metadata
tags:
- bertopic
library_name: bertopic
pipeline_tag: text-classification
NewBERTopicCEEW_lemmatize_nocommonwords
This is a BERTopic model. BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
Usage
To use this model, please install BERTopic:
pip install -U bertopic
You can use the model as follows:
from bertopic import BERTopic
topic_model = BERTopic.load("VATSAL1729/NewBERTopicCEEW_lemmatize_nocommonwords")
topic_model.get_topic_info()
Topic overview
- Number of topics: 469
- Number of training documents: 92948
Click here for an overview of all topics.
| Topic ID | Topic Keywords | Topic Frequency | Label |
|---|---|---|---|
| -1 | encourage - fall - tube - excessive - hook | 42 | -1_encourage_fall_tube_excessive |
| 0 | - - - - | 13603 | 0____ |
| 1 | butter - corn - rice - blending - protein | 43102 | 1_butter_corn_rice_blending |
| 2 | weave - basket - strip - twig - craft | 458 | 2_weave_basket_strip_twig |
| 3 | chisel - hammer - wooden - saw - smoothly | 314 | 3_chisel_hammer_wooden_saw |
| 4 | glassware - pot - utensil - dish - plate | 292 | 4_glassware_pot_utensil_dish |
| 5 | dirt - wipe - smudge - furniture - brush | 266 | 5_dirt_wipe_smudge_furniture |
| 6 | travel - supported - luggage - itinerant - traveling | 230 | 6_travel_supported_luggage_itinerant |
| 7 | suggestion - suggest - recommendation - recommend - circle | 223 | 7_suggestion_suggest_recommendation_recommend |
| 8 | idle - minimise - riot - disruption - lagging | 213 | 8_idle_minimise_riot_disruption |
| 9 | explosive - blast - munition - rake - stopping | 185 | 9_explosive_blast_munition_rake |
| 10 | bolt - coil - screw - fast - collar | 179 | 10_bolt_coil_screw_fast |
| 11 | sorting - sort - discard - inspecting - sorted | 174 | 11_sorting_sort_discard_inspecting |
| 12 | baker - cake - pantry - artisan - decoration | 173 | 12_baker_cake_pantry_artisan |
| 13 | oxygen - torch - thermal - arc - ame | 171 | 13_oxygen_torch_thermal_arc |
| 14 | grid - module - interconnection - terminal - parallel | 166 | 14_grid_module_interconnection_terminal |
| 15 | pulley - suspension - pointing - gearbox - rake | 163 | 15_pulley_suspension_pointing_gearbox |
| 16 | proportion - additional - addition - characteristic - pitch | 160 | 16_proportion_additional_addition_characteristic |
| 17 | instrumentation - frequency - sound - abnormal - fro | 158 | 17_instrumentation_frequency_sound_abnormal |
| 18 | forecast - schelling - prediction - script - investigate | 154 | 18_forecast_schelling_prediction_script |
| 19 | shield - entire - taste - knee - neck | 150 | 19_shield_entire_taste_knee |
| 20 | cruel - seizing - passage - damaging - exhausted | 148 | 20_cruel_seizing_passage_damaging |
| 21 | international - national - framework - reasoning - comparing | 146 | 21_international_national_framework_reasoning |
| 22 | refrigeration - freeze - evaporation - coil - condensed | 144 | 22_refrigeration_freeze_evaporation_coil |
| 23 | accuracy - precision - combined - depending - precise | 143 | 23_accuracy_precision_combined_depending |
| 24 | welcome - home - visitor - visit - extent | 141 | 24_welcome_home_visitor_visit |
| 25 | drinking - drink - tea - serve - provision | 139 | 25_drinking_drink_tea_serve |
| 26 | dye - coloring - grass - coat - twig | 137 | 26_dye_coloring_grass_coat |
| 27 | insurance - - - - | 133 | 27_insurance___ |
| 28 | theater - entertainment - theme - attractive - cultural | 133 | 28_theater_entertainment_theme_attractive |
| 29 | sketch - draw - blueprint - image - trace | 130 | 29_sketch_draw_blueprint_image |
| 30 | dusting - coloured - teeth - wearing - clothes | 130 | 30_dusting_coloured_teeth_wearing |
| 31 | winter - rapid - bow - pad - waterproof | 130 | 31_winter_rapid_bow_pad |
| 32 | worksite - chip - extent - balancing - | 129 | 32_worksite_chip_extent_balancing |
| 33 | match - recorded - history - look - suitably | 128 | 33_match_recorded_history_look |
| 34 | satisfaction - addressed - discontent - combined - half | 127 | 34_satisfaction_addressed_discontent_combined |
| 35 | rope - helmet - rock - course - sings | 127 | 35_rope_helmet_rock_course |
| 36 | adherence - designing - forward - actual - designer | 127 | 36_adherence_designing_forward_actual |
| 37 | adapt - climate - class - study - | 126 | 37_adapt_climate_class_study |
| 38 | expedition - leader - tree - porter - oozing | 126 | 38_expedition_leader_tree_porter |
| 39 | abnormality - anomaly - attained - recruit - gradually | 124 | 39_abnormality_anomaly_attained_recruit |
| 40 | apron - covering - waterproof - dressing - coat | 124 | 40_apron_covering_waterproof_dressing |
| 41 | ask - helper - pool - bearer - enquire | 124 | 41_ask_helper_pool_bearer |
| 42 | implication - encountered - description - consequence - preliminary | 124 | 42_implication_encountered_description_consequence |
| 43 | house - remaining - map - region - surrounding | 122 | 43_house_remaining_map_region |
| 44 | thickness - width - turning - sliding - shaping | 122 | 44_thickness_width_turning_sliding |
| 45 | sickness - giving - organic - improper - attention | 120 | 45_sickness_giving_organic_improper |
| 46 | anticipated - expected - equivalent - typical - want | 119 | 46_anticipated_expected_equivalent_typical |
| 47 | quotation - compile - treating - - | 119 | 47_quotation_compile_treating_ |
| 48 | equality - abnormality - sickness - remain - home | 119 | 48_equality_abnormality_sickness_remain |
| 49 | rubber - noble - nut - intake - parking | 118 | 49_rubber_noble_nut_intake |
| 50 | consistent - consistently - bulk - consistency - tormented | 117 | 50_consistent_consistently_bulk_consistency |
