Tag: TG_URL_TEXT

The length of the URL, divided by 5

URL satisfies forum_detector regularly

The URL has an ancient date. Ancient news are recognized. Factor 1 if there is a year in Url <= 2007.

The largest total tuning of Urla and request, normalized by the length of Urla

All coincidences are only in the URL, there are no coincidences in the text

Coating domain three -bouqu and request. (Chelyabinsk lottery - Chelloto. We translate a request to translite, find the three -book that are covered (Che, Hel, Lot, Olo), we look at what share of all three -bouquets are covered)

The same as the previous factor, but about the entire Url except the domain

Domna in Zone .com

Domain in the .ua zone

Domain is not in the .ru zone

There are no numbers in Urla

BM25 on URL'U

DSSM model with early binding, trained on reforming and learned by ASR hypotheses of musical requests for Alice

A model trained on a PRS-Law PRS to predict BERT, trained on sinsig_ce with threshold value 0.5, using a chain of regions to the country

DSSM model with early binding, trained on reforming and learned on musical requests for Alice

Type of canonized Urla Yandex Music - Album

The host of the document is recognized in the request

URL consists only of the host, which is recognized in the request

URL is the plot of Yandex News

The number of slashes in Url

The factor is calculated from the text of Url using the classifier of sequences Quality/Seq/GSK

Model with the training of each trigram on '+' and '-' Urlah. It does not depend on the request.

The coincidence of geography, determined from the Url of the document and the city of the request (IP or LR)

The coincidence of geography, determined from the Url of the Document and the Request region (IP or LR)

The coincidence of geography, determined from the Url of the document and the country of request (IP or LR). Actual for Russia and Ukraine.

The coincidence of geography, determined from Ural Documents and the City in the request (GEOCITY rule)

Urlngramsmodel ranking factor in ERF

A pool of logs is marked with BERT trained on Sinsig. DSSM model is trained on this pool using BaseregionChain

The number of 'Nebukv 'in Url

The length of the URL with an accuracy to the symbol. Disconnected in production.

The URL document corresponds to the user (http://wiki.yandex-team.ru/jandekspoisk/kacheStvopoiska/geo/regnavquerispoisk/KacheStvopoiska/GEO/RENAVAVQURIES)

Url contains a token that coincides with the short name of the user country. The factor is considered only on the EU stream.

Url satisfies the regexp expression set in the demon

DSSM Prediction of the probability of URL + Title that there is no product on the page.

DSSM Prediction of the probability of URL + Title, which is on the page one product.

DSSM Prediction of the probability of URL + Title, that there are a lot of goods on the page.

For Urla, a geo-approval of the city level is determined according to the rules of the BUKI-1125

For Urla, a geo-approval of the country's level is determined according to the BUKI-1125 rules

Finetuned reformulations DSSM to commercial clicked bargain odd-like target from visit log

URL is a product on the market.

URL is a product on the market and has Offerid.

URL is Shopinshopcpa.

DSSM Prediction of the probability of URL + Title that the document is an overlap.

Predict SOS.DSSM models by URL + Title.

Med.DSSM Predictions URL + Title models.

FIN_LAW.DSSM Predictions URL + TITLE.

Predict Cruelty.dssm URL + TITLE models.

Request and documentary navigation model.

Prediction of Med_with_Trash.DSSM (Medic. Document model with Tresh Valley in Lern) Models for URL + Title.

Prediction FIN_LAW_WITH_TRASH.DSSM (Fin-Jur. Document model with a tresh valve in Lern) Models for URL + Title.

DSSM, predicting the Page Quality rating for the document

A document is a short video (Tiktok, Reels, Shorts).

Document-telegram channel in web format.

Document - post in a telegram.

Factor about the presence of a symbol '?' In Url. It is zero if the Url has CGI parameters (more precisely: all duplicate have a symbol '?' In Url).

