![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "# 1. Dataset Preparation"
+ ],
+ "metadata": {
+ "id": "LNsZ3c69cGnY"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!nvidia-smi "
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "Loz2U2x_xxpj",
+ "outputId": "e550a634-f73e-420a-d281-6a775f77099b"
+ },
+ "execution_count": 1,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Mon Jun 5 04:18:42 2023 \n",
+ "+-----------------------------------------------------------------------------+\n",
+ "| NVIDIA-SMI 525.85.12 Driver Version: 525.85.12 CUDA Version: 12.0 |\n",
+ "|-------------------------------+----------------------+----------------------+\n",
+ "| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |\n",
+ "| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |\n",
+ "| | | MIG M. |\n",
+ "|===============================+======================+======================|\n",
+ "| 0 Tesla T4 Off | 00000000:00:04.0 Off | 0 |\n",
+ "| N/A 62C P8 11W / 70W | 0MiB / 15360MiB | 0% Default |\n",
+ "| | | N/A |\n",
+ "+-------------------------------+----------------------+----------------------+\n",
+ " \n",
+ "+-----------------------------------------------------------------------------+\n",
+ "| Processes: |\n",
+ "| GPU GI CI PID Type Process name GPU Memory |\n",
+ "| ID ID Usage |\n",
+ "|=============================================================================|\n",
+ "| No running processes found |\n",
+ "+-----------------------------------------------------------------------------+\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!pip install datasets"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "oAkWgqvwc34x",
+ "outputId": "925b0b15-e1c2-4ee3-9776-97b8b8aa7cc4"
+ },
+ "execution_count": 2,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
+ "Collecting datasets\n",
+ " Downloading datasets-2.12.0-py3-none-any.whl (474 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━��\u001b[0m \u001b[32m474.6/474.6 kB\u001b[0m \u001b[31m39.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hRequirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.22.4)\n",
+ "Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (9.0.0)\n",
+ "Collecting dill<0.3.7,>=0.3.0 (from datasets)\n",
+ " Downloading dill-0.3.6-py3-none-any.whl (110 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m110.5/110.5 kB\u001b[0m \u001b[31m16.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (1.5.3)\n",
+ "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2.27.1)\n",
+ "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.65.0)\n",
+ "Collecting xxhash (from datasets)\n",
+ " Downloading xxhash-3.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (212 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m212.5/212.5 kB\u001b[0m \u001b[31m24.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting multiprocess (from datasets)\n",
+ " Downloading multiprocess-0.70.14-py310-none-any.whl (134 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.3/134.3 kB\u001b[0m \u001b[31m17.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hRequirement already satisfied: fsspec[http]>=2021.11.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.4.0)\n",
+ "Collecting aiohttp (from datasets)\n",
+ " Downloading aiohttp-3.8.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.0 MB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m71.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting huggingface-hub<1.0.0,>=0.11.0 (from datasets)\n",
