instructions for hcat questions

fiboa/hcat-instructions.txt

@@ -0,0 +1,131 @@
+Many questions will be about specific crops. The following is the list of strings that will appear in the crop_type column:
+
+arable_crops, cereal, common_soft_wheat, winter_common_soft_wheat, spring_common_soft_wheat, unspecified_season_common_soft_wheat, durum_hard_wheat, winter_durum_hard_wheat, spring_durum_hard_wheat, unspecified_season_durum_hard_wheat, rye, winter_rye, spring_rye, unspecified_season_rye, barley, winter_barley, spring_barley, unspecified_season_barley, oats, winter_oats, spring_oats, unspecified_season_oats, grain_maize_corn_popcorn, unspecified_season_grain_maize_corn_popcorn, rice, unspecified_season_rice, triticale, winter_triticale, spring_triticale, unspecified_season_triticale, millet_sorghum, winter_millet_sorghum, spring_millet_sorghum, teff, unspecified_season_millet_sorghum, spelt, winter_spelt, spring_spelt, unspecified_season_spelt, meslin, winter_meslin, spring_meslin, unspecified_season_meslin, emmer, winter_emmer, spring_emmer, unspecified_season_emmer, einkorn, winter_einkorn, spring_einkorn, unspecified_season_einkorn, canary_seed_canaryseed, unspecified_season_canary_seed_canaryseed, unspecified_cereals, winter_unspecified_cereals, spring_unspecified_cereals, summer_unspecified_cereals, unspecified_season_unspecified_cereals, other_cereals, unspecified_season_other_cereals, legumes_dried_pulses_protein_crops, beans, chickpeas, esparsette_onobrychis, fenugreek, lentils, peas, sweet_lupins, unspecified_legumes_dried_pulses_protein_crops, other_dry_pulses, potatoes, sweet_potatoes, fodder_roots, industrial_nonfood_crops, tobacco, hops, cotton, rapeseed_rape, winter_rapeseed_rape, spring_rapeseed_rape, summer_rapeseed_rape, unspecified_season_rapeseed_rape, sunflower, poppy, winter_poppy, summer_poppy, flax_linseed, flax_linen, flax_linseed_oil, oilseed_crops, guizotia_abyssinica_nyger, hemp_cannabis, finola, fibre_crops, aromatic_medicinal_culinary_plants_spices_herbs, actaea_baneberry_christopher_herbs, alchemilla_ladys_mantle, anethum_dill, angelica, anise_aniseed, artemisia, basil, black_cumin, borage, calendula_marigold, caraway, catnip, chamomile, chervil, coriander, ericaceae_heather, galium_bedstraw, hibiscus, lavender_lavandula, lemon_balm_melissa, lovage_maggiplant, mints_peppermint, moldavian_dragonhead, nasturtiums, nettles, oregano, parsly, piper_pepper, polygonum, rosemary, rubia_tinctorum_common_madder, saffron_crocus_sativus, silver_comb, st_johns_wort, stachys_hedgenettle_chinese_artichoke, tarragon, thyme, valerian, yarrow, unspecified_aromatic_medicinal_culinary_plants_spices_herbs, other_aromatic_medicinal_culinary_plants_spices_herbs, marian_thistles, phacelia, camelina, onobrychis_sainfoins, other_industrial_crops, fresh_vegetables, flowers_ornamental_plants, adonis, anemones_windflowers, asters, begonias, bluebells, bulrush, burnet, carnation, chrysanthemum, cornflowers, corsican_hellebore, dahlia, daisy_daisies, dandelions, echinacea_sun_hat, edelweiss, fiddleneck_amsinckia, fuchsias, galega, gentians, gladiolus_gladioli, goldenrod, iris, isatis_tinctoria_woad, lilies, lotus, lunaria_honesty_silver, malva, milk_star, miscanthus_silvergrass, monstera_adansonii_eyelet, moonseed, narcissus_daffodil, peony_peonies, primrose, rhododendron, roses, rudbeckia_coneflowers, safflower, salsify, sanvitalia_procumbens, serradella, silene_catchfly, silphium_rosinweeds, snapdragons, stonecrop, tagetes, thimbles, tulips, viola, violets_pansies, zinnias, unspecified_flowers_ornamental_plants, other_flowers_ornamental_plants, plants_harvested_green, temporary_grass, poaceae_grasses, elymus, festuca_fescue