From 17c65b50b4540719cbec12e2a0e52ef2bf99199e Mon Sep 17 00:00:00 2001 From: Vikachubro21 <57052932+Vikachubro21@users.noreply.github.com> Date: Tue, 7 Jun 2022 14:51:58 -0500 Subject: [PATCH 01/12] Create irelevant_keywords_spanish.txt --- .../Crawlers and Process/Patterns/irelevant_keywords_spanish.txt | 1 + 1 file changed, 1 insertion(+) create mode 100644 pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt diff --git a/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt b/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt new file mode 100644 index 0000000..4d8161a --- /dev/null +++ b/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt @@ -0,0 +1 @@ +eksdee From 51354feadf05ac888549fbfabb06f24ac4e0b3ee Mon Sep 17 00:00:00 2001 From: Vikachubro21 <57052932+Vikachubro21@users.noreply.github.com> Date: Tue, 7 Jun 2022 14:52:33 -0500 Subject: [PATCH 02/12] Create wiki_relevant_spanish.txt --- .../Crawlers and Process/Patterns/wiki_relevant_spanish.txt | 1 + 1 file changed, 1 insertion(+) create mode 100644 pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_spanish.txt diff --git a/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_spanish.txt b/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_spanish.txt new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_spanish.txt @@ -0,0 +1 @@ + From 481bdab34f269dbb1d4eb3c7de76bb0e6de79ab7 Mon Sep 17 00:00:00 2001 From: Vikachubro21 <57052932+Vikachubro21@users.noreply.github.com> Date: Tue, 7 Jun 2022 14:53:00 -0500 Subject: [PATCH 03/12] Create wiki_relevant_exclude_spanish.txt --- .../Patterns/wiki_relevant_exclude_spanish.txt | 1 + 1 file changed, 1 insertion(+) create mode 100644 pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_exclude_spanish.txt diff --git a/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_exclude_spanish.txt b/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_exclude_spanish.txt new file mode 100644 index 0000000..4d8161a --- /dev/null +++ b/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_exclude_spanish.txt @@ -0,0 +1 @@ +eksdee From d105e07a2053dec985e0a386265dd38eda407941 Mon Sep 17 00:00:00 2001 From: Vikachubro21 <57052932+Vikachubro21@users.noreply.github.com> Date: Tue, 7 Jun 2022 14:55:09 -0500 Subject: [PATCH 04/12] Update irelevant_keywords_spanish.txt --- .../Patterns/irelevant_keywords_spanish.txt | 249 +++++++++++++++++- 1 file changed, 248 insertions(+), 1 deletion(-) diff --git a/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt b/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt index 4d8161a..74f27cd 100644 --- a/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt +++ b/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt @@ -1 +1,248 @@ -eksdee +/\bstyles?\b/ +/books?/ +/cars?/ +/earth/ +/food/ +/future/ +/health/ +/life/ +/living/ +/members?/ +/money/ +/packages?/ +/pictures?/ +/popular/ +/radio/ +/videos?/ +\w+ball +accident +album +AMEX +animal +art\b +artist +athlet +australian.open +Auto.Rac +autos?\b +badminton +bbcthree +bcs.champion +bcs.national +beauty +bids?\b +Billboard +Books? Review +bowl\b +bowling +boxing +Braves +Brewers +British.open +Broadway +business +Cardinals +career +CBA.Playoffs +celebrit +champinship +champion +cinema +climate +clinics?\b +comed +commentisfree +commodit +concert +consumer +Corporat +cricket +culture +cup\b +currency +cyclyng +daytona 500 +deals?\b +DJIA +Dollar +Dow.Jones +dragster +earning +Econom +education +entertainment +environment +equestrian +exchange +Expos +farming +fashion +fiction +field \w+ goal +FIFA\b +films?\b +FINA\b +finalist +finals +financ +fitness +Flowery.Gold.Mines|FLOD +french.open +fund\b +funding +gallery +games?\b +genre\b +gifts?\b +goalkeeper +goals\b +golf\b +Grammy +grand.national +grand.prix +grand.slam +graphic +gymnastic +had \w+ goal +half.time +heartquake +Hockey +hollywood +hurricane +Index.Future +Indianapolis.500 +IndyCar +info\b +interest.rate +invest +iron.man +jazz +kentucky.derby +le.mans +LEAGUE +lifestyle +Lottery +Lotto +LPGA\b +marathon +march.madness +market +meals?