'name': 'United States'}, 'destination': {'id': 3932488, 'name': 'Peru'}}), Example(input='mileage from different airports in florida to st. augustine', semantics={'domain': 'travel', 'type': 'distance', 'destination': {'id': 4170894, 'name': 'St. Augustine, FL, US'}}), Example(input='train from moscow to st. petersburg', semantics={'domain': 'travel', 'mode': 'train', 'origin': {'id': 524901, 'name': 'Moscow, RU'}, 'destination': {'id': 498817, 'name': 'Saint-Petersburg, RU'}}), Example(input='flight from ft.lauderdale florida to lexington kentucky', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 4155966, 'name': 'Fort Lauderdale, FL, US'}, 'destination': {'id': 4297983, 'name': 'Lexington, KY, US'}}), Example(input='ithaca to scranton trains', semantics={'domain': 'travel', 'mode': 'train', 'origin': {'id': 5122432, 'name': 'Ithaca, NY, US'}, 'destination': {'id': 5211303, 'name': 'Scranton, PA, US'}}), Example(input='time shares florida to rent', semantics={'domain': 'other'}), Example(input='what will it cost to drive from kemerovo to st. petersburg russia', semantics={'domain': 'travel', 'type': 'cost', 'mode': 'car', 'origin': {'id': 1503901, 'name': 'Kemerovo, RU'}, 'destination': {'id': 498817, 'name': 'Saint-Petersburg, RU'}}), Example(input='balloons and flowers from israel to usa', semantics={'domain': 'other'}), Example(input='transportation to ft lauderdale from orlando', semantics={'domain': 'travel', 'origin': {'id': 4167147, 'name': 'Orlando, FL, US'}, 'destination': {'id': 4155966, 'name': 'Fort Lauderdale, FL, US'}}), Example(input='lawton va to orlando fl amtrak', semantics={'domain': 'travel', 'mode': 'train', 'origin': {'id': 4770714, 'name': 'Lorton, VA, US'}, 'destination': {'id': 4167147, 'name': 'Orlando, FL, US'}}), Example(input='ride this train to roseburg oregon now ther\'s a town for ya', semantics={'domain': 'other'}), Example(input='cheapest airline flight from charlotte to nashville', semantics={'domain': 'travel','mode': 'air', 'origin': {'id': 4460243, 'name': 'Charlotte, NC, US'}, 'destination': {'id': 4644585, 'name': 'Nashville, TN, US'}}), Example(input='flights newark to raleigh nc', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 5101798, 'name': 'Newark, NJ, US'}, 'destination': {'id': 4487042, 'name': 'Raleigh, NC, US'}}), Example(input='driving from los angeles to seattle', semantics={'domain': 'travel', 'mode': 'car', 'origin': {'id': 5368361, 'name': 'Los Angeles, CA, US'}, 'destination': {'id': 5809844, 'name': 'Seattle, WA, US'}}), Example(input='cheap airfare from pittsburgh pa to las vegas nv', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 5206379, 'name': 'Pittsburgh, PA, US'}, 'destination': {'id': 5506956, 'name': 'Las Vegas, NV, US'}}), Example(input='scenic drive to duluth mn', semantics={'domain': 'travel', 'mode': 'car', 'destination': {'id': 5024719, 'name': 'Duluth, MN, US'}}), ] travel_test_examples = [ Example(input='how to fight a disorderly conduct ticket in fairborn ohio', semantics={'domain': 'other'}), Example(input='csaa discount ticket to marine world usa in vallejo', semantics={'domain': 'other'}), Example(input='bus from nyc to boston', semantics={'domain': 'travel', 'mode': 'bus', 'origin': {'id': 5128581, 'name': 'New York City, NY, US'}, 'destination': {'id': 4930956, 'name': 'Boston, MA, US'}}), Example(input='distance from hawaii to california', semantics={'domain': 'travel', 'type': 'distance', 'origin': {'id': 5855797, 'name': 'Hawaii, US'}, 'destination': {'id': 5332921, 'name': 'California, US'}}), Example(input='cheap tickets to