DSSM CLOSE DISCOUNT according to data specific for Alice

The prediction of the total time spent to the end of the session, provided that this pair is implemented by the request-document

The prediction of the contribution of this pair request-document to the timetable

The prediction of the percentage of the length of the track, which will be lost subject to the implementation of this pair of the request

The likelihood that the Yweb/Robot/urlgeo_ml region is correct is correct, provided that the city is predicted

Linguistic boosting factor. Type of extensions: XFDTSHOW. Factor: BM15 in the group of streams 2. The maximum value of the factor for extensions.

Linguistic boosting factor. Type of extensions: XFDTSHOW. Factor: BM15FLOGW0 for Urlu and Title. The maximum value of the expansion factor.

Linguistic boosting factor. Type of extensions: XFDTSHOW. Factor: BM15 on Ural. The maximum value of the expansion factor.

Linguistic boosting factor. Type of extensions: XFDTSHOW. Factor: BM15FLOG by the Stream group 1. The average balanced values ​​of the factor multiplied by weight (\ frac {\ sum w_i * (w_i * f_i)} {\ sum w_i}) for extensions.

Linguistic boosting factor. Type of extensions: XFDTSHOW. Factor: BM15FLOGW0 for Urlu and Title. The average balanced values ​​of the factor multiplied by weight (\ frac {\ sum w_i * (w_i * f_i)} {\ sum w_i}) for extensions.

URL coating with trigrams from the request. Analogue of Urldomainfraction, Urlpathandparamsfraction factors.

Bm15K01 factor over hits from Url

Bm15FLogW0K00001 factor over hits from FieldSetUT stream

DSSM model trained on clicks.

DSSM model trained on clicks.

DSSM model trained on clicks.

DSSM model trained on clicks.

DSSM model trained on clicks.

DSSM model trained on clicks.

DSSM model trained on clicks.

DSSM model trained on clicks.

Neural model of content quality for medical subjects

Neural model of content quality for medical subjects (for ex -)

Neural model of content quality for financial and legal topics

Neural model of content quality for financial and legal topics (for exposures)

Linguistic boosting factor. Type of extensions: Requestwithregionname. Factor: BM15 in the group of streams 1.

Linguistic boosting factor. Type of extensions: Requestwithregionname. Factor: BM15 in the group of streams 2.

Neural model of content quality for SOS topics

Neural model of content quality for SOS subjects (for ex -)

Copy of Old Version No.294 Factor. Added for Use on L3 Stage Only. Coating domain three -bouqu and request. (Chelyabinsk lottery - Chelloto. We translate a request to translite, find the three -book that are covered (Che, Hel, Lot, Olo), we look at what share of all three -bouquets are covered)

Fast version of FI_URL_DOMAIN_FRACTION

Prediction of the time of the session, provided that this pair is requested by the request-document

Request-document DSSM, predicting the dog's dog

Document - this is a selection of Tiktok /Tag

Document - this is a selection of Tictock /Discovery

Document - this is a selection of Tiktok /Music

Request-document model Sinsiga.

The factor for the original request. It is considered to be toxicated by Ural. Algorithm Cosinematchmaxpredical.

The factor for the original request. It is considered to be toxicated by Ural. The weight of the hit is multiplied by 1/ (1 + the position of the word in the sentence) an algorithm for aggregation of the scales of words: BM15. Normalization coefficient 0.5.

DSSM, predicting whether the site is a facial

DSSM model trained on clicks. Takes bigrams into account.

DSSM model trained on clicks. Takes bigrams into account. Embeddings for documents are computed offline.

A minimum of gradients according to the Bigramm LogdwellTime model.

Maximum from gradients according to the Bigramm Logdwelltime model.

The second central moment (dispersion) from gradients according to the Bigramm Logdwelltime model.

The third central moment from gradients according to the Bigramm Logdwelltime model.

Linguistic boosting factor. Type of extensions: QFUF. Factor: BM15FLOGW0_K0.0001 on Ural and the heading. The maximum value of the expansion factor.

Linguistic boosting factor. Type of extensions: QFUF. Factor: BM15FLOG_K0.001 according to Fieldset1. The average balanced values ​​of the factor with a quadratic weight in the top 10 in terms of factor value by extensions.