\b +meast +medalist +membership +Mets\b +Mortgage +motorsport +movie +music +NASCAR +NASD +Nasdaq +natural disaster +NBA\b +NCAA +Netflix +nfl\b +NHL\b +novels?\b +NYSE +obituar +offseason +Olympic +Orioles +Oscar +Padres +paidpost +paralympic +Penguins +performance +PGA\b +Phillies +Pirates +Pitchers +play.ball +player +Playoffs +podcast +pollut +polo\b +pop\b +popular culture +Powerball +prices?\b +product +PSE\b +quarterback +quote +racing +real.?estate +Recap +Recipe +religion +results +roundup +rowing\b +rugby\b +Russell.2000 +Russell.US.Index +ryder\b +S&P +sailing +sales?\b +score \w+ goal +score\b +scorers?\b +scoring\b +seller +semi.final +semifinal +shoot \w+ goal +shopping +Shoppers +shot \w+ goal +showbiz +singer +six.nations +soccer +specials +sports?\b +Spring.training +starting.grid +stock +success +surfer +surfing +swim +T-bill +tech\b +tech\b +technology +technology\b +temperature +tennis +theater +ticket +top sing +tornado +tour.de.france +tournament +trade +travel +Treasuries +Treasury +Triathlon +tv\b +U\.S\. Open +uefa\b +us.open +venture +vr\b +weather +weight.?lift +Wimbledon +winning +world.classic +world.series +Yankees +Tourism From 86dcc639558806918dde08b5bdbce93740f92f55 Mon Sep 17 00:00:00 2001 From: Vikachubro21 <57052932+Vikachubro21@users.noreply.github.com> Date: Tue, 7 Jun 2022 14:58:05 -0500 Subject: [PATCH 05/12] Update irelevant_keywords_spanish.txt --- .../Patterns/irelevant_keywords_spanish.txt | 340 +++++++++--------- 1 file changed, 170 insertions(+), 170 deletions(-) diff --git a/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt b/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt index 74f27cd..05e2039 100644 --- a/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt +++ b/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt @@ -1,248 +1,248 @@ -/\bstyles?\b/ -/books?/ -/cars?/ -/earth/ -/food/ -/future/ -/health/ -/life/ -/living/ -/members?/ -/money/ -/packages?/ -/pictures?/ +/estilos? +/¿Libros? +/coches +/tierra +/alimentos/ +/futuro/ +/salud +/vida/ +/vida/ +/miembros/ +/dinero/ +/paquetes +/fotos /popular/ /radio/ -/videos?/ -\w+ball -accident -album +/¿videos? +\w+bola +accidente +álbum AMEX animal -art\b -artist +arte +artista athlet -australian.open +australiano.abierto Auto.Rac -autos?\b -badminton +auto.rac +bádminton bbcthree -bcs.champion -bcs.national -beauty -bids?\b -Billboard -Books? Review -bowl\b -bowling -boxing +bcs.campeón +bcs.nacional +belleza +ofertas.bcs +Cartelera +¿Libros? Revisar +bolos +bolos +boxeo Braves -Brewers +Cerveceros British.open Broadway -business -Cardinals -career +negocio +Cardenales +carrera CBA.Playoffs celebrit -champinship -champion -cinema -climate -clinics?\b +campeonato +campeón +cine +clima +clinics?|b comed commentisfree commodit -concert -consumer +concierto +consumidor Corporat cricket -culture -cup\b -currency +cultura +copa +moneda cyclyng daytona 500 -deals?\b +ofertas... DJIA -Dollar +Dólar Dow.Jones dragster -earning -Econom -education -entertainment -environment -equestrian -exchange +ganancia +Economía +educación +entretenimiento +medio ambiente +ecuestre +intercambio Expos -farming -fashion -fiction -field \w+ goal +agricultura +moda +ficción +campo \w+ gol FIFA\b -films?\b +películas FINA\b -finalist -finals +finalista +finales financ fitness -Flowery.Gold.Mines|FLOD -french.open +Minas.de.oro.floridas|FLOD +francés.abierto fund\b -funding -gallery -games?\b -genre\b -gifts?\b -goalkeeper -goals\b -golf\b +financiación +galería +juegos +género +regalos +portero +goles +golf Grammy -grand.national -grand.prix +gran.nacional +gran.premio grand.slam -graphic -gymnastic -had \w+ goal -half.time -heartquake +gráfico +gimnástico +tenía \w+ meta +medio tiempo +temblor de corazón Hockey hollywood -hurricane -Index.Future -Indianapolis.500 +huracán +Índice.futuro +Indianápolis.500 IndyCar -info\b -interest.rate -invest +info +tipo.de.interés +invertir iron.man jazz kentucky.derby le.mans -LEAGUE -lifestyle -Lottery -Lotto +LIGA +estilo de vida +Lotería +Lotería LPGA\b -marathon -march.madness -market -meals?