, cocksfoot_catgrass, festulolium, lolium_ryegrass, setaria, sod_turf, switchgrass, timothy, legumes_harvested_green, alfalfa_lucerne, arachis, clover, melilot, vetches, unspecified_legumes_harvested_green, green_silo_maize, other_plants_harvested_green, arable_land_seed_seedlings, fallow_land_not_crop, kitchen_gardens, strawberries, cucurbits, cucumber_pickle, honeydew, melon, pumpkin_squash_gourd, watermelon, zucchini_courgette, pseudocereal, amaranth, buckwheat, quinoa, soy_soybeans, fennel, topinambur_jerusalem_artichoke, sage_chia, asparagus, brassicaceae_cruciferae, mustard, brassica_oleracea_cabbage, bok_choy_pak_choi, broccoli, brussels_sprouts, cauliflower, chinese_cabbage, collard_greens, gai_lan, kale, kohlrabi, red_cabbage, savoy_cabbage, white_cabbage, other_brassica_oleracea_cabbage, cress, horseradish, swede_rutabaga, alliums, chives, garlic, leek, onions, scallion, shallot, rhubarb, purslane, celery, celeriac, leaf_celery, aubergine_eggplant, artichoke, tomato, root_vegetables, arctium_burdock, beetroot_beets, carrots_daucus, mangelwurzel_fodder_beet, parsnips, radish, sugar_beet, turnips, unspecified_root_vegetables, capsicum, bell_pepper_paprika, chili_pepper, salads_lettuce_leaf_vegetables, chard, chicory_chicories, endive, iceberg, lambs_lettuce_rapunzel, rocket_arugula, sorrel, spinach, other_salads_lettuce_leaf_vegetables, other_arable_land_crops, pasture_meadow_grassland_grass, permanent_crops_perennial, orchards_fruits, amelanchier_serviceberry, apples, apricots, cherry_cherries, feijoa, fig, kiwi, medlar_loquat, nectarine, pawpaw, peach, pears, plums, pomegranate, quinces, unspecified_orchards_fruits, berries_berry_species, aronia_chokeberries, blackberry, blackcurrant_cassis, blueberry, cranberry, currants, gooseberry_gooseberries_cranberries, hippophae_sea_buckthorns_seaberry, jostaberry, raspberry_raspberries, redcurrant, rose_hip_rosehip, rowan_rowanberries, tayberry, unspecified_berries_berry_species, nuts, almond, hazelnuts_hazel, pecan, pistachio, sweet_chestnuts, walnuts, citrus_plantations, olive_plantations, olives_for_oil_production, table_olives, vineyards_wine_vine_rebland_grapes, nurseries_nursery, shrubberries_shrubs, azaleas, chaenomeles_cathayensis, crataegus_hawthorn, elder_elderberry, honeysuckle, ricinus_castor, wire_bush, ginko, avocado, legumes_from_trees, carob, mesquite, tamarind, unspecified_permanent_crops, other_permanent_crops_plantations, mushrooms_energy_genetically_modified_crops, energy_crops, genetically_modified_crops, igniscum_candy, sida_virginia_mallow, truffle, other_mushrooms_energy_crops_genetically_modified_crops, greenhouse_foil_film, tree_wood_forest, afforestation_reforestation, aspen, birch, dogwood_cornus, eucalyptus, oak, populus, willows_osiers, unspecified_tree_wood_forest, other_tree_wood_forest, peat_turf, unmaintained, not_known_and_other
+
+You should take any crop name the user mentions and convert it to one of the strings in the list above. Always query on the crop_type column, using one or more of the above, never query on 'crop' column.
+
+There are many 'groups' of crops that users may ask about, that map to several categories of the above. For these the where clause should use a crop_type IN with the list of matching values as listed below. Be sure to always escape each name with single quotes. 
+
+If a user asks for 'common soft wheat' or similar, then query on:
+common_soft_wheat, winter_common_soft_wheat, spring_common_soft_wheat, unspecified_season_common_soft_wheat.
+
+If a user asks for 'durum hard wheat' or similar, then query on:
+durum_hard_wheat, winter_durum_hard_wheat, spring_durum_hard_wheat, unspecified_season_durum_hard_wheat.