Linguistic boosting factor. Type of extensions: QFUF. Factor: BM15FLOGW0_K0.0001 on Ural and the heading. The average balanced values ​​of the expansion factor.

DSSM model trained on clicks, target=OneClicks/Clicks. Takes bigrams into account.

DSSM model trained on clicks, target=QueryDwellTime stream value. Takes bigrams into account.

Document DSSM model Language Classifier Rus.

Document DSSM model Language Classifier Eng.

Document DSSM model Language Classifier Other.

DSSM Prediction to determine Alice's irrelevant answers

DSSM model trained on CTRs without miner.

DSSM prediction (URL + Title), trained for the Page_QUALYY signal and implemented in RTHUB, the first slot.

DSSM prediction (URL + Title), trained on the Page_QUALYY signal and implemented in RTHUB, the second slot.

DSSM model trained on click odd pool

DSSM model trained on click personalization pool

DSSM model trained on click triangle pool

DSSM model trained on clicks without miner (with no-clicks and AM-hard negatives). Takes bigrams into account.

Type of canonized Urla Yandex Music - track

Document has Fio from original request

DSSM model trained on clicks without miner (with no-clicks and am_hard negatives 50/50 and then on am_hard negatives only). Takes bigrams into account.

Neural document model for finding unexpected tin

The initial request with the removal of verbs. It is considered to be composational stream, consisting of an tokenized Url and a title of a document. The algorithm for aggregation of the scales of words: BM15FLOGW0. Normalization coefficient 0.0001.

The initial request with the removal of verbs. It is considered to be toxicated by Ural. The algorithm for aggregation of the scales of words: BM15. Normalization coefficient 0.1.

The document has a HTTPS protocol

Levenstein’s distance between the request and Url of the type of YouTubecom/Watch normalized to the maximum of the length of the request and Url

The length of the largest total setting between Url and the request normalized for the length of the request

Linguistic boosting factor. Type of extensions: QFUFFILTEDBYXFONSE (QFUF, filtered on the DSSM models Xfonese). Aggregation on all extensions. The greatest value of the factor. Into aircraft association of the URLs, Title, Body, Correctedctr, Longclick, OneClick, Browserpagerank, Splitdwelltime, SampleperiodDayFrc, SimpleClick, Yabarvisits, Yabartime. The algorithm for aggregation of the scales of words: BM15FLOG (BM15 Aggregation of Logarithm of Construction of Words). Normalization coefficient 0.001.

Linguistic boosting factor. Type of extensions: QFUFFILTEDBYXFONSE (QFUF, filtered on the DSSM models Xfonese). Aggregation on all extensions. The greatest value of the factor. Rebelled association of streams Title, Body, LongClick, LongClicksp, OneClick. The algorithm for aggregation of the scales of words: BCLMWEIGHTEDFLOGW0. Normalization coefficient 0.001.

Linguistic boosting factor. Type of extensions: QFUFFILTEDBYXFONSE (QFUF, filtered on the DSSM models Xfonese). Aggregation on all extensions. The greatest value of the factor. It is considered to be composational stream, consisting of an tokenized Url and a title of a document. The algorithm for aggregation of the scales of words: BM15FLOGW0. Normalization coefficient 0.0001.

Linguistic boosting factor. Type of extensions: QFUFFILTEDBYXFONSE (QFUF, filtered on the DSSM models Xfonese). Aggregation by TOP-10 (by the value of the factor) extensions. A suspended sum of the Libra of factors. Normalized for the total weight of extensions. Into aircraft association of the URLs, Title, Body, Correctedctr, Longclick, OneClick, Browserpagerank, Splitdwelltime, SampleperiodDayFrc, SimpleClick, Yabarvisits, Yabartime. The algorithm for aggregation of the scales of words: BM15FLOG (BM15 Aggregation of Logarithm of Construction of Words). Normalization coefficient 0.001.