+ " Downloading huggingface_hub-0.15.1-py3-none-any.whl (236 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m236.8/236.8 kB\u001b[0m \u001b[31m28.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hRequirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (23.1)\n",
+ "Collecting responses<0.19 (from datasets)\n",
+ " Downloading responses-0.18.0-py3-none-any.whl (38 kB)\n",
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0)\n",
+ "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.1.0)\n",
+ "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (2.0.12)\n",
+ "Collecting multidict<7.0,>=4.5 (from aiohttp->datasets)\n",
+ " Downloading multidict-6.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (114 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m114.5/114.5 kB\u001b[0m \u001b[31m14.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting async-timeout<5.0,>=4.0.0a3 (from aiohttp->datasets)\n",
+ " Downloading async_timeout-4.0.2-py3-none-any.whl (5.8 kB)\n",
+ "Collecting yarl<2.0,>=1.0 (from aiohttp->datasets)\n",
+ " Downloading yarl-1.9.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (268 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m268.8/268.8 kB\u001b[0m \u001b[31m32.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting frozenlist>=1.1.1 (from aiohttp->datasets)\n",
+ " Downloading frozenlist-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (149 kB)\n",
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━��━━━━━━━━━━━━━\u001b[0m \u001b[32m149.6/149.6 kB\u001b[0m \u001b[31m20.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting aiosignal>=1.1.2 (from aiohttp->datasets)\n",
+ " Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n",
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0.0,>=0.11.0->datasets) (3.12.0)\n",
+ "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0.0,>=0.11.0->datasets) (4.5.0)\n",
+ "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (1.26.15)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2022.12.7)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.4)\n",
+ "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n",
+ "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2022.7.1)\n",
+ "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.16.0)\n",
+ "Installing collected packages: xxhash, multidict, frozenlist, dill, async-timeout, yarl, responses, multiprocess, huggingface-hub, aiosignal, aiohttp, datasets\n",
+ "Successfully installed aiohttp-3.8.4 aiosignal-1.3.1 async-timeout-4.0.2 datasets-2.12.0 dill-0.3.6 frozenlist-1.3.3 huggingface-hub-0.15.1 multidict-6.0.4 multiprocess-0.70.14 responses-0.18.0 xxhash-3.2.0 yarl-1.9.2\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from datasets import load_dataset\n",
+ "dataset = load_dataset(\"stsb_multi_mt\", name=\"en\", split=\"train\")"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 296,
+ "referenced_widgets": [
+ "af1447d9bcdf4aca9565b6fc6ea1925e",
+ "3d8d2fb343a247c8a18261296d853ada",
+ "99ba3022e3ce4c8a951f10def140926a",
+ "e641966dcabb4b8a9b4cdf6e8119cb01",
+ "e29c844f5c71456bbeee66ee6dd04e9f",
+ "e264fde939754c2f99505ecbfc772ac2",
+ "0a70b07df2e44c1585d50b0dfaa75c1c",
+ "2a58190009a54fb39724ae91dd2a03c3",
+ "3b6a9922fbc94db5bee56ab828c4c72f",
+ "722c285950d0449ea0d91617210a72a9",
+ "e33ad31d5b264705bd2be4e217381e0d",
+ "643fa374d2604c3cbb2d64a6f521dd85",
+ "a17a23a19dc44a54aafc75e8f43b5384",
+ "17e54f01287e4ff2bab5067a8bcc88c9",
+ "9f8f845c1f1d45b6be0fbbadaa32f5aa",
+ "3ce9930e72604b73ab3bd9405ce96937",
+ "865094c7cb3147389403375515138e11",
+ "4e931121898b440eb8fa4c62a5021eab",
+ "500f4a69e988410aa3c542561a00e449",
+ "b631048bb7f541c4bc0cc89aab8c3374",
+ "278623db814a4ca6b7bbe7e1629a9192",