\b +maratón +locura.de.marzo +mercado +comidas meast -medalist -membership +medallista +afiliación Mets\b -Mortgage -motorsport -movie -music +Hipoteca +deporte del motor +película +música NASCAR NASD Nasdaq -natural disaster +desastre natural NBA\b NCAA Netflix nfl\b NHL\b -novels?\b +Novelas NYSE obituar -offseason -Olympic +fuera de temporada +Olímpico Orioles Oscar Padres paidpost -paralympic -Penguins -performance +paralímpico +Pingüinos +rendimiento PGA\b Phillies -Pirates -Pitchers -play.ball -player +Piratas +Lanzadores +jugar.bola +jugador Playoffs podcast pollut polo\b pop\b -popular culture +cultura popular Powerball -prices?\b -product +precios +producto PSE\b -quarterback -quote -racing -real.?estate -Recap -Recipe -religion -results -roundup -rowing\b -rugby\b +mariscal de campo +cotización +carreras +inmobiliario... +Recapitulación +Receta +religión +resultados +resumen +Remo +rugby\N Russell.2000 -Russell.US.Index +Índice.Russell.US ryder\b S&P -sailing -sales?\b -score \w+ goal -score\b -scorers?\b -scoring\b -seller -semi.final +vela +ventas?\Nb +puntuación \w+ gol +puntuación\b +goleadores +goleadores +vendedor semifinal -shoot \w+ goal -shopping -Shoppers -shot \w+ goal -showbiz -singer -six.nations -soccer -specials -sports?\b -Spring.training -starting.grid +semifinal +disparar \w+ gol +compras +Compradores +tiro \w+ gol +mundo del espectáculo +cantante +seis.naciones +fútbol +especiales +deportes +entrenamiento.de.primavera +parrilla.de.salida stock -success -surfer -surfing -swim +éxito +surfista +surf +nadar T-bill tech\b -tech\b -technology -technology\b -temperature -tennis -theater -ticket +tecnología +tecnología +tecnología +temperatura +tenis +teatro +billete top sing tornado -tour.de.france -tournament -trade -travel -Treasuries -Treasury -Triathlon +tour.de.francia +torneo +comercio +viaje +Tesoros +Tesorería +Triatlón tv\b -U\.S\. Open +U\N- S\N. Abierto uefa\b us.open -venture +aventura vr\b -weather -weight.?lift +tiempo +Peso. Wimbledon -winning -world.classic -world.series +ganar +clásico.mundial +serie.mundial Yankees -Tourism +Turismo From ff407518cd07885436e1cbc2bbff0730482cf73f Mon Sep 17 00:00:00 2001 From: Nathan Garrett Hilburn <106279957+nathangarretth@users.noreply.github.com> Date: Tue, 7 Jun 2022 15:04:17 -0500 Subject: [PATCH 06/12] Add files via upload --- .../Crawlers and Process/Patterns/wiki_relevant_spanish.txt | 1 - 1 file changed, 1 deletion(-) diff --git a/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_spanish.txt b/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_spanish.txt index 8b13789..e69de29 100644 --- a/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_spanish.txt +++ b/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_spanish.txt @@ -1 +0,0 @@ - From d0c7fe40f57a38055f2cfeb52010fd82cf92c623 Mon Sep 17 00:00:00 2001 From: Nathan Garrett Hilburn <106279957+nathangarretth@users.noreply.github.com> Date: Tue, 7 Jun 2022 15:13:44 -0500 Subject: [PATCH 07/12] Add files via upload --- .../Patterns/wiki_relevant_spanish.txt | 265 ++++++++++++++++++ 1 file changed, 265 insertions(+) diff --git a/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_spanish.txt b/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_spanish.txt index e69de29..1062661 100644 --- a/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_spanish.txt +++ b/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_spanish.txt @@ -0,0 +1,265 @@ +relaciones \w+-\w+ +secuestrar +abuso +activista +actos\b +administración +contra las mujeres +agencias +allegati +embajador +anarquía +armado +ejército +detención +artillería +asesino +asalto +asamblea +asilo +ataque +attrocit +autoridades +boleta electoral +batallas... +derramamiento de sangre +BLOTTER +cuerpos +bomba +frontera +boicot +armarios +caso\b +casualt +bajas +censores +civil\b +coaccionar +colonial +combate +comité +mancomunidad +comunismo +comunista +conflicto +congreso +conscripto +conservador +constituenc +constitución +convicto +corps\b +corrupto +consejo +concejal +Contrainsurgencia +Contra el terrorismo +Países en +golpes de estado +tribunales +delitos? +criminal +restringir +ciberataque +cibercrimen +daño +muerte +muerte +defensa +defensa +delegado +democrático +demostración +departamento +representación +desplegar +deportar +diputado +destruir +detener +detención +dictador +diplomático +diplomático +discriminar +desestablecido +desobediencia +desobedecer +desplazar +disputas +elecciones +electoral +emancipat +Embajada +aplicación +esclavizar +ejecutado +ejecutar +ejecuciones +expatriados +expulsar +explotar +explosión +extraditar +extremista +federal +feminista +fuerzas? +forcibl +extranjero +Asuntos.exteriores +relaciones.exteriores +formaciones +fraude +gángster +genocidio +gobernar +granada +guerrilla +armas... +colgado +derechos.humanos? +encarcelar +incendiario +incidentes +independencia +injur +insurgente +inteligencia +Intergubernamental +relación.internacional +invadir +invasión +cárceles +jueces +justicia +secuestrar +matar +leyes +legalidad +legalización +legislativo +legisladores +liberal +liberación +lobby +medios de comunicación de masas +fosa.masiva +masacre +alcalde +Estados miembros de +militante +militar +milicia +ministro +ministerios +ministerio +misiles +monarca +movimiento +municipal +asesinato +mutilación +nacionalismo +nacionalista +nacionalidad +nato\b +non... violen +nypd +ocupación +titular de la oficina +oficial +funcionarios +operaciones +organización +organizado +parlamento +partidos +partido +mantenimiento de la paz +persecución +piquete +policía +político +político +política +preprisal +presidente +prisión +propaganda +prostitut +protesta +violación +rebelde +referéndum +reforma +refugio +relaciones +reprimir +republicano +resolución +restringir +tomar represalias +revolución +rifle +derechos +disturbios... +gobernantes +sanción +Secretario de Estado +seguridad +senado +condenado +separatismo +servidores +disparando +dispara +disparo +matanza +esclavo +Asuntos sociales +Asuntos sociales +socialista +soldado +apuñalado +Apuñalamiento +huelga +supremo +sospechoso +sospechoso +territorial +territorios +territorio +terror +Think tank +amenaza +tortura +tráfico +tragedia +trágico +tratados +juicios +tribunal +tropa +desarmado +ilegal +víctima +vigilancia +violat +violen +voto +guerra +guerras +waterboard +arma +bienestar +casa blanca +Ciberseguridad +Brexit +inmigración +marihuana +disturbios +drogas +disputa +desigualdad +Prensa... libertad \ No newline at end of file From 69f0d8de295697cf3d6836a8262e390ba6e0724c Mon Sep 17 00:00:00 2001 From: Vikachubro21 <57052932+Vikachubro21@users.noreply.github.com> Date: Wed, 8 Jun 2022 13:14:10 -0500 Subject: [PATCH 08/12] Update irelevant_keywords_spanish.txt --- .../Patterns/irelevant_keywords_spanish.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt b/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt index 05e2039..e452e91 100644 --- a/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt +++ b/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt @@ -1,4 +1,4 @@ -/estilos? +/estilos?/ /¿Libros? /coches /tierra From 29106ee73560ad548749a3944322e7a453fc0f6d Mon Sep 17 00:00:00 2001 From: Vikachubro21 <57052932+Vikachubro21@users.noreply.github.com> Date: Wed, 8 Jun 2022 13:15:51 -0500 Subject: [PATCH 09/12] Update irelevant_keywords_spanish.txt --- .../Patterns/irelevant_keywords_spanish.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt b/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt index e452e91..36f59f2 100644 --- a/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt +++ b/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt @@ -1,5 +1,5 @@ /estilos?