The factor for the filtered original request: the DSSM state from the request is calculated without words to the initial request, after which the threshold is cut off. Into aircraft association of the URLs, Title, Body, Links, Correctedctr, LongClick, OneClick, Browserpagerank, Splitdwelltime, SampleperiodDayFrc, SimpleClick, Yabarvisits, Yabartime. The algorithm for aggregation of the scales of words: BM15FLOG (BM15 Aggregation of Logarithm of Construction of Words). Normalization coefficient 0.001.

The factor for the filtered original request: the DSSM state from the request is calculated without words to the initial request, after which the threshold is cut off. It is considered to be composational stream, consisting of an tokenized Url and a title of a document. The algorithm for aggregation of the scales of words: BM15FLOGW0. Normalization coefficient 0.0001.

DSSM model trained on cross language CTRs using serp similarity hard miner.

Linguistic boosting factor. Type of extensions: XFONESEKNN (closest to the DSSM models trained to predict XFDTSHOW of extension). Aggregation on all extensions. The greatest balanced value of the factor. It is normalized for the maximum weight of expansion. Into aircraft association of the URLs, Title, Body, Links, Correctedctr, LongClick, OneClick, Browserpagerank, Splitdwelltime, SampleperiodDayFrc, SimpleClick, Yabarvisits, Yabartime. The algorithm for aggregation of the scales of words: BM15FLOG (BM15 Aggregation of Logarithm of Construction of Words). Normalization coefficient 0.001.

Linguistic boosting factor. Type of extensions: QuerytotextByxfoneKnn (Querytotext extensions of Xfoneeseknn extensions). Aggregation on all extensions. A suspended sum of the Libra of factors. Normalized for the total weight of extensions. Rebelled association of streams Title, Body, LongClick, LongClicksp, OneClick. The algorithm for aggregation of the scales of words: BCLMWEIGHTEDFLOGW0. Normalization coefficient 0.001.

Domain in the international zone

DSSM model that predicts the logarithm of the longest click on the Serpa. As negative examples, select Urla from past requests of the same user, and the maximum time between requests is no more than 7 minutes (super -cords for reformulations)

DSSM model with early binding, trained in reformulations, which predicts the logarithm of the longest click on the Serpa.

DSSM model trained on a reformal pool, which in the request, in addition to the request itself, receives 4 extensions of the XFDT with the largest weight

A model trained to predict an assessment of the USSR-DUMP-20190719 PRS-20190720 ALL-8-YEARS [T> 0.25] Crossentropy 20K 0.25 -s 0.8 -z 1.

Neuron document model for finding unexpected tin (for ex -)

Features calculated on url with request multitokens expansion

Features calculated on url with request multitokens expansion

A model trained to predict an assessment of the USSR-DUMP-20190719 PRS-20190720 ALL-8-YEARS [T> 0.25] Crossentropy 20K 0.25 -s 0.8 -z 1 and an educational study on assessments of relevance.

The porn of the picture calculated according to the porn N-grams in urlax with this picture

Number of destination hosts

Fraction of image pages from avito.ru host

The porn of the picture calculated according to the porn N-grams in the Urlah pages with this picture

The porn of the picture calculated according to the porn N-grams in urlax with this picture

Median of destination url lengths

Number of destination hosts

Fraction of image pages from avito.ru host

Fraction of image pages from vk.com host

The porn of the picture calculated according to the porn N-grams in the Urlah pages with this picture

The porn of the picture calculated according to the porn N-grams in urlax with this picture

Median of destination url lengths

Number of destination hosts

Fraction of image pages from avito.ru host

Fraction of image pages from vk.com host

The porn of the picture calculated according to the porn N-grams in the Urlah pages with this picture

The porn of the picture calculated according to the porn N-grams in urlax with this picture

Median of destination url lengths

Number of destination hosts

URL satisfies forum_detector regularly

The URL has an ancient date. Ancient news are recognized. Factor 1 if there is a year in Url <= 2007.

Model with the training of each trigram on '+' and '-' Urlah. It does not depend on the request.

