Hugging Face's logo

ShinoharaHare
/
AICUP-2023-Spring-NLP

Model card Files
xet
Community
ShinoharaHare commited on
Commit
62621fc
·
1 Parent(s): bd96138

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. data/sentence_retrieval/pairwise_ranking/config.json +11 -0
  2. data/sentence_retrieval/pairwise_ranking/dataset_dict.json +1 -0
  3. data/sentence_retrieval/pairwise_ranking/test/data-00000-of-00001.arrow +3 -0
  4. data/sentence_retrieval/pairwise_ranking/test/dataset_info.json +50 -0
  5. data/sentence_retrieval/pairwise_ranking/test/state.json +13 -0
  6. data/sentence_retrieval/pairwise_ranking/train/data-00000-of-00001.arrow +3 -0
  7. data/sentence_retrieval/pairwise_ranking/train/dataset_info.json +50 -0
  8. data/sentence_retrieval/pairwise_ranking/train/state.json +13 -0
data/sentence_retrieval/pairwise_ranking/config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "claim_dataset_path": "data/claim_dataset_v2",
3
+ "wiki_dataset_path": "data/wiki_dataset",
4
+ "output_dir": "data/sentence_retrieval/pairwise_ranking_v2",
5
+ "top_k": 3,
6
+ "min_score": 10.0,
7
+ "return_by_noun": true,
8
+ "merge_adjacent": true,
9
+ "return_unmerged": true,
10
+ "seed": 42
11
+ }
data/sentence_retrieval/pairwise_ranking/dataset_dict.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"splits": ["train", "test"]}
data/sentence_retrieval/pairwise_ranking/test/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23178a383b9025f46d18b1087100d7e48470f396e844724b241f96181caeeee7
3
+ size 8388656
data/sentence_retrieval/pairwise_ranking/test/dataset_info.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "generator",
3
+ "citation": "",
4
+ "config_name": "default",
5
+ "dataset_size": 1907090,
6
+ "description": "",
7
+ "download_checksums": {},
8
+ "download_size": 0,
9
+ "features": {
10
+ "positive_claim": {
11
+ "dtype": "string",
12
+ "_type": "Value"
13
+ },
14
+ "positive_sentence": {
15
+ "feature": {
16
+ "dtype": "string",
17
+ "_type": "Value"
18
+ },
19
+ "_type": "Sequence"
20
+ },
21
+ "negative_claim": {
22
+ "dtype": "string",
23
+ "_type": "Value"
24
+ },
25
+ "negative_sentence": {
26
+ "feature": {
27
+ "dtype": "string",
28
+ "_type": "Value"
29
+ },
30
+ "_type": "Sequence"
31
+ }
32
+ },
33
+ "homepage": "",
34
+ "license": "",
35
+ "size_in_bytes": 1907090,
36
+ "splits": {
37
+ "train": {
38
+ "name": "train",
39
+ "num_bytes": 1907090,
40
+ "num_examples": 11620,
41
+ "dataset_name": "generator"
42
+ }
43
+ },
44
+ "version": {
45
+ "version_str": "0.0.0",
46
+ "major": 0,
47
+ "minor": 0,
48
+ "patch": 0
49
+ }
50
+ }
data/sentence_retrieval/pairwise_ranking/test/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "1a6a5afe498a255c",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": "train"
13
+ }
data/sentence_retrieval/pairwise_ranking/train/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a46b3bd8e995b97ce1cdd75414ed49230e62debc730b30200f37329810e2b07
3
+ size 74367848
data/sentence_retrieval/pairwise_ranking/train/dataset_info.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "generator",
3
+ "citation": "",
4
+ "config_name": "default",
5
+ "dataset_size": 1907090,
6
+ "description": "",
7
+ "download_checksums": {},
8
+ "download_size": 0,
9
+ "features": {
10
+ "positive_claim": {
11
+ "dtype": "string",
12
+ "_type": "Value"
13
+ },
14
+ "positive_sentence": {
15
+ "feature": {
16
+ "dtype": "string",
17
+ "_type": "Value"
18
+ },
19
+ "_type": "Sequence"
20
+ },
21
+ "negative_claim": {
22
+ "dtype": "string",
23
+ "_type": "Value"
24
+ },
25
+ "negative_sentence": {
26
+ "feature": {
27
+ "dtype": "string",
28
+ "_type": "Value"
29
+ },
30
+ "_type": "Sequence"
31
+ }
32
+ },
33
+ "homepage": "",
34
+ "license": "",
35
+ "size_in_bytes": 1907090,
36
+ "splits": {
37
+ "train": {
38
+ "name": "train",
39
+ "num_bytes": 1907090,
40
+ "num_examples": 11620,
41
+ "dataset_name": "generator"
42
+ }
43
+ },
44
+ "version": {
45
+ "version_str": "0.0.0",
46
+ "major": 0,
47
+ "minor": 0,
48
+ "patch": 0
49
+ }
50
+ }
data/sentence_retrieval/pairwise_ranking/train/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "1c80317fa3b1799d",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": "train"
13
+ }