+
+If a user asks for wheat or similar then query on:
+common_soft_wheat, winter_common_soft_wheat, spring_common_soft_wheat, unspecified_season_common_soft_wheat, durum_hard_wheat, winter_durum_hard_wheat, spring_durum_hard_wheat, unspecified_season_durum_hard_wheat.
+
+
+If a user asks for 'rye' or similar, then query on:
+rye, winter_rye, spring_rye, unspecified_season_rye.
+
+If a user asks for 'barley' or similar, then query on:
+barley, winter_barley, spring_barley, unspecified_season_barley.
+
+If a user asks for 'oats' or similar, then query on:
+oats, winter_oats, spring_oats, unspecified_season_oats.
+
+If a user asks for 'triticale' or similar, then query on:
+triticale, winter_triticale, spring_triticale, unspecified_season_triticale.
+
+If a user asks for 'millet' or 'sorghum' or similar, then query on:
+millet_sorghum, winter_millet_sorghum, spring_millet_sorghum, teff, unspecified_season_millet_sorghum.
+
+If a user asks for 'spelt' or similar, then query on:
+spelt, winter_spelt, spring_spelt, unspecified_season_spelt.
+
+If a user asks for 'meslin' or similar, then query on:
+meslin, winter_meslin, spring_meslin, unspecified_season_meslin.
+
+If a user asks for 'emmer' or similar, then query on:
+emmer, winter_emmer, spring_emmer, unspecified_season_emmer.
+
+If a user asks for 'einkorn' or similar, then query on:
+einkorn, winter_einkorn, spring_einkorn, unspecified_season_einkorn.
+
+If a user asks for 'unspecified cereals' or similar, then query on:
+unspecified_cereals, winter_unspecified_cereals, spring_unspecified_cereals, summer_unspecified_cereals, unspecified_season_unspecified_cereals.
+
+If a user asks for 'rapeseed' or 'rape' or similar, then query on:
+rapeseed_rape, winter_rapeseed_rape, spring_rapeseed_rape, summer_rapeseed_rape, unspecified_season_rapeseed_rape.
+
+If a user asks for 'poppy' or similar, then query on:
+poppy, winter_poppy, summer_poppy.
+
+If a user asks for 'flax' or 'linseed' or similar, then query on:
+flax_linseed, flax_linen, flax_linseed_oil.
+
+If a user asks for 'aromatic medicinal plants', 'culinary plants', 'spices', 'herbs' or similar, then query on:
+aromatic_medicinal_culinary_plants_spices_herbs, actaea_baneberry_christopher_herbs, alchemilla_ladys_mantle, anethum_dill, angelica, anise_aniseed, artemisia, basil, black_cumin, borage, calendula_marigold, caraway, catnip, chamomile, chervil, coriander, ericaceae_heather, galium_bedstraw, hibiscus, lavender_lavandula, lemon_balm_melissa, lovage_maggiplant, mints_peppermint, moldavian_dragonhead, nasturtiums, nettles, oregano, parsly, piper_pepper, polygonum, rosemary, rubia_tinctorum_common_madder, saffron_crocus_sativus, silver_comb, st_johns_wort, stachys_hedgenettle_chinese_artichoke, tarragon, thyme, valerian, yarrow, unspecified_aromatic_medicinal_culinary_plants_spices_herbs, other_aromatic_medicinal_culinary_plants_spices_herbs.
+
+If a user asks for 'poaceae grasses' or similar, then query on:
+poaceae_grasses, elymus, festuca_fescue, cocksfoot_catgrass, festulolium, lolium_ryegrass, setaria, sod_turf, switchgrass, timothy.
+
+If a user asks for 'legumes harvested green' or similar, then query on:
+legumes_harvested_green, alfalfa_lucerne, arachis, clover, melilot, vetches, unspecified_legumes_harvested_green.
+
+If a user asks for 'cucurbits' or similar, then query on:
+cucurbits, cucumber_pickle, honeydew, melon, pumpkin_squash_gourd, watermelon, zucchini_courgette.
+
+If a user asks for 'brassicaceae' or 'cruciferae' or similar, then query on:
+brassicaceae_cruciferae, mustard, brassica_oleracea_cabbage, bok_choy_pak_choi, broccoli, brussels_sprouts, cauliflower, chinese_cabbage, collard_greens, gai_lan, kale, kohlrabi, red_cabbage, savoy_cabbage, white_cabbage, other_brassica_oleracea_cabbage, cress, horseradish, swede_rutabaga.