The number of slashes in Url

The factor is calculated from the text of Url using the classifier of sequences Quality/Seq/GSK

Urlngramsmodel ranking factor in ERF

Factor about the presence of a symbol '?' In Url. It is zero if the Url has CGI parameters (more precisely: all duplicate have a symbol '?' In Url).

The number of 'Nebukv 'in Url

The length of the URL with an accuracy to the symbol. Disconnected in production.

The length of the URL, divided by 5

There are no numbers in Urla

Domain in the .ua zone

Domain is not in the .ru zone

Fraction of url's path that can be covered with trigrams from the query

Similar to Urla and request by cosine metric

Logdwelltime by the VEB model DSSM, trained in reformulations. It is also used in the ranking of ether.

Win (click longer than 60 seconds) on the DSSM video model trained in reformulations.

The largest tackling of the request and the domain part of Url, normalized by the length of the request

Logdwelltime by the VEB model DSSM. It is also used in the ranking of ether.

Logdwelltime by the VEB model DSSM.

The similarity of the T2q vehicles of the Title and the request a la Klakhman, trained by clicks

URL satisfies forum_detector regularly

URL satisfies forum_detector regularly

The URL has an ancient date. Ancient news are recognized. Factor 1 if there is a year in Url <= 2007.

The URL has an ancient date. Ancient news are recognized. Factor 1 if there is a year in Url <= 2007.

Model with the training of each trigram on '+' and '-' urlah. It does not depend on the request.

Model with the training of each trigram on '+' and '-' urlah. It does not depend on the request.

The number of slashes in Url

The number of slashes in Url

The factor is calculated from the text of Url using the classifier of sequences Quality/Seq/GSK

The factor is calculated from the text of Url using the classifier of sequences Quality/Seq/GSK

Urlngramsmodel ranking factor in ERF

Urlngramsmodel ranking factor in ERF

Domna in Zone .com

Domna in Zone .com

The length of the URL 'A, divided by 5

There are no numbers in Urla

Number 'Nebukv ' in Url

The length of the URL 'and with an accuracy to the symbol. Disconnected in production.

The factor about the presence of a symbol '? ' In Url. It is zero if the Url has CGI parameters (more precisely: all duplicate have a symbol '? ' In Url).

The length of the URL 'A, divided by 5

There are no numbers in Urla

Number 'Nebukv ' in Url

The length of the URL 'and with an accuracy to the symbol. Disconnected in production.

The factor about the presence of a symbol '? ' In Url. It is zero if the Url has CGI parameters (more precisely: all duplicate have a symbol '? ' In Url).

Domain in the .ua zone

Domain is not in the .ru zone

Domain in the .ua zone

Domain is not in the .ru zone

dot product of DocDssmLogDwellTimeBigramsL3Embedding for left and right urls

RecDssmSpyTitleDomainEmb12Dot

RecCFSharpDomainDot

DSSM model trained on clicks. Takes bigrams into account. Embeddings for documents are computed offline.

Linguistic boosting factor.

Linguistic boosting factor.

DSSM model of panther terms. Embed -expanded bar are used for L2. Top5 QFUF of Cosine proximity to the Embed document is filtered. As a factor, a minimum of the weight of the expansion of proximity is used.

DSSM model of panther terms. Embed -expanded bar are used for L2. Top5 QFUF of Cosine proximity to the Embed document is filtered. Next, the weighed amount of proximity is calculated, the weight of the expansion is used in the quality of weight, normalized for the amount of the weights of filtered extensions.

DSSM model of panther terms. Embed -expanded bar are used for L2. As a factor, the average proximity to the Embed of the document is used.

DSSM model of panther terms. Embed -expanded bar are used for L2. As a factor, a minimum of the weight of the expansion of proximity is used.