| 51 | accommodation - booking - public - paid - allot | 117 | 51_accommodation_booking_public_paid |
| 52 | autoconer - mind - automobile - telematics - reliability | 117 | 52_autoconer_mind_automobile_telematics |
| 53 | cash - tall - exchange - acquire - cum | 116 | 53_cash_tall_exchange_acquire |
| 54 | family - ache - knee - break - | 114 | 54_family_ache_knee_break |
| 55 | exchange - culture - vat - blended - plate | 114 | 55_exchange_culture_vat_blended |
| 56 | optical - detection - detect - detector - man | 114 | 56_optical_detection_detect_detector |
| 57 | lamp - methode - ame - rake - viewing | 113 | 57_lamp_methode_ame_rake |
| 58 | participant - session - alternative - trained - engagement | 113 | 58_participant_session_alternative_trained |
| 59 | extruded - die - stamped - kerseys - lowering | 113 | 59_extruded_die_stamped_kerseys |
| 60 | repeat - printed - convert - modeling - copy | 113 | 60_repeat_printed_convert_modeling |
| 61 | vanity - accepted - peri - associate - print | 112 | 61_vanity_accepted_peri_associate |
| 62 | liable - expenditure - liability - property - lease | 112 | 62_liable_expenditure_liability_property |
| 63 | grinder - grind - practical - granule - showcase | 111 | 63_grinder_grind_practical_granule |
| 64 | relating - pertaining - reported - sense - operative | 111 | 64_relating_pertaining_reported_sense |
| 65 | painting - brush - painted - hanging - brushing | 110 | 65_painting_brush_painted_hanging |
| 66 | aseptic - treated - ash - rise - evaporation | 110 | 66_aseptic_treated_ash_rise |
| 67 | moral - dark - marked - loaded - grass | 110 | 67_moral_dark_marked_loaded |
| 68 | today - opened - poor - shelf - rail | 110 | 68_today_opened_poor_shelf |
| 69 | selling - margin - sold - buying - paid | 110 | 69_selling_margin_sold_buying |
| 70 | axillary - rail - siege - blockade - friction | 110 | 70_axillary_rail_siege_blockade |
| 71 | shut - closure - closing - closed - fetch | 109 | 71_shut_closure_closing_closed |
| 72 | successful - showcase - study - picture - schematic | 109 | 72_successful_showcase_study_picture |
| 73 | engage - formality - attention - gather - engaging | 109 | 73_engage_formality_attention_gather |
| 74 | maintains - disruption - intake - coordination - realistic | 109 | 74_maintains_disruption_intake_coordination |
| 75 | resolved - resolution - inter - achieving - informed | 109 | 75_resolved_resolution_inter_achieving |
| 76 | embroidery - stitch - traditional - motif - indian | 109 | 76_embroidery_stitch_traditional_motif |
| 77 | screen - magnetic - separated - density - sitting | 108 | 77_screen_magnetic_separated_density |
| 78 | claim - insurance - took - selecting - typical | 107 | 78_claim_insurance_took_selecting |
| 79 | extraction - extract - city - extracted - logging | 107 | 79_extraction_extract_city_extracted |
| 80 | linen - dirty - par - stained - fresh | 107 | 80_linen_dirty_par_stained |
| 81 | recycle - big - decorative - rubber - marking | 107 | 81_recycle_big_decorative_rubber |
| 82 | regent - particular - stability - exposure - guidance | 107 | 82_regent_particular_stability_exposure |
| 83 | - - - - | 106 | 83____ |
| 84 | foundation - structural - mounting - civil - pile | 106 | 84_foundation_structural_mounting_civil |
| 85 | dismantling - transporting - fork - lowered - moist | 105 | 85_dismantling_transporting_fork_lowered |
| 86 | aroma - concentrate - evaluation - harmful - sensory | 105 | 86_aroma_concentrate_evaluation_harmful |
| 87 | executive - menu - appraise - ordering - directed | 105 | 87_executive_menu_appraise_ordering |
| 88 | compression - compressed - hole - oppressor - condensed | 105 | 88_compression_compressed_hole_oppressor |
| 89 | electrode - plasma - arc - force - tightness | 104 | 89_electrode_plasma_arc_force |
| 90 | repaired - remarked - repairing - flag - segregating | 104 | 90_repaired_remarked_repairing_flag |
| 91 | coordinating - tender - representative - analyzing - engagement | 104 | 91_coordinating_tender_representative_analyzing |
| 92 | stimulation - commercial - study - park - modeling | 104 | 92_stimulation_commercial_study_park |
| 93 | furnace - heating - boiler - melting - approximately | 104 | 93_furnace_heating_boiler_melting |
| 94 | troubleshooting - pollution - live - mob - approximately | 103 | 94_troubleshooting_pollution_live_mob |
| 95 | isolated - negative - priority - adequately - ache | 103 | 95_isolated_negative_priority_adequately |
| 96 | wind - turbine - proposed - conventional - hut | 102 | 96_wind_turbine_proposed_conventional |
| 97 | bias - conversion - farmer - cow - bale | 101 | 97_bias_conversion_farmer_cow |
| 98 | evidence - criterion - evaluation - competence - reviewing | 101 | 98_evidence_criterion_evaluation_competence |
| 99 | breakage - break - cracking - crack - wrong | 101 | 99_breakage_break_cracking_crack |
| 100 | blocked - changing - substance - class - highlight | 100 | 100_blocked_changing_substance_class |
| 101 | rooftop - dam - mounted - suitability - leveled | 99 | 101_rooftop_dam_mounted_suitability |
| 102 | technician - specialist - anddemonstrate - session - celebrated | 98 | 102_technician_specialist_anddemonstrate_session |
| 103 | unloading - unload - papa - watching - indicated | 98 | 103_unloading_unload_papa_watching |
| 104 | andros - disaster - undertaking - biodegradable - james | 97 | 104_andros_disaster_undertaking_biodegradable |
| 105 | natural - insect - alert - animal - raise | 96 | 105_natural_insect_alert_animal |
| 106 | strong - strength - weakness - capability - appealing | 95 | 106_strong_strength_weakness_capability |