/ -/¿Libros? +/libros? /coches /tierra /alimentos/ From 41b33bd7a5fc0fad2b9d8692531b4fac2fb409b0 Mon Sep 17 00:00:00 2001 From: Nathan Garrett Hilburn <106279957+nathangarretth@users.noreply.github.com> Date: Wed, 8 Jun 2022 13:52:32 -0500 Subject: [PATCH 10/12] Update wiki_relevant_exclude_spanish.txt --- .../wiki_relevant_exclude_spanish.txt | 23 ++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_exclude_spanish.txt b/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_exclude_spanish.txt index 4d8161a..42f7447 100644 --- a/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_exclude_spanish.txt +++ b/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_exclude_spanish.txt @@ -1 +1,22 @@ -eksdee +álbum +ficción +firma +película +paralímpico +deporte +cementerio +novela +juego +jugar +cultura popular +Entorno de +\w+bola +diseño +Vida silvestre +fauna +marcial +AC\b +accidente +desastre +Barcos construidos +Barcos de\b From f45612456c99ea5489ed400931543ddf85f29bb1 Mon Sep 17 00:00:00 2001 From: Nathan Garrett Hilburn <106279957+nathangarretth@users.noreply.github.com> Date: Wed, 8 Jun 2022 13:55:17 -0500 Subject: [PATCH 11/12] Update wiki_relevant_exclude_spanish.txt --- .../Patterns/wiki_relevant_exclude_spanish.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_exclude_spanish.txt b/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_exclude_spanish.txt index 42f7447..2b2aae9 100644 --- a/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_exclude_spanish.txt +++ b/pretrain-corpora/Crawlers and Process/Patterns/wiki_relevant_exclude_spanish.txt @@ -4,7 +4,7 @@ firma película paralímpico deporte -cementerio +cementer novela juego jugar From c6dc3ecc8426718d87495640e6e71c264b3fbc69 Mon Sep 17 00:00:00 2001 From: Nathan Garrett Hilburn <106279957+nathangarretth@users.noreply.github.com> Date: Wed, 8 Jun 2022 14:14:52 -0500 Subject: [PATCH 12/12] Update irelevant_keywords_spanish.txt --- .../Patterns/irelevant_keywords_spanish.txt | 73 +++++++++---------- 1 file changed, 36 insertions(+), 37 deletions(-) diff --git a/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt b/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt index 36f59f2..78d940f 100644 --- a/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt +++ b/pretrain-corpora/Crawlers and Process/Patterns/irelevant_keywords_spanish.txt @@ -1,19 +1,20 @@ -/estilos?/ -/libros? -/coches -/tierra +/\bestilos?\b/ +/libros?/ +/coches?/ +/carros?/ +/automóviles?/ +/tierra/ /alimentos/ /futuro/ -/salud +/salud/ /vida/ -/vida/ -/miembros/ +/miembros?/ /dinero/ -/paquetes -/fotos +/paquetes?/ +/fotos?/ /popular/ /radio/ -/¿videos? +/videos/ \w+bola accidente álbum @@ -22,9 +23,9 @@ animal arte artista athlet -australiano.abierto +australian.open Auto.Rac -auto.rac +autos?\b bádminton bbcthree bcs.campeón @@ -32,9 +33,8 @@ bcs.nacional belleza ofertas.bcs Cartelera -¿Libros? Revisar -bolos -bolos +Libros? Revisar +bolos\b boxeo Braves Cerveceros @@ -44,7 +44,7 @@ negocio Cardenales carrera CBA.Playoffs -celebrit +celebrid campeonato campeón cine @@ -80,26 +80,26 @@ moda ficción campo \w+ gol FIFA\b -películas +películas?\b FINA\b finalista finales financ fitness -Minas.de.oro.floridas|FLOD +Flowery.Gold.Mines|FLOD francés.abierto fund\b financiación galería -juegos -género -regalos +juegos?\b +género\b +regalos?\b portero -goles -golf +goles\b +golf\b Grammy -gran.nacional -gran.premio +grand.national +grand.prix grand.slam gráfico gimnástico @@ -170,7 +170,7 @@ polo\b pop\b cultura popular Powerball -precios +precios?\b producto PSE\b mariscal de campo @@ -185,17 +185,17 @@ resumen Remo rugby\N Russell.2000 -Índice.Russell.US +Russell.US.Index ryder\b S&P vela -ventas?\Nb +ventas?\b puntuación \w+ gol puntuación\b -goleadores -goleadores +goleadores\b +goleadores\b vendedor -semifinal +semi.final semifinal disparar \w+ gol compras @@ -217,8 +217,7 @@ nadar T-bill tech\b tecnología -tecnología -tecnología +tecnología\b temperatura tenis teatro @@ -233,16 +232,16 @@ Tesoros Tesorería Triatlón tv\b -U\N- S\N. Abierto +U\.S\. Open uefa\b us.open aventura vr\b tiempo -Peso. +Peso.?leventar Wimbledon ganar -clásico.mundial -serie.mundial +world.classic +world.series Yankees Turismo