Meta:Resid metafactor on web_itditp:DssmLogDwellTimeBigramsDot(606)

SD:DFT_GREATER_CNT metafactor on web_itditp:DssmBoostingXfOneSeAmSsHardDot(657)

Meta:EpsHashShare metafactor on web_itditp:UrlNGramsModel(103)

Meta:ResidMin metafactor on web_itditp:DssmLogDwellTimeBigramsDot(606)

MutualSerp:DFT_MAX metafactor on web_itditp:DssmBoostingXfWtd45Dot(632)

Avg metafactor on IsNotCgi(899)

Max metafactor on GskUrlModel(487)

The number of direct descendants of the URL on PRS designed by the text URLA; A more detailed description in wiki

The number of descendants of the URL on PRS calculated by the text URLA; A more detailed description in wiki

The number of direct URLs on PRS designed by the URLA text; A more detailed description in wiki

The average on PRS value of the expression (1 - ISFORUM) * (1 - DiversityCategreview)

The average on PRS value of the expression (1 - ruswordsintitle) * (1 - GSKURLMODEL)

Position XFDTSHOWALMAXFELDSET2BM15FLOGK0001 * SimpleClickMixMatchHTEDVALUE among all documents on PRS

Position (1- Fieldset3bclmweightedflogw0k0001) * (1 - DSSMLONGMIDLESHORDSHARDCLICS) Among all documents on PRS

Max metafactor on Production:DssmMiddleVsShortLongHardNoClicks(1221)

Max metafactor on Production:DssmLogDwellTimeBigrams(1338)

Max metafactor on Production:XfDtShowAllMaxFFieldSetUTBm15FLogW0(1027)

DFT_GREATER_CNT metafactor on Production:DssmLogDwellTimeBigrams(1338)

DFT_SUM_WF_NORM_SUM_W metafactor on Production:DssmLogDwellTimeBigrams(1338)

DFT_GREATER_CNT metafactor on Production:RequestWithRegionNameFieldSet2Bm15FLogK0001(1264)

Similar documents, type of similarity: mutualserp. SUMWFNORMSUMW AGGENT DSSMBIGRAMSQUERYDERIVATIMAX factor

Similar documents, type of similarity: mutualserp. Max Aggregion DSSMLOGDWELTIMEBIGRAMS Factor

Similar documents, type of similarity: mutualserp. Max Aggregation of Queryurllcs factor

Similar documents, type of similarity: mutualserp. Sumwfnormsumw DSSMLONGVSMIDLESHORTNOCLICS AGGENT

Similar documents, type of similarity: mutualserp. Max Agnigation DSSMLONGMIDLESHORDSHARDCLICS Factor

We count the coating of the letter 3 grams URLA, 3 grams from PRS that are found at least in 3 different hosts. Only Latin symbols and Path part of Url are taken into account

We count the cover of the letter 4 grams URLA, 4 grams from PRS that are found at least in 3 different hosts

Meta:Avg metafactor on web_production:DssmQueryDwellTime(1406)

Meta:Rmse metafactor on web_production:DssmLogDtBigramsAMHardQueriesNoClicks(1523)

Meta:ResidMax metafactor on web_production:DssmLogDtBigramsAMHardQueriesNoClicksMixed(1596)

Meta:EpsHashShare metafactor on web_production:DssmLogDtBigramsAMHardQueriesNoClicksMixed(1596)

Meta:Resid metafactor on web_production:DssmQueryDwellTime(1406)

Meta:Resid metafactor on web_production:DssmLogDtBigramsAMHardQueriesNoClicksMixed(1596)

Fract metafactor on NeuroTextModelLongClickPredictorByWordAndBigramCountersWithSSHards(1845).

Resid metafactor on NeuroTextModelLongClickPredictorByWordAndBigramCountersWithSSHards(1845).

EpsHashShare metafactor on NeuroTextModelLongClickPredictorByWordAndBigramCountersWithSSHards(1845).