hawaii', semantics={'domain': 'travel', 'destination': {'id': 5855797, 'name': 'Hawaii, US'}}), Example(input='california coach tours and trains tours from san francisco', semantics={'domain': 'travel', 'mode': 'train', 'origin': {'id': 5391959, 'name': 'San Francisco, CA, US'}}), Example(input='personal rights to selling a used car in pennsylvania', semantics={'domain': 'other'}), Example(input='travel to sioux falls', semantics={'domain': 'travel', 'destination': {'id': 5231851, 'name': 'Sioux Falls, SD, US'}}), Example(input='road trip fun on i10 alabama to phoenix', semantics={'domain': 'other'}), Example(input='cheap air fares to florida', semantics={'domain': 'travel', 'mode': 'air', 'destination': {'id': 4155751, 'name': 'Florida, US'}}), Example(input='travel orlando fl to las vegas nv by auto', semantics={'domain': 'travel', 'mode': 'car', 'origin': {'id': 4167147, 'name': 'Orlando, FL, US'}, 'destination': {'id': 5506956, 'name': 'Las Vegas, NV, US'}}), Example(input='bus service from south bend in to ft. lauderdale', semantics={'domain': 'travel', 'mode': 'bus', 'origin': {'id': 4926563, 'name': 'South Bend, IN, US'}, 'destination': {'id': 4155966, 'name': 'Fort Lauderdale, FL, US'}}), Example(input='2006 airfare to san juan puerto rico', semantics={'domain': 'travel', 'mode': 'air', 'destination': {'id': 4568127, 'name': 'San Juan, PR'}}), Example(input='flight to tampa florida name your own price', semantics={'domain': 'travel', 'mode': 'air', 'destination': {'id': 4174757, 'name': 'Tampa, FL, US'}}), Example(input='train schedule from new hampshire to nova scotia', semantics={'domain': 'travel', 'type': 'schedule', 'mode': 'train', 'origin': {'id': 5090174, 'name': 'New Hampshire, US'}, 'destination': {'id': 6091530, 'name': 'Nova Scotia, CA'}}), Example(input='flights from san juan puerto rico to jfk ny', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 4568127, 'name': 'San Juan, PR'}, 'destination': {'id': 5122732, 'name': 'John F. Kennedy International Airport, NY, US'}}), Example(input='seattle to portlad bike ride', semantics={'domain': 'travel', 'mode': 'bike', 'origin': {'id': 5809844, 'name': 'Seattle, WA, US'}, 'destination': {'id': 5746545, 'name': 'Portland, OR, US'}}), Example(input='cheap flight to charlotte', semantics={'domain': 'travel', 'mode': 'air', 'destination': {'id': 4460243, 'name': 'Charlotte, NC, US'}}), Example(input='boats from jacksonville fl to the bahamas', semantics={'domain': 'travel', 'mode': 'boat', 'origin': {'id': 4160021, 'name': 'Jacksonville, FL, US'}, 'destination': {'id': 3572887, 'name': 'Bahamas'}}), Example(input='is it legal to drive in florida using a cellular phone', semantics={'domain': 'other'}), Example(input='taking drivers license away from senior citizen texas driving', semantics={'domain': 'other'}), Example(input='best time to visit niagara falls', semantics={'domain': 'other'}), Example(input='airline tickers to monteray california fromn dc area', semantics={'domain': 'travel', 'mode': 'air', 'origin': {'id': 4140963, 'name': 'Washington, DC, US'}, 'destination': {'id': 5374361, 'name': 'Monterey, CA, US'}}), Example(input='bus service -detroit to chicago', semantics={'domain': 'travel', 'mode': 'bus', 'origin': {'id': 4990729, 'name': 'Detroit, MI, US'}, 'destination': {'id': 4887398, 'name': 'Chicago, IL, US'}}), Example(input='transportation from winston salem to raleigh durham', semantics={'domain': 'travel', 'origin': {'id': 4499612, 'name': 'Winston-Salem, NC, US'}, 'destination': {'id': 4487056, 'name': 'Raleigh-Durham International Airport, NC, US'}}), ]