[WIP] CoNLL-2003 dataset -Ner, Chunk and POS tagger #170
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,124 @@ | ||
| dataset: conll2003 | ||
| templates: | ||
| 3b777e30-bdd1-4c4a-b5d9-3372c7a756f4: !Template | ||
| id: 3b777e30-bdd1-4c4a-b5d9-3372c7a756f4 | ||
| jinja: "{% set _ner_lable_dict = ({\n0:\"O\",\n1:\"B-PER\",\n2:\"I-PER\",\n3:\"\ | ||
| B-ORG\",\n4:\"I-ORG\",\n5:\"B-LOC\",\n6:\"I-LOC\",\n7:\"B-MISC\",\n8:\"I-MISC\"\ | ||
| \n}) %}\nGenerate named entities from the following sentence. \n{{\"\"}}\n{%\ | ||
| \ for i in tokens -%}\n {{- \" \" if not loop.last else \"\" -}}\n {{\ | ||
| \ i }}\n{% endfor %} \n|||\n{% set flag = 0 %}\n{% set outer_cnt = namespace(value=0)\ | ||
| \ -%}\n{% for tok in tokens -%}\n {% set inner_cnt = namespace(value=0) -%}\n\ | ||
| \ {% for lable in ner_tags -%}\n {% if outer_cnt.value == inner_cnt.value\ | ||
| \ -%}\n {% if flag != 0 -%}\n \n \ | ||
| \ {% endif -%}\n {% set flag = 1 -%}\n {{tok}}:{{ _ner_lable_dict[lable]\ | ||
| \ }}\n {% endif -%}\n {% set inner_cnt.value = inner_cnt.value\ | ||
| \ + 1 -%}\n {% endfor -%} \n {% set outer_cnt.value = outer_cnt.value\ | ||
| \ + 1 -%}\n{% endfor -%} \n\n" | ||
| name: ner_flat_question_without_lable | ||
| reference: Natural question | ||
| 6345fd1a-5272-4a8d-b5b2-02c1d837e521: !Template | ||
| id: 6345fd1a-5272-4a8d-b5b2-02c1d837e521 | ||
| jinja: "{% set _pos_lable_dict = ({\n0:'\"',\n1:\"''\",\n2:\"#\",\n3:\"\\$\",\n\ | ||
| 4:\"(\",\n5:\")\",\n6:\",\",\n7:\".\",\n8:\":\",\n9:\"``\",\n10:\"CC\",\n11:\"\ | ||
| CD\",\n12:\"DT\",\n13:\"EX\",\n14:\"FW\",\n15:\"IN\",\n16:\"JJ\",\n17:\"JJR\"\ | ||
| ,\n18:\"JJS\",\n19:\"LS\",\n20:\"MD\",\n21:\"NN\",\n22:\"NNP\",\n23:\"NNPS\"\ | ||
| ,\n24:\"NNS\",\n25:\"NN|SYM\",\n26:\"PDT\",\n27:\"POS\",\n28:\"PRP\",\n29:\"\ | ||
| PRP\\$\",\n30:\"RB\",\n31:\"RBR\",\n32:\"RBS\",\n33:\"RP\",\n34:\"SYM\",\n35:\"\ | ||
| TO\",\n36:\"UH\",\n37:\"VB\",\n38:\"VBD\",\n39:\"VBG\",\n40:\"VBN\",\n41:\"\ | ||
| VBP\",\n42:\"VBZ\",\n43:\"WDT\",\n44:\"WP\",\n45:\"WP$\",\n46:\"WRB\"\n}) %}\n\ | ||
| \n\nGenerate parts of speech from the following sentence. \n{% set flag = 0\ | ||
| \ %}\n{% for i in tokens -%}\n {% if flag != 0 -%}\n \n {%\ | ||
| \ endif -%}\n {% set flag = 1 -%}\n {{ i }}\n{% endfor %} \n|||\n{% set\ | ||
| \ flag = 0 %}\n{% set outer_cnt = namespace(value=0) -%}\n{% for tok in tokens\ | ||
| \ -%}\n {% set inner_cnt = namespace(value=0) -%}\n {% for lable in pos_tags\ | ||
| \ -%}\n {% if outer_cnt.value == inner_cnt.value -%}\n {%\ | ||
| \ if flag != 0 -%}\n \n {% endif -%}\n \ | ||
| \ {% set flag = 1 -%}\n {{tok}}:{{ _pos_lable_dict[lable] }}\n\ | ||
| \ {% endif -%}\n {% set inner_cnt.value = inner_cnt.value + 1\ | ||
| \ -%}\n {% endfor -%} \n {% set outer_cnt.value = outer_cnt.value + 1\ | ||
| \ -%}\n{% endfor -%} " | ||
| name: pos_flat_question_without_label | ||
| reference: Natural Question | ||
| 71eadc14-9533-43a8-82dc-6d6a171119ef: !Template | ||
| id: 71eadc14-9533-43a8-82dc-6d6a171119ef | ||