Dispersion of the Addtime factor in terms of PRS, where the mask of words in the URL+Title document that coincided as a synonym or better, the same as the document

DBMNUMBERS factor dispersion in terms of PRS, where are the words mask in the URL+Title document that coincided as a synonym or better, the same as the document

Dispersion of the DoubleFrcallwcmmatch95AVGVALUE factor in terms of PRS, where a mask of words in the URL+Title document that coincided as a synonym or better, the same as a document

The average value of the DoubleFrCallwcmmatch95AVGVALUE factor in PRS, where the words mask in the URL+Title document that coincided as a synonym or better, the same as the document

The dispersion of the OneClickFrCXFSPPERWORDCMAXMATCHMIN factor in terms of PRS, where the words mask in the URL+Title document that coincided as a synonym or better, the same as the document

The average value of the OneClickFrCXFSPPERWORDCMAXMATCHMIN factor in terms of PRS, where a mask of words in the URL+Title document that coincided as a synonym or better, is the same as that of the document

The dispersion of the factor QFUFALLSUMWFSUMWQURYDWELTIMEXMATCHWEIGHTEDVALE in PRS, where the words mask in the URL+Title document, coincided with a synonym or better, are the same as the document of

The minimum value of the DSSMQUERYDWELTIME factor in PRS, where the mask of words in the URL+Title document that coincided or better, is the same as the document

The average value of the QFUFUFALLMAXWFLINKANNINNINNINNINNINNDILLMATCHVALUE factor in terms of PRS, where a mask of words in the URL+Title document that coincided or better, the same as the document

The average value of the Randomloghostismusicavg factor in PRS, where the mask of words in the URL+Title document that coincided as a synonym or better, is the same as the document

The average value of the factor Randomlogownermetaweb1099Web1219Productinvposlogavg in part of PRS, where a mask of words in the URL+Title document that coincided or better, is the same as the document of

The average value of the RandomlogownerdomrandomlogQuevghaspaymentslogavg factor in PRS, where the words mask in the URL+Title document that coincided or better, the same as the document is

The average value of the QFUFFIFILTEDBYXFONESETOPSUMWBODYMINWIDOWINDOWSIZE factor in PRS, where the words mask in the URL+Title document that coincided or better, the same as the document is

HostShare:HostShare metafactor on web_production:UrlDomainFraction(294)

Meta:Resid metafactor on web_production:DssmCtrEngSsHard(1855)

bert model which predicts 1rel 2vital 0other for arabic alice music search scenario

slot for support of two parallel aramusic models

small-bert-model sbr:1721013142 predict Predict_sinsig_mse_1502766203_standartized_mse_target - Distillation of the sinsig mse bert model 1502766203

small-bert-model sbr:1721013142 predict Predict_dbd_mse_1502778723_standartized_mse_target Distillation of the dbd mse bert model 1502778723

small-bert-model sbr:1721013142 predict Predict_sinsig_fresh_20200118_0502_1528253243_standartized_mse_target Distillation of the fresh bert model 1528253243

small-bert-model sbr:1721013142 predict Predict_sinsig_ce_multitarget_012_1511368337_standartized_mse_target Distillation of the sinsig ce multitarget bert model 1511368337, head 0.12 threshold

small-bert-model sbr:1721013142 predict Predict_sinsig_ce_multitarget_025_1511368337_standartized_mse_target Distillation of the sinsig ce multitarget bert model 1511368337, head 0.25 threshold

small-bert-model sbr:1721013142 predict Predict_sinsig_ce_multitarget_05_1511368337_standartized_mse_target Distillation of the sinsig ce multitarget bert model 1511368337, head 0.5 threshold

small-bert-model sbr:1721013142 predict Predict_proxima_large_mse_1545302456_standartized_mse_target Distillation of the proxima mse bert model 1545302456

small-bert-model sbr:1721013142 predict Predict_click_pers_ce_1534051635_standartized_mse_target Distillation of the click pers ce bert model 1534051635

small-bert-model sbr:1721013142 predict Predict_click_odd_mse_1512795366_standartized_mse_target Distillation of the click odd mse bert model 1512795366

split-bert-model sbr:2005741938 predict Predict_mse_prediction_1628966206_proxima_standartized Split distillation of the proxima mse bert model 1628966206

split-bert-model sbr:2005741938 predict Predict_ce_0_12_1633847052_sinsig_standartized Split distillation of the sinsig ce multitarget bert model 1633847052, head 0.12 threshold