+
+If a user asks for 'brassica oleracea cabbage' or similar, then query on:
+brassica_oleracea_cabbage, bok_choy_pak_choi, broccoli, brussels_sprouts, cauliflower, chinese_cabbage, collard_greens, gai_lan, kale, kohlrabi, red_cabbage, savoy_cabbage, white_cabbage, other_brassica_oleracea_cabbage.
+
+If a user asks for 'alliums' or similar, then query on:
+alliums, chives, garlic, leek, onions, scallion, shallot.
+
+If a user asks for 'root vegetables' or similar, then query on:
+root_vegetables, arctium_burdock, beetroot_beets, carrots_daucus, mangelwurzel_fodder_beet, parsnips, radish, sugar_beet, turnips, unspecified_root_vegetables.
+
+If a user asks for 'capsicum' or similar, then query on:
+capsicum, bell_pepper_paprika, chili_pepper.
+
+If a user asks for 'salads', 'lettuce', 'leaf vegetables' or similar, then query on:
+salads_lettuce_leaf_vegetables, chard, chicory_chicories, endive, iceberg, lambs_lettuce_rapunzel, rocket_arugula, sorrel, spinach, other_salads_lettuce_leaf_vegetables.
+
+If a user asks for 'berries' or similar, then query on:
+berries_berry_species, aronia_chokeberries, blackberry, blackcurrant_cassis, blueberry, cranberry, currants, gooseberry_gooseberries_cranberries, hippophae_sea_buckthorns_seaberry, jostaberry, raspberry_raspberries, redcurrant, rose_hip_rosehip, rowan_rowanberries, tayberry, unspecified_berries_berry_species.
+
+If a user asks for 'nuts' or similar, then query on:
+nuts, almond, hazelnuts_hazel, pecan, pistachio, sweet_chestnuts, walnuts.
+
+If a user asks for 'olive plantations' or similar, then query on:
+olive_plantations, olives_for_oil_production, table_olives.
+
+If a user asks for 'permanent crops', 'perennial crops' or similar, then query on:
+permanent_crops_perennial, orchards_fruits, amelanchier_serviceberry, apples, apricots, cherry_cherries, feijoa, fig, kiwi, medlar_loquat, nectarine, pawpaw, peach, pears, plums, pomegranate, quinces, unspecified_orchards_fruits, berries_berry_species (list all berries as in mapping 28), nuts (list all nuts as in mapping 29), citrus_plantations, olive_plantations (list olive codes as in mapping 30), vineyards_wine_vine_rebland_grapes, nurseries_nursery, shrubberries_shrubs, azaleas, chaenomeles_cathayensis, crataegus_hawthorn, elder_elderberry, honeysuckle, ricinus_castor, wire_bush, ginko, avocado, legumes_from_trees, carob, mesquite, tamarind, unspecified_permanent_crops, other_permanent_crops_plantations.
+
+If a user asks for 'flowers', 'ornamental plants' or similar, then query on:
+flowers_ornamental_plants, adonis, anemones_windflowers, asters, begonias, bluebells, bulrush, burnet, carnation, chrysanthemum, cornflowers, corsican_hellebore, dahlia, daisy_daisies, dandelions, echinacea_sun_hat, edelweiss, fiddleneck_amsinckia, fuchsias, galega, gentians, gladiolus_gladioli, goldenrod, iris, isatis_tinctoria_woad, lilies, lotus, lunaria_honesty_silver, malva, milk_star, miscanthus_silvergrass, monstera_adansonii_eyelet, moonseed, narcissus_daffodil, peony_peonies, primrose, rhododendron, roses, rudbeckia_coneflowers, safflower, salsify, sanvitalia_procumbens, serradella, silene_catchfly, silphium_rosinweeds, snapdragons, stonecrop, tagetes, thimbles, tulips, viola, violets_pansies, zinnias, unspecified_flowers_ornamental_plants, other_flowers_ornamental_plants.
+
+If a user asks for 'tree wood forest', 'forest' or similar, then query on:
+tree_wood_forest, afforestation_reforestation, aspen, birch, dogwood_cornus, eucalyptus, oak, populus, willows_osiers, unspecified_tree_wood_forest, other_tree_wood_forest.
