how to use seq2seq to decode concatenated string

Asked Feb 03 '19 at 08:55

Active Feb 03 '19 at 08:55

Viewed 54 times

Am trying to decode a concatenated String like below ...

 SQCB7A750BATWE SQ CB 7 A 750 B A T WE 
 PT05A1219PY023 PT 05 A 12 19 P Y 023  
 PT55A1019PX02  PT 55 A 10 19 P X 02  
 PT33SE2215SW023    PT 33 SE 22 15 S W 023  
 PT05A2216PW023(LC) PT 05 A 22 16 P W 023 (LC)

am looking for a smarter way rather than hard-coded rules as the input will have variations(number of characters and digits), I came across SEQ2SEQ model and I want to know if it's possible to use it in such problem I already followed some tutorials to get a taste of it, but the results weren't even close it also seems there are 2 approaches character level and word level as per this tutorial

Character level:

Input sentence: SQCACA333BA71A
Decoded sentence: P 9(PDD366AZ2IDD4K )F)F(L)L)1)1)1)        6A
-
Input sentence: SQCAAC152DA71A
Decoded sentence: P 9(PDD366AZ2IDD4K )F)F(L)L)1)1)1)        6A

am still trying to implement the word level, but I'd like to know if the problem can be solved using this approach (seq2seq)

asked Feb 03 '19 at 08:55

Exorcismus

2,243
1
35
68

Do you have a fixed number of possible words? – xashru Feb 03 '19 at 10:13
no, because the number of words varies on the input, and this is won't be fixed – Exorcismus Feb 03 '19 at 10:36
I mean in the vocabulary. Do you know how many possible words you have in the vocabulary? – xashru Feb 03 '19 at 10:53
@xashru, no, won't be known – Exorcismus Feb 03 '19 at 11:06

how to use seq2seq to decode concatenated string

0 Answers0