| jinja: "{% set _chunk_lable_dict = ({\n0:\"O\",\n1:\"B-ADJP\",\n2:\"I-ADJP\",\n\ | ||
| 3:\"B-ADVP\",\n4:\"I-ADVP\",\n5:\"B-CONJP\",\n6:\"I-CONJP\",\n7:\"B-INTJ\",\n\ | ||
| 8:\"I-INTJ\",\n9:\"B-LST\",\n10:\"I-LST\",\n11:\"B-NP\",\n12:\"I-NP\",\n13:\"\ | ||
| B-PP\",\n14:\"I-PP\",\n15:\"B-PRT\",\n16:\"I-PRT\",\n17:\"B-SBAR\",\n18:\"I-SBAR\"\ | ||
| ,\n19:\"B-UCP\",\n20:\"I-UCP\",\n21:\"B-VP\",\n22:\"I-VP\"\n}) %}\nGenerate\ | ||
| \ chunk tag from the following sentence. The chunk tags are\n{% for k,v in _chunk_lable_dict.items()\ | ||
| \ -%}\n {{ v }}\n {{- \", \" if not loop.last else \"\" -}}\n {{- \"\ | ||
| \\n\" if loop.last -}}\n{% endfor %} \n{% for i in tokens -%}\n {{- \" \"\ | ||
| \ if not loop.last else \"\" -}}\n {{ i }}\n{% endfor %} \n|||\n{% set flag\ | ||
| \ = 0 %}\n{% set outer_cnt = namespace(value=0) -%}\n{% for tok in tokens -%}\n\ | ||
| \ {% set inner_cnt = namespace(value=0) -%}\n {% for lable in ner_tags\ | ||
| \ -%}\n {% if outer_cnt.value == inner_cnt.value -%}\n {%\ | ||
| \ if flag != 0 -%}\n \n {% endif -%}\n \ | ||
| \ {% set flag = 1 -%}\n {{tok}}:{{ _chunk_lable_dict[lable]\ | ||
| \ }}\n {% endif -%}\n {% set inner_cnt.value = inner_cnt.value\ | ||
| \ + 1 -%}\n {% endfor -%} \n {% set outer_cnt.value = outer_cnt.value\ | ||
| \ + 1 -%}\n{% endfor -%} \n\n" | ||
| name: chunk_flat_question_with_label | ||
| reference: Natural Question | ||
| 8613a9bb-94c7-4b91-998c-3c298087d719: !Template | ||
| id: 8613a9bb-94c7-4b91-998c-3c298087d719 | ||
| jinja: "{% set _ner_lable_dict = ({\n0:\"O\",\n1:\"B-PER\",\n2:\"I-PER\",\n3:\"\ | ||
| B-ORG\",\n4:\"I-ORG\",\n5:\"B-LOC\",\n6:\"I-LOC\",\n7:\"B-MISC\",\n8:\"I-MISC\"\ | ||
| \n}) %}\nGenerate named entities from the following sentence. The named entities\ | ||
| \ are\n{% for k,v in _ner_lable_dict.items() -%}\n {{ v }}\n {{- \", \"\ | ||
| \ if not loop.last else \"\" -}}\n {{- \"\\n\" if loop.last -}}\n{% endfor\ | ||
| \ %} \n{% for i in tokens -%}\n {{- \" \" if not loop.last else \"\" -}}\n\ | ||
| \ {{ i }}\n{% endfor %} \n|||\n{% set flag = 0 %}\n{% set outer_cnt = namespace(value=0)\ | ||
| \ -%}\n{% for tok in tokens -%}\n {% set inner_cnt = namespace(value=0) -%}\n\ | ||
| \ {% for lable in ner_tags -%}\n {% if outer_cnt.value == inner_cnt.value\ | ||
| \ -%}\n {% if flag != 0 -%}\n \n \ | ||
| \ {% endif -%}\n {% set flag = 1 -%}\n {{tok}}:{{ _ner_lable_dict[lable]\ | ||
| \ }}\n {% endif -%}\n {% set inner_cnt.value = inner_cnt.value\ | ||
| \ + 1 -%}\n {% endfor -%} \n {% set outer_cnt.value = outer_cnt.value\ | ||
| \ + 1 -%}\n{% endfor -%} \n\n" | ||
| name: ner_flat_question_with_lable | ||
| reference: Natural question | ||
| 87bb05ff-f6bf-4c0d-bbcc-56f75095f4a1: !Template | ||
| id: 87bb05ff-f6bf-4c0d-bbcc-56f75095f4a1 | ||
| jinja: "{% set _chunk_lable_dict = ({\n0:\"O\",\n1:\"B-ADJP\",\n2:\"I-ADJP\",\n\ | ||
|
|
||
| 3:\"B-ADVP\",\n4:\"I-ADVP\",\n5:\"B-CONJP\",\n6:\"I-CONJP\",\n7:\"B-INTJ\",\n\ | ||
| 8:\"I-INTJ\",\n9:\"B-LST\",\n10:\"I-LST\",\n11:\"B-NP\",\n12:\"I-NP\",\n13:\"\ | ||