split-bert-model sbr:2005741938 predict Predict_mse_Predict_ce_0_25_1633847052_sinsig_standartized Split distillation of the sinsig ce multitarget bert model 1633847052, head 0.25 threshold

split-bert-model sbr:2005741938 predict Predict_mse_Predict_ce_0_5_1633847052_sinsig_standartized Split distillation of the sinsig ce multitarget bert model 1633847052, head 0.5 threshold

split-bert-model sbr:2005741938 predict mse_Predict_ce_0_78_1633847052_sinsig_standartized Split distillation of the sinsig ce multitarget bert model 1633847052, head 0.78 threshold

split-bert-model sbr:2005741938 predict Predict_mse_Predict_ce_1_3_1633847052_sinsig_standartized Split distillation of the sinsig ce multitarget bert model 1633847052, head 1.3 threshold

split-bert-model sbr:2005741938 predict Predict_mse_Predict_ce_2_0_1633847052_sinsig_standartized Split distillation of the sinsig ce multitarget bert model 1633847052, head 2.0 threshold

split-bert-model sbr:2005741938 predict Predict_mse_prediction_1625097377_proxima_standartized Split distillation of the proxima mse bert model 1625097377

split-bert-model sbr:2005741938 predict Predict_mse_prediction_1633307071_dbd_standartized Split distillation of the dbd mse bert model 1633307071

split-bert-model sbr:2005741938 predict prediction_1528253243_sinsig_fresh_20200118_0502_standartized Split distillation of the fresh bert model 1528253243

split-bert-model sbr:2005741938 predict prediction_1644380449_is_pirate_0807_standartized Split distillation of the is_pirate bert model 1644380449

split-bert-model sbr:2005741938 predict Predict_oct_large_1871529228_sinsig_relev10_mse_stand_mse Split distillation of the nov-large model with relev10 1871529228

split-bert-model sbr:2005741938 predict Predict_oct_large_1872243553_proxima_relev10_mse_stand_mse Split distillation of the nov-large model with relev10 1872243553

split-bert-model sbr:2005741938 predict Predict_xLarge_prediction_nov_lav_1990027087_standartized_mse Split distillation of the xlarge model with relev10 1990027087

split-bert-model sbr:2005741938 predict Predict_xLarge_prediction_nov_proxima_1970068024_standartized_mse Split distillation of the nov-large model with relev10 1970068024

split-bert-model sbr:2005741938 predict Predict_Large_predict_target_fin_law_1967416198_standartized_mse Split distillation of the large model 1967416198

split-bert-model sbr:2005741938 predict Predict_Large_predict_target_med_doc_1967182618_standartized_mse Split distillation of the large model 1967182618

split-bert-model sbr:2005741938 predict Predict_Large_predict_target_sos_1969262884_standartized_mse Split distillation of the large model 1969262884

sbr:2411087272 splitv3 head Predict_jul_xlarge_lav_with_platform_2344793612_stand_mse

sbr:2411087272 splitv3 head Predict_jul_xlarge_sinsig_baskets_with_platform_2339818891_stand_mse

berts_storage:2022/02/artmironov/2831823537 splitv4 head Predict_bert_650_merge_platform_no_trans_v1_2784077050_stand_mse

bert model 2021/09/boyalex/2405042847 head: Predict_jul_xlarge_sinsig_baskets_2339818891_stand_mse

bert model 2021/09/boyalex/2405042847 head: Predict_large_cs_clever_clicks_2360931838_stand_mse

bert model 2021/09/boyalex/2405042847 head: Predict_large_google_2334139725_stand_mse

bert model 2021/09/boyalex/2405042847 head: Predict_pq_large_2394064809_stand_mse

bert model 2021/09/boyalex/2405042847 head: Predict_jul_xlarge_cs_sinsig_full_2394990987_stand_mse

bert model 2021/09/boyalex/2405042847 head: Predict_jul_xlarge_cs_apscore_2397363137_stand_mse