- 对比关键词没有权重的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;
