SQLnet 代碼閱讀筆記

table 1-10015132-11 的樣子:

player | no. | nationality | position | years in toronto | school/club team

[Antonio Lang, 21, United States, Guard-Forward, 1999-2000, Duke]

[Voshon Lenard, 2, United States, Guard, 2002-03, Minnesota]

[Martin Lewis, 32, 44, United States, Guard-Forward, 1996-97, Butler CC (KS)]

[Brad Lohaus, 33, United States, Forward-Center, 1996, Iowa]

[Art Long, 42, United States, Forward-Center, 2002-03, Cincinnati]

[John Long, 25, United States, Guard, 1996-97, Detroit]

[Kyle Lowry, 3, United States, Guard, 2012-Present, Villanova]

query和sql的樣子:

What position does the player who played for butler cc (ks) play?

SELECT position WHERE school/club team EQL butler cc (ks)

{agg: 0, sel: 3, conds: [[5, 0, Butler CC (KS)]]}

其中3是第四列position,5是第六列school/club team

對於column的embedding:

因為層次是這樣:table - column - column_words

所以是採用column_words過LSTM的最後一個state作為一個column的表示

最終參與attention計算的維度是batch_size, max_column_number_of_one_table, lstm_hidden_size]


推薦閱讀:

學習筆記CB002:詞幹提取、詞性標註、中文切詞、文檔分類
Learning to Skim Text 閱讀筆記
016【NLP】word2vec新手項目
torchtext入門教程,輕鬆玩轉文本數據處理
show and tell 代碼閱讀筆記

TAG:自然語言處理 |