2019-08-09工作進展3

  1. 對比關鍵詞沒有權重的dssm模型的效果

train_query : hs_dssm_dic_query_1 - | id | words_mainse_ids | se_keyword |
train_title : hs_dssm_dic_title_3 - | id | words_mainse_ids | title |


inference_query : hs_dssm_dic_query_inf_1 - | id | words_mainse_ids | query |
inference_title : hs_dssm_dic_title_inf_1 - | id | words_mainse_ids | title |


train : hs_train_data_dssm_v2_5 : | se_keyword_mainse_ws | title_mainse_ws | label |
inference : hs_tmp_207 : | query_id | video_id | query_ws | video_ws |

drop table hs_tmp_206;
yes
create table hs_tmp_206
as select c.se_keyword_mainse_ws, d.emb as title_mainse_ws, c.label from
(select a.*, b.emb as se_keyword_mainse_ws from (select * from hs_dssm_train_v2_0)a left join (select * from hs_tmp_202)b on a.query_id == b.id)c left join (select * from hs_tmp_203)d on c.item_id == d.id;

create table hs_tmp_209 as
select c.se_keyword_mainse_ws, d.title_mainse_ws, c.label from
(select a.*, b.se_keyword_mainse_ws from (select * from hs_dssm_train_v2_0)a join (select id as query_id, search_kg:alinlp_word_embedding(hs_return_clean(se_keyword), "100", "CONTENT_SEARCH") as se_keyword_mainse_ws from hs_dssm_dic_query_1)b on a.query_id == b.query_id)c join (select id as video_id, search_kg:alinlp_word_embedding(hs_return_clean(title), "100", "CONTENT_SEARCH") as title_mainse_ws from hs_dssm_dic_title_3)d on c.item_id == d.video_id;

http://logview.odps.aliyun-inc.com:8080/logview/?h=http://service-corp.odps.aliyun-inc.com/api&p=graph_embedding&i=20190809100830603ga3ywtyi2&token=TWRROEJuNUxKWGEyK3BXTXdVTUZaZU05b21ZPSxPRFBTX09CTzoxMjkzMzAzOTgzMjUxNTQ4LDE1NjU5NTAxMTEseyJTdGF0ZW1lbnQiOlt7IkFjdGlvbiI6WyJvZHBzOlJlYWQiXSwiRWZmZWN0IjoiQWxsb3ciLCJSZXNvdXJjZSI6WyJhY3M6b2RwczoqOnByb2plY3RzL2dyYXBoX2VtYmVkZGluZy9pbnN0YW5jZXMvMjAxOTA4MDkxMDA4MzA2MDNnYTN5d3R5aTIiXX1dLCJWZXJzaW9uIjoiMSJ9

?著作權歸作者所有,轉載或內容合作請聯(lián)系作者
【社區(qū)內容提示】社區(qū)部分內容疑似由AI輔助生成,瀏覽時請結合常識與多方信息審慎甄別。
平臺聲明:文章內容(如有圖片或視頻亦包括在內)由作者上傳并發(fā)布,文章內容僅代表作者本人觀點,簡書系信息發(fā)布平臺,僅提供信息存儲服務。

相關閱讀更多精彩內容

  • graph_embedding.jl_jingyan_query_related_top_query_detail...
    Songger閱讀 435評論 0 0
  • set odps.sql.mapper.split.size=1;昨天工作: 重新處理數(shù)據(jù)集,給一些重要的關鍵詞,...
    Songger閱讀 293評論 0 0
  • rm -rf ../../origin_deep_cluster_odps_8.tar.gztar -cvzf ....
    Songger閱讀 343評論 0 0
  • 上周五工作: 使用手肘法測試top 1w query最佳聚類類別數(shù),但是在這一數(shù)據(jù)中,sse斜率變化不大,分析的原...
    Songger閱讀 370評論 0 0
  • 昨天工作:使用類目過濾信息對dssm網絡進行finetune,正樣本采用的類目過濾之后剩下的數(shù)據(jù),負樣本采用的是d...
    Songger閱讀 206評論 0 0

友情鏈接更多精彩內容