| 107 | underground - locate - extended - shifting - foundation | 94 | 107_underground_locate_extended_shifting |
| 108 | economic - bending - aesthetic - climate - economy | 94 | 108_economic_bending_aesthetic_climate |
| 109 | placement - organised - placing - organizing - organizer | 92 | 109_placement_organised_placing_organizing |
| 110 | procured - ration - provision - helper - multi | 92 | 110_procured_ration_provision_helper |
| 111 | shortage - undesirable - fed - lack - unforeseen | 92 | 111_shortage_undesirable_fed_lack |
| 112 | recto - early - earliest - occurs - harder | 92 | 112_recto_early_earliest_occurs |
| 113 | week - gape - locate - normal - started | 91 | 113_week_gape_locate_normal |
| 114 | jacket - stir - pure - admit - burned | 91 | 114_jacket_stir_pure_admit |
| 115 | rodent - requiring - touch - extent - infestation | 91 | 115_rodent_requiring_touch_extent |
| 116 | ulm - saw - covering - say - outline | 90 | 116_ulm_saw_covering_say |
| 117 | unattended - visible - treat - - | 90 | 117_unattended_visible_treat_ |
| 118 | toxic - highly - treat - delivered - | 90 | 118_toxic_highly_treat_delivered |
| 119 | recall - exist - consumer - rejected - rejection | 90 | 119_recall_exist_consumer_rejected |
| 120 | debris - dump - season - accumulation - rise | 89 | 120_debris_dump_season_accumulation |
| 121 | conform - conforming - conformity - city - frequent | 89 | 121_conform_conforming_conformity_city |
| 122 | raising - insight - specialized - buying - attending | 89 | 122_raising_insight_specialized_buying |
| 123 | toilet - fauces - oozing - replenished - shower | 89 | 123_toilet_fauces_oozing_replenished |
| 124 | subordinate - - - - | 89 | 124_subordinate___ |
| 125 | - - - - | 88 | 125____ |
| 126 | requisite - navigation - laying - achieved - requiredfor | 88 | 126_requisite_navigation_laying_achieved |
| 127 | exhaust - exist - remain - waking - concentration | 88 | 127_exhaust_exist_remain_waking |
| 128 | cracked - glassware - suit - nerve - washed | 87 | 128_cracked_glassware_suit_nerve |
| 129 | carrot - creeping - peeling - bringing - autoconer | 87 | 129_carrot_creeping_peeling_bringing |
| 130 | handed - engagement - connect - camp - removing | 87 | 130_handed_engagement_connect_camp |
| 131 | andspeci - andrew - utilised - release - trouble | 87 | 131_andspeci_andrew_utilised_release |
| 132 | occurrence - combination - intervention - harmful - excess | 86 | 132_occurrence_combination_intervention_harmful |
| 133 | focus - fig - themachine - institutional - prospective | 86 | 133_focus_fig_themachine_institutional |
| 134 | merit - executive - subordinate - designed - delivered | 86 | 134_merit_executive_subordinate_designed |
| 135 | achievement - achieving - stay - recognized - achieved | 86 | 135_achievement_achieving_stay_recognized |
| 136 | leadership - recruit - leader - bossing - purchasing | 86 | 136_leadership_recruit_leader_bossing |
| 137 | roller - tapping - rolling - tip - steel | 86 | 137_roller_tapping_rolling_tip |
| 138 | cultural - diverse - unique - mind - interactive | 86 | 138_cultural_diverse_unique_mind |
| 139 | consult - recommend - encountered - developing - | 85 | 139_consult_recommend_encountered_developing |
| 140 | video - picture - photograph - brand - enhance | 85 | 140_video_picture_photograph_brand |
| 141 | knife - blade - extruded - opened - containing | 85 | 141_knife_blade_extruded_opened |
| 142 | - - - - | 85 | 142____ |
| 143 | engineer - supervision - specialist - analyzing - resolved | 85 | 143_engineer_supervision_specialist_analyzing |
| 144 | easily - easy - ease - shall - | 85 | 144_easily_easy_ease_shall |
| 145 | formal - writing - - - | 85 | 145_formal_writing__ |
| 146 | gather - failed - - - | 84 | 146_gather_failed__ |
| 147 | recovered - decorating - venue - disposed - explosive | 82 | 147_recovered_decorating_venue_disposed |
| 148 | human - son - boy - man - oneself | 82 | 148_human_son_boy_man |
| 149 | secondary - primary - interactive - tertiary - mr | 82 | 149_secondary_primary_interactive_tertiary |
| 150 | managing - ladder - applying - leaning - asset | 82 | 150_managing_ladder_applying_leaning |
| 151 | sealing - mechanic - seal - earth - wet | 81 | 151_sealing_mechanic_seal_earth |
| 152 | diameter - origin - square - depth - treating | 81 | 152_diameter_origin_square_depth |
| 153 | selected - usually - frequently - chosen - highly | 81 | 153_selected_usually_frequently_chosen |
| 154 | attach - discipline - initiate - medal - suspension | 80 | 154_attach_discipline_initiate_medal |
| 155 | strategy - strike - acted - scenario - strategic | 80 | 155_strategy_strike_acted_scenario |
| 156 | transferring - alert - adjusting - wet - attention | 80 | 156_transferring_alert_adjusting_wet |
| 157 | combed - lap - comb - carrier - mount | 80 | 157_combed_lap_comb_carrier |
| 158 | teeth - ash - pool - visibility - sprinkled | 80 | 158_teeth_ash_pool_visibility |
| 159 | doctor - prompt - frothy - appointed - center | 80 | 159_doctor_prompt_frothy_appointed |
| 160 | placed - neutral - - - | 80 | 160_placed_neutral__ |
| 161 | - - - - | 80 | 161____ |
| 162 | reaction - separately - shall - west - leaning | 79 | 162_reaction_separately_shall_west |
| 163 | protected - - - - | 79 | 163_protected___ |
| 164 | biological - depict - origin - detect - characteristic | 79 | 164_biological_depict_origin_detect |
| 165 | putting - candle - pillage - arson - shielding | 78 | 165_putting_candle_pillage_arson |
| 166 | doubt - possessing - - - | 78 | 166_doubt_possessing__ |
| 167 | consumer - education - discount - exchange - added | 78 | 167_consumer_education_discount_exchange |