| B-PP\",\n14:\"I-PP\",\n15:\"B-PRT\",\n16:\"I-PRT\",\n17:\"B-SBAR\",\n18:\"I-SBAR\"\ | ||
| ,\n19:\"B-UCP\",\n20:\"I-UCP\",\n21:\"B-VP\",\n22:\"I-VP\"\n}) %}\nGenerate\ | ||
| \ chunk tag from the following sentence. \n{% for i in tokens -%}\n {{- \"\ | ||
| \ \" if not loop.last else \"\" -}}\n {{ i }}\n{% endfor %} \n|||\n{% set\ | ||
| \ flag = 0 %}\n{% set outer_cnt = namespace(value=0) -%}\n{% for tok in tokens\ | ||
| \ -%}\n {% set inner_cnt = namespace(value=0) -%}\n {% for lable in ner_tags\ | ||
| \ -%}\n {% if outer_cnt.value == inner_cnt.value -%}\n {%\ | ||
| \ if flag != 0 -%}\n \n {% endif -%}\n \ | ||
| \ {% set flag = 1 -%}\n {{tok}}:{{ _chunk_lable_dict[lable]\ | ||
| \ }}\n {% endif -%}\n {% set inner_cnt.value = inner_cnt.value\ | ||
| \ + 1 -%}\n {% endfor -%} \n {% set outer_cnt.value = outer_cnt.value\ | ||
| \ + 1 -%}\n{% endfor -%} \n\n" | ||
| name: chunk_flat_question_without_label | ||
| reference: Natural question | ||
| d10ab706-e2ea-4b7a-b6b4-371aa0ab483b: !Template | ||
| id: d10ab706-e2ea-4b7a-b6b4-371aa0ab483b | ||
| jinja: "{% set _pos_lable_dict = ({\n0:'\"',\n1:\"''\",\n2:\"#\",\n3:\"\\$\",\n\ | ||
| 4:\"(\",\n5:\")\",\n6:\",\",\n7:\".\",\n8:\":\",\n9:\"``\",\n10:\"CC\",\n11:\"\ | ||
| CD\",\n12:\"DT\",\n13:\"EX\",\n14:\"FW\",\n15:\"IN\",\n16:\"JJ\",\n17:\"JJR\"\ | ||
| ,\n18:\"JJS\",\n19:\"LS\",\n20:\"MD\",\n21:\"NN\",\n22:\"NNP\",\n23:\"NNPS\"\ | ||
| ,\n24:\"NNS\",\n25:\"NN|SYM\",\n26:\"PDT\",\n27:\"POS\",\n28:\"PRP\",\n29:\"\ | ||
| PRP\\$\",\n30:\"RB\",\n31:\"RBR\",\n32:\"RBS\",\n33:\"RP\",\n34:\"SYM\",\n35:\"\ | ||
| TO\",\n36:\"UH\",\n37:\"VB\",\n38:\"VBD\",\n39:\"VBG\",\n40:\"VBN\",\n41:\"\ | ||
| VBP\",\n42:\"VBZ\",\n43:\"WDT\",\n44:\"WP\",\n45:\"WP$\",\n46:\"WRB\"\n}) %}\n\ | ||
| \n\nGenerate parts of speech from the following sentence. The parts of speech\ | ||
| \ tags are\n{% for k,v in _pos_lable_dict.items() -%}\n {{ v }}\n {{-\ | ||
| \ \", \" if not loop.last else \"\" -}}\n {{- \"\\n\" if loop.last -}}\n\ | ||
| {% endfor %} \n{% set flag = 0 %}\n{% for i in tokens -%}\n {% if flag !=\ | ||
| \ 0 -%}\n \n {% endif -%}\n {% set flag = 1 -%}\n {{ i\ | ||
| \ }}\n{% endfor %} \n|||\n{% set flag = 0 %}\n{% set outer_cnt = namespace(value=0)\ | ||
| \ -%}\n{% for tok in tokens -%}\n {% set inner_cnt = namespace(value=0) -%}\n\ | ||
| \ {% for lable in pos_tags -%}\n {% if outer_cnt.value == inner_cnt.value\ | ||
| \ -%}\n {% if flag != 0 -%}\n \n \ | ||
| \ {% endif -%}\n {% set flag = 1 -%}\n {{tok}}:{{ _pos_lable_dict[lable]\ | ||
| \ }}\n {% endif -%}\n {% set inner_cnt.value = inner_cnt.value\ | ||
| \ + 1 -%}\n {% endfor -%} \n {% set outer_cnt.value = outer_cnt.value\ | ||
| \ + 1 -%}\n{% endfor -%} " | ||
| name: pos_flat_question_with_lable | ||
| reference: ' Natural question' | ||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This looks very complex. If there a reason you can't use loop index?
https://stackoverflow.com/questions/1567291/get-loop-index-of-outer-loop
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done.