+
+If a user asks for 'mushrooms', 'energy crops', 'genetically modified crops' or similar, then query on:
+mushrooms_energy_genetically_modified_crops, energy_crops, genetically_modified_crops, igniscum_candy, sida_virginia_mallow, truffle, other_mushrooms_energy_crops_genetically_modified_crops.
+
+If a user asks for 'unmaintained land' or similar, then query on:
+unmaintained.
+
+If a user asks for 'unknown crops', 'other crops' or similar, then query on:
+not_known_and_other.
+
+If a user asks for 'corn', 'maize' or similar, then query on:
+grain_maize_corn_popcorn, unspecified_season_grain_maize_corn_popcorn.
+
+If a user asks for 'rice' or similar, then query on:
+rice, unspecified_season_rice.
+
+If a user asks for 'canary seed', 'canaryseed' or similar, then query on:
+canary_seed_canaryseed, unspecified_season_canary_seed_canaryseed.
+
+If a user asks for 'other cereals' or similar, then query on:
+other_cereals, unspecified_season_other_cereals.
+
+If a user asks for 'arable crops' or similar, then query on:
+arable_crops, cereal, common_soft_wheat, winter_common_soft_wheat, spring_common_soft_wheat, unspecified_season_common_soft_wheat, durum_hard_wheat, winter_durum_hard_wheat, spring_durum_hard_wheat, unspecified_season_durum_hard_wheat, rye, winter_rye, spring_rye, unspecified_season_rye, barley, winter_barley, spring_barley, unspecified_season_barley, oats, winter_oats, spring_oats, unspecified_season_oats, grain_maize_corn_popcorn, unspecified_season_grain_maize_corn_popcorn, rice, unspecified_season_rice, triticale, winter_triticale, spring_triticale, unspecified_season_triticale, millet_sorghum, winter_millet_sorghum, spring_millet_sorghum, teff, unspecified_season_millet_sorghum, spelt, winter_spelt, spring_spelt, unspecified_season_spelt, meslin, winter_meslin, spring_meslin, unspecified_season_meslin, emmer, winter_emmer, spring_emmer, unspecified_season_emmer, einkorn, winter_einkorn, spring_einkorn, unspecified_season_einkorn, canary_seed_canaryseed, unspecified_season_canary_seed_canaryseed, unspecified_cereals, winter_unspecified_cereals, spring_unspecified_cereals, summer_unspecified_cereals, unspecified_season_unspecified_cereals, other_cereals, unspecified_season_other_cereals, legumes_dried_pulses_protein_crops, beans, chickpeas, esparsette_onobrychis, fenugreek, lentils, peas, sweet_lupins, unspecified_legumes_dried_pulses_protein_crops, other_dry_pulses, potatoes, sweet_potatoes, fodder_roots, industrial_nonfood_crops, tobacco, hops, cotton, rapeseed_rape, winter_rapeseed_rape, spring_rapeseed_rape, summer_rapeseed_rape, unspecified_season_rapeseed_rape, sunflower, poppy, winter_poppy, summer_poppy, flax_linseed, flax_linen, flax_linseed_oil, oilseed_crops, guizotia_abyssinica_nyger, hemp_cannabis, finola, fibre_crops, aromatic_medicinal_culinary_plants_spices_herbs, actaea_baneberry_christopher_herbs, alchemilla_ladys_mantle, anethum_dill, angelica, anise_aniseed, artemisia, basil, black_cumin, borage, calendula_marigold, caraway, catnip, chamomile, chervil, coriander, ericaceae_heather, galium_bedstraw, hibiscus, lavender_lavandula, lemon_balm_melissa, lovage_maggiplant, mints_peppermint, moldavian_dragonhead, nasturtiums, nettles, oregano, parsly, piper_pepper, polygonum, rosemary, rubia_tinctorum_common_madder, saffron_crocus_sativus, silver_comb, st_johns_wort, stachys_hedgenettle_chinese_artichoke, tarragon, thyme, valerian, yarrow, unspecified_aromatic_medicinal_culinary_plants_spices_herbs, other_aromatic_medicinal_culinary_plants_spices_herbs, marian_thistles, phacelia, camelina, onobrychis_sainfoins, other_industrial_crops, fresh_vegetables, flowers_ornamental_plants, adonis, anemones_windflowers, asters, begonias, bluebells, bulrush, burnet, carnation, chrysanthemum, cornflowers, corsican_hellebore, dahlia, daisy_daisies, dandelions, echinacea_sun_hat, edelweiss, fiddleneck_amsinckia, fuchsias, galega, gentians, gladiolus_gladioli, goldenrod, iris, isatis_tinctoria_woad, lilies, lotus, lunaria_honesty_silver, malva, milk_star, miscanthus_silvergrass, monstera_adansonii_eyelet, moonseed, narcissus_daffodil, peony_peonies, primrose, rhododendron, roses, rudbeckia_coneflowers, safflower, salsify, sanvitalia_procumbens, serradella, silene_catchfly, silphium_rosinweeds, snapdragons, stonecrop, tagetes, thimbles, tulips, viola, violets_pansies, zinnias, unspecified_flowers_ornamental_plants, other_flowers_ornamental_plants, plants_harvested_green, temporary_grass, poaceae_grasses, elymus, festuca_fescue, cocksfoot_catgrass, festulolium, lolium_ryegrass, setaria, sod_turf, switchgrass, timothy, legumes_harvested_green, alfalfa_lucerne, arachis, clover, melilot, vetches, unspecified_legumes_harvested_green, green_silo_maize, other_plants_harvested_green, arable_land_seed_seedlings, fallow_land_not_crop, kitchen_gardens, strawberries, cucurbits, cucumber_pickle, honeydew, melon, pumpkin_squash_gourd, watermelon, zucchini_courgette, pseudocereal, amaranth, buckwheat, quinoa, soy_soybeans, fennel, topinambur_jerusalem_artichoke, sage_chia, asparagus, brassicaceae_cruciferae, mustard, brassica_oleracea_cabbage, bok_choy_pak_choi, broccoli, brussels_sprouts, cauliflower, chinese_cabbage, collard_greens, gai_lan, kale, kohlrabi, red_cabbage, savoy_cabbage, white_cabbage, other_brassica_oleracea_cabbage, cress, horseradish, swede_rutabaga, alliums, chives, garlic, leek, onions, scallion, shallot, rhubarb, purslane, celery, celeriac, leaf_celery, aubergine_eggplant, artichoke, tomato, root_vegetables, arctium_burdock, beetroot_beets, carrots_daucus, mangelwurzel_fodder_beet, parsnips, radish, sugar_beet, turnips, unspecified_root_vegetables, capsicum, bell_pepper_paprika, chili_pepper, salads_lettuce_leaf_vegetables, chard, chicory_chicories, endive, iceberg, lambs_lettuce_rapunzel, rocket_arugula, sorrel, spinach, other_salads_lettuce_leaf_vegetables, other_arable_land_crops.
+
+If a user asks for 'cereal' or similar, then query on:
+cereal, common_soft_wheat, winter_common_soft_wheat, spring_common_soft_wheat, unspecified_season_common_soft_wheat, durum_hard_wheat, winter_durum_hard_wheat, spring_durum_hard_wheat, unspecified_season_durum_hard_wheat, rye, winter_rye, spring_rye, unspecified_season_rye, barley, winter_barley, spring_barley, unspecified_season_barley, oats, winter_oats, spring_oats, unspecified_season_oats, grain_maize_corn_popcorn, unspecified_season_grain_maize_corn_popcorn, rice, unspecified_season_rice, triticale, winter_triticale, spring_triticale, unspecified_season_triticale, millet_sorghum, winter_millet_sorghum, spring_millet_sorghum, teff, unspecified_season_millet_sorghum, spelt, winter_spelt, spring_spelt, unspecified_season_spelt, meslin, winter_meslin, spring_meslin, unspecified_season_meslin, emmer, winter_emmer, spring_emmer, unspecified_season_emmer, einkorn, winter_einkorn, spring_einkorn, unspecified_season_einkorn, canary_seed_canaryseed, unspecified_season_canary_seed_canaryseed, unspecified_cereals, winter_unspecified_cereals, spring_unspecified_cereals, summer_unspecified_cereals, unspecified_season_unspecified_cereals, other_cereals, unspecified_season_other_cereals.