| 168 | discussion - expert - initial - phase - adopted | 77 | 168_discussion_expert_initial_phase |
| 169 | voice - audible - closing - statement - delivered | 77 | 169_voice_audible_closing_statement |
| 170 | cop - organised - magazine - patrol - pool | 77 | 170_cop_organised_magazine_patrol |
| 171 | accepted - - - - | 77 | 171_accepted___ |
| 172 | communicated - took - creating - riot - look | 77 | 172_communicated_took_creating_riot |
| 173 | improved - cook - portable - leg - advantage | 76 | 173_improved_cook_portable_leg |
| 174 | construction - building - play - construct - civil | 76 | 174_construction_building_play_construct |
| 175 | exile - adapt - auxiliary - peak - trough | 76 | 175_exile_adapt_auxiliary_peak |
| 176 | tore - rid - consideration - - | 76 | 176_tore_rid_consideration_ |
| 177 | unforeseen - absence - shortage - owner - absent | 76 | 177_unforeseen_absence_shortage_owner |
| 178 | reliability - verifying - conformity - statistical - reduction | 75 | 178_reliability_verifying_conformity_statistical |
| 179 | conducted - interaction - ride - ordering - demonstration | 75 | 179_conducted_interaction_ride_ordering |
| 180 | selected - - - - | 75 | 180_selected___ |
| 181 | chilled - cooled - fomentation - utilised - dwyer | 75 | 181_chilled_cooled_fomentation_utilised |
| 182 | stitch - stitching - twice - lot - uneven | 75 | 182_stitch_stitching_twice_lot |
| 183 | clamp - relay - bus - transformer - induration | 74 | 183_clamp_relay_bus_transformer |
| 184 | toxic - anti - harmful - publication - explosive | 74 | 184_toxic_anti_harmful_publication |
| 185 | consult - consultation - commission - expert - representative | 74 | 185_consult_consultation_commission_expert |
| 186 | lid - sealing - seal - mechanically - beaming | 74 | 186_lid_sealing_seal_mechanically |
| 187 | procure - theory - agricultural - beforestarting - requisition | 73 | 187_procure_theory_agricultural_beforestarting |
| 188 | abrasion - polished - compound - standing - cement | 73 | 188_abrasion_polished_compound_standing |
| 189 | knot - tail - weaver - tie - cord | 73 | 189_knot_tail_weaver_tie |
| 190 | smiling - graph - analyzed - microbiological - obtained | 73 | 190_smiling_graph_analyzed_microbiological |
| 191 | spray - fresh - gun - watered - peasant | 73 | 191_spray_fresh_gun_watered |
| 192 | celebrate - celebrated - checked - tested - shall | 73 | 192_celebrate_celebrated_checked_tested |
| 193 | controlling - sister - controlled - - | 73 | 193_controlling_sister_controlled_ |
| 194 | recovery - follows - recovered - initiation - minimise | 72 | 194_recovery_follows_recovered_initiation |
| 195 | year - variant - past - suit - average | 72 | 195_year_variant_past_suit |
| 196 | multi - multiple - single - let - | 72 | 196_multi_multiple_single_let |
| 197 | occupational - preferred - average - committee - cooperate | 72 | 197_occupational_preferred_average_committee |
| 198 | - - - - | 72 | 198____ |
| 199 | wishing - amiable - prayer - subsequent - tidings | 72 | 199_wishing_amiable_prayer_subsequent |
| 200 | tape - winter - circular - adjacent - roller | 72 | 200_tape_winter_circular_adjacent |
| 201 | shade - sun - intensity - shell - row | 72 | 201_shade_sun_intensity_shell |
| 202 | exterior - mirror - seat - window - rear | 72 | 202_exterior_mirror_seat_window |
| 203 | queried - doubt - participant - forward - directly | 72 | 203_queried_doubt_participant_forward |
| 204 | - - - - | 72 | 204____ |
| 205 | period - acceptable - aback - particular - lack | 72 | 205_period_acceptable_aback_particular |
| 206 | releasing - completeness - ride - indirect - possessing | 71 | 206_releasing_completeness_ride_indirect |
| 207 | tra - consequence - selected - statutory - wheeler | 71 | 207_tra_consequence_selected_statutory |
| 208 | modify - petitioning - acceptable - tolerable - authorization | 71 | 208_modify_petitioning_acceptable_tolerable |
| 209 | enhancing - spirit - enhance - expenditure - mile | 70 | 209_enhancing_spirit_enhance_expenditure |
| 210 | zero - weighing - counter - balance - | 70 | 210_zero_weighing_counter_balance |
| 211 | cart - ordering - sold - sending - buying | 70 | 211_cart_ordering_sold_sending |
| 212 | pick - drop - traveller - dropping - jack | 70 | 212_pick_drop_traveller_dropping |
| 213 | optimization - improved - subordinate - better - landscape | 70 | 213_optimization_improved_subordinate_better |
| 214 | minute - come - early - lot - late | 70 | 214_minute_come_early_lot |
| 215 | tic - quick - troubleshooting - premature - preliminary | 70 | 215_tic_quick_troubleshooting_premature |
| 216 | replaced - disposed - ending - appointed - duly | 70 | 216_replaced_disposed_ending_appointed |
| 217 | sac - perstandard - varnish - secondary - institutional | 70 | 217_sac_perstandard_varnish_secondary |
| 218 | party - applied - come - - | 70 | 218_party_applied_come_ |
| 219 | overhead - lower - lowered - low - round | 69 | 219_overhead_lower_lowered_low |
| 220 | restaurant - dining - seating - suggest - highly | 69 | 220_restaurant_dining_seating_suggest |
| 221 | candle - wax - knob - mold - dip | 69 | 221_candle_wax_knob_mold |
| 222 | commitment - let - dedicated - complement - implementing | 69 | 222_commitment_let_dedicated_complement |
| 223 | half - early - - - | 69 | 223_half_early__ |
| 224 | maturity - prioritize - assign - integrate - foster | 69 | 224_maturity_prioritize_assign_integrate |
| 225 | compile - lack - subsequent - option - comment | 69 | 225_compile_lack_subsequent_option |
| 226 | global - obstacle - normal - radiation - row | 69 | 226_global_obstacle_normal_radiation |
