Add tracked ABSA datasets and demo resources

Adds initial data assets under `data/`, including a demo review file, the FastText language ID model (`lid.176.ftz`), and tokenized Hugging Face Arrow datasets for both ABSA classification and NER across train/validation/test splits. Also adds `data/raw.dvc` to track the raw dataset directory with DVC and a local `.gitignore` entry for `data/raw`.

data/.gitignore

@@ -0,0 +1 @@
+/raw

data/demo/demo_single_reviews.txt

@@ -0,0 +1,5 @@
+The phone has an amazing screen but the battery life is terrible.
+I absolutely love the camera quality on this device.
+फोन की बैटरी अच्छी है लेकिन कैमरा बेकार है
+खाना बहुत स्वादिष्ट था, पर सर्विस थोड़ी स्लो थी
+Design mast hai par price bahut high hai

data/models/lid.176.ftz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3472cfe8738a7b6099e8e999c3cbfae0dcd15696aac7d7738a8039db603e83
+size 938013

data/raw.dvc

@@ -0,0 +1,6 @@
+outs:
+- md5: 0d10b4997c93bd1bce4a9d53a6e4748e.dir
+  size: 7943297
+  nfiles: 21
+  hash: md5
+  path: raw

data/tokenized/absa_cls_dataset/dataset_dict.json

@@ -0,0 +1 @@
+{"splits": ["train", "validation", "test"]}

data/tokenized/absa_cls_dataset/test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb8d8230357e82431b68c2226770b209f0a61fe34425c0fd037b17f913a028c
+size 101864

data/tokenized/absa_cls_dataset/test/dataset_info.json

@@ -0,0 +1,26 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "label": {
+      "dtype": "int64",
+      "_type": "Value"
+    },
+    "input_ids": {
+      "feature": {
+        "dtype": "int32",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "attention_mask": {
+      "feature": {
+        "dtype": "int8",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

data/tokenized/absa_cls_dataset/test/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "b686d9c13fd54a9d",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

data/tokenized/absa_cls_dataset/train/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74827f37b8915b4946a33e030d5833d109bfcf9d9d847edf54fd830fe33a0a3d
+size 808112

data/tokenized/absa_cls_dataset/train/dataset_info.json

@@ -0,0 +1,26 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "label": {
+      "dtype": "int64",
+      "_type": "Value"
+    },
+    "input_ids": {
+      "feature": {
+        "dtype": "int32",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "attention_mask": {
+      "feature": {
+        "dtype": "int8",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

data/tokenized/absa_cls_dataset/train/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "59c1808a1a0be248",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

data/tokenized/absa_cls_dataset/validation/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9da21b3401a16a246766047cda0695dcf07ef7d3c7eb64804ed9f59f0746f08
+size 105136

data/tokenized/absa_cls_dataset/validation/dataset_info.json

@@ -0,0 +1,26 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "label": {
+      "dtype": "int64",
+      "_type": "Value"
+    },
+    "input_ids": {
+      "feature": {
+        "dtype": "int32",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "attention_mask": {
+      "feature": {
+        "dtype": "int8",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

data/tokenized/absa_cls_dataset/validation/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "a33b9cfd2402e633",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

data/tokenized/absa_ner_dataset/dataset_dict.json

@@ -0,0 +1 @@
+{"splits": ["train", "validation", "test"]}

data/tokenized/absa_ner_dataset/test/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ec218e3b5b0c88fd86358c8e87f44709510cff43c41a81dac98274ce4eb0e7
+size 141712

data/tokenized/absa_ner_dataset/test/dataset_info.json

@@ -0,0 +1,29 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "input_ids": {
+      "feature": {
+        "dtype": "int32",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "attention_mask": {
+      "feature": {
+        "dtype": "int8",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "labels": {
+      "feature": {
+        "dtype": "int64",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

data/tokenized/absa_ner_dataset/test/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "0fa99b895566c7b5",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

data/tokenized/absa_ner_dataset/train/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76c719d76d95127fc82691bbe1455e988c0c593fcdd510f270deac3e625cb929
+size 1101368

data/tokenized/absa_ner_dataset/train/dataset_info.json

@@ -0,0 +1,29 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "input_ids": {
+      "feature": {
+        "dtype": "int32",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "attention_mask": {
+      "feature": {
+        "dtype": "int8",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "labels": {
+      "feature": {
+        "dtype": "int64",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

data/tokenized/absa_ner_dataset/train/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "535b22b0ddf3661d",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

data/tokenized/absa_ner_dataset/validation/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f94a6981561bcaa124a70fb560b93e355e57df287e9e721a2e6e887b6689b236
+size 144312

data/tokenized/absa_ner_dataset/validation/dataset_info.json

@@ -0,0 +1,29 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "input_ids": {
+      "feature": {
+        "dtype": "int32",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "attention_mask": {
+      "feature": {
+        "dtype": "int8",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "labels": {
+      "feature": {
+        "dtype": "int64",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

data/tokenized/absa_ner_dataset/validation/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "caedb7425c742cc1",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}