| 227 | attribute - degree - evacuated - said - attractive | 69 | 227_attribute_degree_evacuated_said |
| 228 | especially - computer - trained - faulty - referring | 69 | 228_especially_computer_trained_faulty |
| 229 | horrid - wheeler - dismantled - today - important | 68 | 229_horrid_wheeler_dismantled_today |
| 230 | rejection - rejected - conforming - say - instructed | 68 | 230_rejection_rejected_conforming_say |
| 231 | - - - - | 68 | 231____ |
| 232 | consider - opinion - utters - conformity - discussion | 68 | 232_consider_opinion_utters_conformity |
| 233 | cartoon - wrap - primary - ray - mechanically | 68 | 233_cartoon_wrap_primary_ray |
| 234 | microbiological - andreport - conforms - specimen - watered | 68 | 234_microbiological_andreport_conforms_specimen |
| 235 | furniture - bed - cabinet - built - minimal | 68 | 235_furniture_bed_cabinet_built |
| 236 | involving - preparatory - celebrating - prototype - recto | 68 | 236_involving_preparatory_celebrating_prototype |
| 237 | weld - welded - comparing - torch - lack | 68 | 237_weld_welded_comparing_torch |
| 238 | chip - regard - danger - removing - issued | 68 | 238_chip_regard_danger_removing |
| 239 | advance - requiredfor - forward - execution - theproduct | 67 | 239_advance_requiredfor_forward_execution |
| 240 | proactively - - - - | 67 | 240_proactively___ |
| 241 | session - aggregation - practical - producing - addressing | 67 | 241_session_aggregation_practical_producing |
| 242 | bind - bound - host - collected - conveys | 67 | 242_bind_bound_host_collected |
| 243 | munition - parking - enhance - better - frequently | 67 | 243_munition_parking_enhance_better |
| 244 | outline - highlight - schematic - print - corporation | 67 | 244_outline_highlight_schematic_print |
| 245 | trim - pair - pencil - stem - cast | 67 | 245_trim_pair_pencil_stem |
| 246 | casting - jacques - cast - uniformly - ordered | 66 | 246_casting_jacques_cast_uniformly |
| 247 | satisfaction - framework - minimise - leadership - resolution | 65 | 247_satisfaction_framework_minimise_leadership |
| 248 | indian - steel - iron - unload - beforestarting | 65 | 248_indian_steel_iron_unload |
| 249 | execute - execution - killed - ordered - phase | 65 | 249_execute_execution_killed_ordered |
| 250 | tra - - - - | 65 | 250_tra___ |
| 251 | obtaining - obtained - acquisition - determined - acquire | 65 | 251_obtaining_obtained_acquisition_determined |
| 252 | early - biodegradable - adhered - reasoning - tree | 64 | 252_early_biodegradable_adhered_reasoning |
| 253 | launched - receiver - organizer - landing - fold | 64 | 253_launched_receiver_organizer_landing |
| 254 | vacuum - cleaner - suction - shower - jumping | 64 | 254_vacuum_cleaner_suction_shower |
| 255 | correction - corrected - earliest - formulate - news | 64 | 255_correction_corrected_earliest_formulate |
| 256 | objective - strategics - strategic - developing - region | 64 | 256_objective_strategics_strategic_developing |
| 257 | feeling - radio - opinion - play - today | 64 | 257_feeling_radio_opinion_play |
| 258 | statutory - shall - dispatch - permission - authorization | 64 | 258_statutory_shall_dispatch_permission |
| 259 | silently - labour - unforeseen - understood - recognized | 64 | 259_silently_labour_unforeseen_understood |
| 260 | disposed - acquire - waking - lunch - attractive | 64 | 260_disposed_acquire_waking_lunch |
| 261 | utilize - utilised - utilizing - multiple - man | 63 | 261_utilize_utilised_utilizing_multiple |
| 262 | suitability - capability - appropriateness - feasible - recommend | 63 | 262_suitability_capability_appropriateness_feasible |
| 263 | - - - - | 63 | 263____ |
| 264 | - - - - | 62 | 264____ |
| 265 | updated - advice - pu - added - informed | 62 | 265_updated_advice_pu_added |
| 266 | leave - away - departure - attending - break | 62 | 266_leave_away_departure_attending |
| 267 | align - pu - column - semi - true | 62 | 267_align_pu_column_semi |
| 268 | legislation - - - - | 62 | 268_legislation___ |
| 269 | motion - obstacle - shifting - movable - asset | 62 | 269_motion_obstacle_shifting_movable |
| 270 | recipe - formulate - methodology - fat - potato | 62 | 270_recipe_formulate_methodology_fat |
| 271 | failed - - - - | 61 | 271_failed___ |
| 272 | receipt - treat - - - | 61 | 272_receipt_treat__ |
| 273 | rheumatic - semi - indicated - longer - methodology | 61 | 273_rheumatic_semi_indicated_longer |
| 274 | counterpart - handed - come - arrive - | 61 | 274_counterpart_handed_come_arrive |
| 275 | calculation - estimated - simple - reckon - concept | 61 | 275_calculation_estimated_simple_reckon |
| 276 | periodical - temporary - magazine - vice - building | 61 | 276_periodical_temporary_magazine_vice |
| 277 | yield - portion - newness - budgetary - aback | 60 | 277_yield_portion_newness_budgetary |
| 278 | bead - string - jewel - tight - selected | 60 | 278_bead_string_jewel_tight |
| 279 | cup - glassware - utensil - served - contains | 60 | 279_cup_glassware_utensil_served |
| 280 | anti - - - - | 60 | 280_anti___ |
| 281 | link - master - returned - sensory - fetch | 60 | 281_link_master_returned_sensory |
| 282 | drain - immunity - vat - pit - killed | 60 | 282_drain_immunity_vat_pit |
| 283 | reducing - caused - spread - preventing - occurrence | 60 | 283_reducing_caused_spread_preventing |
| 284 | haul - dump - verifying - motion - incompatibility | 60 | 284_haul_dump_verifying_motion |
| 285 | commissioning - cm - acquisition - statutory - installed | 60 | 285_commissioning_cm_acquisition_statutory |
| 286 | aware - - - - | 60 | 286_aware___ |
| 287 | regulate - forming - inter - tender - attended | 60 | 287_regulate_forming_inter_tender |
| 288 | involving - - - - | 60 | 288_involving___ |
| 289 | contribute - initiate - assurance - contract - | 59 | 289_contribute_initiate_assurance_contract |
| 290 | passed - screening - sent - course - passing | 59 | 290_passed_screening_sent_course |
| 291 | enter - entry - allowed - came - entering | 59 | 291_enter_entry_allowed_came |
| 292 | conducted - blow - instructor - come - minute | 59 | 292_conducted_blow_instructor_come |
| 293 | replenished - distribute - distributed - provision - falling | 59 | 293_replenished_distribute_distributed_provision |
| 294 | survey - variable - quantitative - laying - mechanic | 59 | 294_survey_variable_quantitative_laying |
| 295 | planned - nature - - - | 59 | 295_planned_nature__ |
| 296 | delivered - delivering - receipt - consistently - concerning | 58 | 296_delivered_delivering_receipt_consistently |
| 297 | major - die - lie - venerable - ordering | 58 | 297_major_die_lie_venerable |
| 298 | itching - pricking - updated - duly - menu | 58 | 298_itching_pricking_updated_duly |
| 299 | mounting - mounted - mount - attachment - align | 58 | 299_mounting_mounted_mount_attachment |
| 300 | yard - incorrectly - runner - lease - joining | 58 | 300_yard_incorrectly_runner_lease |
| 301 | spinning - outdoing - consumed - landing - providing | 58 | 301_spinning_outdoing_consumed_landing |
| 302 | tent - camp - toilet - crew - provision | 58 | 302_tent_camp_toilet_crew |
| 303 | pit - earth - resistance - laying - queried | 58 | 303_pit_earth_resistance_laying |
| 304 | coating - coated - coat - thinner - sac | 58 | 304_coating_coated_coat_thinner |
| 305 | installed - installing - partner - tied - element | 58 | 305_installed_installing_partner_tied |
| 306 | leftover - unused - partially - controlled - unattended | 58 | 306_leftover_unused_partially_controlled |
| 307 | meal - eating - eat - partner - drinking | 57 | 307_meal_eating_eat_partner |
| 308 | - - - - | 57 | 308____ |
| 309 | employed - adopted - occupational - employ - pole | 57 | 309_employed_adopted_occupational_employ |
| 310 | logbook - signature - logging - bulldozer - conducted | 57 | 310_logbook_signature_logging_bulldozer |
| 311 | - - - - | 57 | 311____ |
| 312 | ligament - balancing - dial - spirit - repaired | 57 | 312_ligament_balancing_dial_spirit |
| 313 | jam - cooked - taste - heated - moulded | 57 | 313_jam_cooked_taste_heated |
| 314 | sub - suspension - drop - tolerable - blueprint | 57 | 314_sub_suspension_drop_tolerable |
| 315 | prioritize - allocation - objective - obstacle - erentiate | 56 | 315_prioritize_allocation_objective_obstacle |
| 316 | kind - economic - pay - analyzing - | 56 | 316_kind_economic_pay_analyzing |
| 317 | employ - additional - mr - recto - | 56 | 317_employ_additional_mr_recto |
| 318 | booking - slip - com - dial - pay | 56 | 318_booking_slip_com_dial |
| 319 | unless - organised - wearing - fig - unnecessary | 56 | 319_unless_organised_wearing_fig |
| 320 | pair - pertaining - reported - abnormal - prime | 56 | 320_pair_pertaining_reported_abnormal |
| 321 | radiation - exposure - exposed - loud - wound | 56 | 321_radiation_exposure_exposed_loud |
| 322 | lip - lie - - - | 56 | 322_lip_lie__ |
| 323 | dismantled - discontent - held - faulty - trumpet | 56 | 323_dismantled_discontent_held_faulty |
| 324 | seat - seating - standing - sitting - dealer | 55 | 324_seat_seating_standing_sitting |
| 325 | direction - decision - - - | 55 | 325_direction_decision__ |
| 326 | strategics - pricking - advantage - better - exist | 55 | 326_strategics_pricking_advantage_better |
| 327 | isolation - live - pain - discontent - nearby | 55 | 327_isolation_live_pain_discontent |
| 328 | nature - earth - wildlife - geological - bird | 55 | 328_nature_earth_wildlife_geological |
| 329 | - - - - | 55 | 329____ |
| 330 | danger - amiable - - - | 55 | 330_danger_amiable__ |
| 331 | trade - aged - committee - bird - pollution | 55 | 331_trade_aged_committee_bird |
| 332 | negotiate - negotiation - farmer - adjusted - contract | 54 | 332_negotiate_negotiation_farmer_adjusted |
| 333 | consolidate - improper - outcome - poor - incorrectly | 54 | 333_consolidate_improper_outcome_poor |
| 334 | weighing - weighed - scale - french - bench | 54 | 334_weighing_weighed_scale_french |
| 335 | harvesting - filter - implementing - rooftop - pain | 54 | 335_harvesting_filter_implementing_rooftop |
| 336 | changed - altered - changing - themachine - thoroughly | 54 | 336_changed_altered_changing_themachine |
| 337 | tenure - laid - amiable - receipt - negotiation | 54 | 337_tenure_laid_amiable_receipt |
| 338 | lock - locked - locking - scenario - interlocking | 54 | 338_lock_locked_locking_scenario |
| 339 | instructed - instruct - advise - formation - peasant | 54 | 339_instructed_instruct_advise_formation |
| 340 | vanity - washed - - - | 54 | 340_vanity_washed__ |
| 341 | jewel - declaration - visitor - checked - par | 54 | 341_jewel_declaration_visitor_checked |
| 342 | blow - kind - furnace - round - straight | 53 | 342_blow_kind_furnace_round |
| 343 | string - clothes - hair - movable - erentiate | 53 | 343_string_clothes_hair_movable |
| 344 | reduction - reduced - mob - better - conventional | 53 | 344_reduction_reduced_mob_better |
| 345 | month - electronically - counting - addressing - andreport | 53 | 345_month_electronically_counting_addressing |
| 346 | disaster - land - till - danger - zone | 53 | 346_disaster_land_till_danger |
| 347 | assurance - owing - assure - outlining - house | 53 | 347_assurance_owing_assure_outlining |
| 348 | tag - dark - mat - - | 53 | 348_tag_dark_mat_ |
| 349 | distinguish - poor - - - | 53 | 349_distinguish_poor__ |
| 350 | soil - dead - bulldozer - stuck - percentage | 53 | 350_soil_dead_bulldozer_stuck |
| 351 | season - farmer - agricultural - variety - corporation | 53 | 351_season_farmer_agricultural_variety |
| 352 | providing - provision - supplied - say - child | 52 | 352_providing_provision_supplied_say |
| 353 | landing - outdoing - come - falling - launch | 52 | 353_landing_outdoing_come_falling |
| 354 | master - education - created - family - degree | 52 | 354_master_education_created_family |
| 355 | extend - changing - - - | 52 | 355_extend_changing__ |
| 356 | oneself - fool - authorization - lie - distributed | 52 | 356_oneself_fool_authorization_lie |
| 357 | accidental - scratch - conditioned - smaller - | 52 | 357_accidental_scratch_conditioned_smaller |
| 358 | pillage - accumulation - unusual - clearing - james | 52 | 358_pillage_accumulation_unusual_clearing |
| 359 | priority - inter - consult - instruct - realistic | 52 | 359_priority_inter_consult_instruct |
| 360 | inspected - examination - observing - inspecting - placed | 52 | 360_inspected_examination_observing_inspecting |
| 361 | assembled - specifying - laboring - fork - popularity | 51 | 361_assembled_specifying_laboring_fork |
| 362 | logistics - organizing - study - motion - consideration | 51 | 362_logistics_organizing_study_motion |
| 363 | came - pan - - - | 51 | 363_came_pan__ |
| 364 | comfortable - posture - toller - fast - suit | 51 | 364_comfortable_posture_toller_fast |
| 365 | peeling - peeled - sorted - core - corner | 51 | 365_peeling_peeled_sorted_core |
| 366 | carding - drafting - draft - drafted - costing | 51 | 366_carding_drafting_draft_drafted |
| 367 | higher - cooper - brought - cooked - advice | 51 | 367_higher_cooper_brought_cooked |
| 368 | example - - - - | 51 | 368_example___ |
| 369 | wax - polish - melt - boiler - causing | 51 | 369_wax_polish_melt_boiler |
| 370 | touch - metallic - touching - inner - dark | 51 | 370_touch_metallic_touching_inner |
| 371 | district - direct - centre - micro - copy | 50 | 371_district_direct_centre_micro |
| 372 | - - - - | 50 | 372____ |
| 373 | refuse - quickly - recent - refused - visit | 50 | 373_refuse_quickly_recent_refused |
| 374 | permit - permission - acquire - submission - copy | 50 | 374_permit_permission_acquire_submission |
| 375 | bias - alive - segment - trained - treated | 50 | 375_bias_alive_segment_trained |
| 376 | legislative - senate - legislation - extent - cooked | 50 | 376_legislative_senate_legislation_extent |
| 377 | sensory - contains - riot - simulate - absent | 50 | 377_sensory_contains_riot_simulate |
| 378 | watering - drainage - establishment - senate - publication | 50 | 378_watering_drainage_establishment_senate |
| 379 | factory - touching - - - | 50 | 379_factory_touching__ |
| 380 | nut - - - - | 50 | 380_nut___ |
| 381 | - - - - | 49 | 381____ |
| 382 | counted - night - conducted - conform - | 49 | 382_counted_night_conducted_conform |
| 383 | public - achieved - explosive - - | 49 | 383_public_achieved_explosive_ |
| 384 | implementing - changed - advise - ending - achieved | 49 | 384_implementing_changed_advise_ending |
| 385 | removed - original - removing - noticed - host | 49 | 385_removed_original_removing_noticed |
| 386 | neutral - - - - | 49 | 386_neutral___ |
| 387 | stoppage - stopped - zone - falling - drafting | 49 | 387_stoppage_stopped_zone_falling |
| 388 | pest - insect - infestation - presence - contaminant | 49 | 388_pest_insect_infestation_presence |
| 389 | creation - creating - created - shared - considered | 49 | 389_creation_creating_created_shared |
| 390 | workforce - labour - capability - pollution - killed | 49 | 390_workforce_labour_capability_pollution |
| 391 | elevated - trench - - - | 48 | 391_elevated_trench__ |
| 392 | faulty - incorrectly - cm - peri - | 48 | 392_faulty_incorrectly_cm_peri |
| 393 | showcase - industrial - picture - skewer - treated | 48 | 393_showcase_industrial_picture_skewer |
| 394 | scale - exposed - horrid - added - troubleshooting | 48 | 394_scale_exposed_horrid_added |
| 395 | smart - wise - bad - neat - pertaining | 48 | 395_smart_wise_bad_neat |
| 396 | - - - - | 48 | 396____ |
| 397 | drainage - pest - - - | 48 | 397_drainage_pest__ |
| 398 | atmosphere - underground - - - | 48 | 398_atmosphere_underground__ |
| 399 | faulty - - - - | 48 | 399_faulty___ |
| 400 | yer - thee - implication - - | 47 | 400_yer_thee_implication_ |
| 401 | standardized - possessing - equivalent - trained - commercial | 47 | 401_standardized_possessing_equivalent_trained |
| 402 | aseptic - useful - absent - fro - continuity | 47 | 402_aseptic_useful_absent_fro |
| 403 | - - - - | 47 | 403____ |
| 404 | interface - practical - repairing - institutional - human | 47 | 404_interface_practical_repairing_institutional |
| 405 | possibility - renewal - limitation - advantage - option | 47 | 405_possibility_renewal_limitation_advantage |
| 406 | tag - course - dont - interpreting - lot | 47 | 406_tag_course_dont_interpreting |
| 407 | latest - locally - true - secondary - soft | 47 | 407_latest_locally_true_secondary |
| 408 | decoration - decorative - unused - decorating - occasion | 47 | 408_decoration_decorative_unused_decorating |
| 409 | important - unique - insight - diverse - tip | 46 | 409_important_unique_insight_diverse |
| 410 | contract - agreement - negotiation - provider - entertainment | 46 | 410_contract_agreement_negotiation_provider |
| 411 | initiating - raised - settling - writing - | 46 | 411_initiating_raised_settling_writing |
| 412 | applied - submitted - - - | 46 | 412_applied_submitted__ |
| 413 | helper - assistant - understood - immunity - instruct | 46 | 413_helper_assistant_understood_immunity |
| 414 | raising - bound - altering - calling - force | 46 | 414_raising_bound_altering_calling |
| 415 | boiling - par - boiled - vessel - wise | 46 | 415_boiling_par_boiled_vessel |
| 416 | scuttle - continue - insert - allotted - exhausted | 45 | 416_scuttle_continue_insert_allotted |
| 417 | simulate - causing - functional - computer - | 45 | 417_simulate_causing_functional_computer |
| 418 | aided - orientation - computer - convert - precise | 45 | 418_aided_orientation_computer_convert |
| 419 | suggested - convey - sound - welcome - loud | 45 | 419_suggested_convey_sound_welcome |
| 420 | perspeci - cabinet - arranged - ray - sort | 45 | 420_perspeci_cabinet_arranged_ray |
| 421 | coordination - abroad - maneuver - coordinating - specialist | 45 | 421_coordination_abroad_maneuver_coordinating |
| 422 | factor - desiring - ness - timing - viz | 45 | 422_factor_desiring_ness_timing |
| 423 | entrepreneur - expert - family - venture - webster | 45 | 423_entrepreneur_expert_family_venture |
| 424 | outlet - sold - tub - purchased - returned | 45 | 424_outlet_sold_tub_purchased |
| 425 | traveling - incise - haul - biodegradable - cart | 45 | 425_traveling_incise_haul_biodegradable |
| 426 | scurry - compose - pointing - andros - altering | 45 | 426_scurry_compose_pointing_andros |
| 427 | concerning - tormented - allot - mixed - completing | 45 | 427_concerning_tormented_allot_mixed |
| 428 | sustainability - culture - carbon - strategic - programming | 45 | 428_sustainability_culture_carbon_strategic |
| 429 | foam - liquid - solid - sticking - agitator | 45 | 429_foam_liquid_solid_sticking |
| 430 | functionality - functional - eliminating - distinguish - erentiate | 44 | 430_functionality_functional_eliminating_distinguish |
| 431 | adhered - sticking - attachment - attach - owing | 44 | 431_adhered_sticking_attachment_attach |
| 432 | dispatch - transporting - transported - transit - ordered | 44 | 432_dispatch_transporting_transported_transit |
| 433 | perched - com - conventional - portion - die | 44 | 433_perched_com_conventional_portion |
| 434 | receipt - simple - supplied - advance - signature | 44 | 434_receipt_simple_supplied_advance |
| 435 | stacked - separately - incorrectly - - | 44 | 435_stacked_separately_incorrectly_ |
| 436 | - - - - | 44 | 436____ |
| 437 | watching - viewing - watch - reckon - allowing | 44 | 437_watching_viewing_watch_reckon |
| 438 | wig - turbine - mind - commissioning - gearbox | 44 | 438_wig_turbine_mind_commissioning |
| 439 | instructor - restriction - cult - evacuated - theme | 44 | 439_instructor_restriction_cult_evacuated |
| 440 | overcome - weakness - adverse - strength - expected | 44 | 440_overcome_weakness_adverse_strength |
| 441 | interpreting - rotating - tolerable - intake - initial | 43 | 441_interpreting_rotating_tolerable_intake |
| 442 | - - - - | 43 | 442____ |
| 443 | systematic - sir - undertaking - - | 43 | 443_systematic_sir_undertaking_ |
| 444 | harmony - - - - | 43 | 444_harmony___ |
| 445 | capture - minute - creating - connect - withthe | 43 | 445_capture_minute_creating_connect |
| 446 | tolerable - - - - | 43 | 446_tolerable___ |
| 447 | capital - venture - dance - distinguish - composite | 43 | 447_capital_venture_dance_distinguish |
| 448 | forth - recall - applying - - | 43 | 448_forth_recall_applying_ |
| 449 | shipping - missing - boy - tall - bound | 43 | 449_shipping_missing_boy_tall |
| 450 | transformer - wig - turbine - rating - phase | 43 | 450_transformer_wig_turbine_rating |
| 451 | owner - possessing - actual - sole - family | 43 | 451_owner_possessing_actual_sole |
| 452 | arrival - arrive - desk - departure - reception | 43 | 452_arrival_arrive_desk_departure |
| 453 | residue - bale - farmer - density - stitching | 43 | 453_residue_bale_farmer_density |
| 454 | pan - shaped - pacing - corner - matter | 43 | 454_pan_shaped_pacing_corner |
| 455 | connect - main - resulting - come - half | 43 | 455_connect_main_resulting_come |
| 456 | entry - preferred - pass - ticket - cash | 43 | 456_entry_preferred_pass_ticket |
| 457 | - - - - | 43 | 457____ |
| 458 | concept - carrier - evacuated - industrial - managing | 43 | 458_concept_carrier_evacuated_industrial |
| 459 | visible - - - - | 43 | 459_visible___ |
| 460 | elevator - conveys - trough - dump - rise | 43 | 460_elevator_conveys_trough_dump |
| 461 | cleanly - carbon - breaking - super - manhood | 43 | 461_cleanly_carbon_breaking_super |
| 462 | inspecting - cochon - sweet - showcase - entire | 42 | 462_inspecting_cochon_sweet_showcase |
| 463 | planned - encountered - unless - sundry - major | 42 | 463_planned_encountered_unless_sundry |
| 464 | integrate - integration - continued - captured - programming | 42 | 464_integrate_integration_continued_captured |
| 465 | pilot - crew - organizer - dressing - radio | 42 | 465_pilot_crew_organizer_dressing |
| 466 | brand - variant - net - wrap - country | 42 | 466_brand_variant_net_wrap |
| 467 | administrative - capital - planned - - | 42 | 467_administrative_capital_planned_ |
Training hyperparameters
- calculate_probabilities: False
- language: None
- low_memory: False
- min_topic_size: 10
- n_gram_range: (1, 1)
- nr_topics: None
- seed_topic_list: None
- top_n_words: 10
- verbose: True
- zeroshot_min_similarity: 0.7
- zeroshot_topic_list: None
Framework versions
- Numpy: 1.26.4
- HDBSCAN: 0.8.37
- UMAP: 0.5.6
- Pandas: 2.2.2
- Scikit-Learn: 1.1.0
- Sentence-transformers: 3.0.1
- Transformers: 4.42.3
- Numba: 0.58.1
- Plotly: 5.18.0
- Python: 3.10.13