+ "7abf8a39096045f9aca5acbd41d1f0b1",
+ "6ccc7b7ffa954c409dd02306d886739b",
+ "4da001ec28184e48a3b125e8e4c7c2a8",
+ "402501ade9c84298bf5c4543336b0eda",
+ "b26e82236a8545ffa553a572790d1ffd",
+ "4e79eaa86ac4479e8c99a4b0c98f2897",
+ "5aeff9f6235b4b7fa629d2e0ac830661",
+ "46c126d08db447c594513d86eae7c2cd",
+ "5b8f7ea6351542edbb8ac0adc81ebbb9",
+ "99e101528f39427682ef0564d351ccab",
+ "8220dbeef26a4d8dbc540795b37969df",
+ "9090c1b8c3f6407492bad8aa951d01d8",
+ "1567280f5ca24b9ea8d544a0f209ce12",
+ "ec84230a427c4dbf9f3a83eab0846102",
+ "95b3c7abfd744519a16987b140b793b7",
+ "0329348fcae24091a417fce671cf6683",
+ "d994b2d977d84dd18a550c34c9b1cf6f",
+ "61d3a9c26b7c4991915512ffd704a838",
+ "a73d03daa94445d9ae45403ce3dab75b",
+ "3922db29c5bd464bbd0a1bcf6d4d73b6",
+ "d1ccaaced48344cab46a28984beab777",
+ "96f2d6e1b0dd4ba1a2154b090d8aaa14",
+ "ef8e09b48f474d3cbf1f0b02530f438e",
+ "593f183fb312419ba36e99946dde9cca",
+ "9d71c1bd82dc4e578a50da5529bacedf",
+ "de303dd1216b4ec9b10b231046c68885",
+ "36bf7db53a60440c94581e9f05ed9fbf",
+ "be0b94a21c1b420d90abb37e627d0b36",
+ "4b6fad1ea2b548b1a7901f2a8c701e46",
+ "e25c623d46af4923ab0d63ccf8e49703",
+ "8f82ad8115044a23b35508beb8ca6372",
+ "94273ad4e26b4147bd24719c872f2bfa",
+ "978d1240f2654c96a8604c35e8704f20",
+ "fc53439a778844d6ad1b9e504bceb6df",
+ "cc115fb0e0b64789931d95933d2a069f",
+ "8a5ab4dc48ba40b39bfddd6982ab8425",
+ "710b989ae29043039d3bd1808fa30954",
+ "c6e7adf3b1214f6fb833743e8860298f",
+ "0363f2b679844c7691493f901422a686",
+ "c17d7fe521ad452995ba447c4ccf3c0d",
+ "841d4851bc0542fe90060ab95e58b2a3",
+ "9f945795562e4f68ac9bc63a05b530db",
+ "c44ae9ca6b164a469d80409615454f7d",
+ "632ca8e821f0470fb7e561d58632ff43",
+ "3ec5b5e177bf4273929f663cc72d237a",
+ "b2c9d3d2b67148ad9ff19dceb121f86a",
+ "b4dc7a1539c447d5bc87b6343ea90304",
+ "477a689b838b421baeef0af1f67393a2",
+ "4b7ed1763fff4e44984767ac9d5cfb91",
+ "ca12ced69d4f474e907b6d5c749b17e9",
+ "d9f0b11c89eb4efe99705a70a3cde029",
+ "d08c78f74a844751ac92d66aa4b79000",
+ "92cfc37a253a4e79a00f1c2e9270e0fa",
+ "5c0c7735acb7415b96c9fd629ec2c4aa",
+ "8e30ee55dad245eaa028e660c462003b",
+ "f5440c3be69e498bae9107891c878a1e",
+ "cb6e8911e39e40e1a66e917c64a7f373",
+ "54f44e8aedda4e3c88ca959aa783a471",
+ "a8f3bea492f7467b892de3087aeb1a87",
+ "1b92030525b340bfb865792a83eb1ca3",
+ "e819701a024b43f8a0ced70a70586223",
+ "f78de6517e7546f0b23ac88deb7ae8a9",
+ "bc849b521628450b97507b4e9fc5ee50",
+ "554bbe4dd8044d5e824a84cc61f7b75e",
+ "a83231741b7444d896a372f514fd683b",
+ "2ed124e5c65e4bbe8b843d7eb421a5b6",
+ "71667758abdb40e38bd5ad54430a3bf4",
+ "c6a2fd8245cc4c6bb921e70d643df121",
+ "4f0da63d4f734c9b97d3aac3529b8505",
+ "745a179bea2a409b9ba7cfc429fc0285",
+ "997c543933cb4c439bc6e2e2a0c51ace",
+ "fd3502bc7e8d47458d039f6401dedd23",
+ "5e8ac64b6eea49c98212d8a023c800a0",
+ "cd12b1d7d15145a68bf39f1e4d995c36",
+ "334642a1c7ee4698ae986935293aa717",
+ "39042492cd9b49d695621b09da8d3708",
+ "2d5bca69411c4ec9b2bc8cb2f02408f1",
+ "12c547c644b94badb5ae5848f26d13d6",
+ "ff0e5e91effe463a932914804f4a2937",
+ "17a58c9332e94970b32126408bb4c57c",
+ "75dcc03186d44fd0b545e36fbef66634",
+ "49d653001d604910a37232d4d2d5a56b",
+ "76858b7ed6be417ab82339fd7cd5de9f",
+ "a05efa676adf4139924970ce8d310cfb",
+ "5268ced2d4484a448c2583d07008d57a",
+ "f9fda21c00de4ee09ff71cfef614b0b0",
+ "6d0aea40fac14c239a1c19edafea8455",
+ "32e6a4fb67f843da8658ac0542a90539",
+ "2bd2fafe92584bfcb57843683d902bc1"
+ ]
+ },
+ "id": "ZyYsS2AccZ2u",
+ "outputId": "2a70ff74-d209-4cd6-fc44-68f4822f002b"
+ },
+ "execution_count": 3,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Downloading builder script: 0%| | 0.00/7.43k [00:00\n",
+ " | \n", + " | sentence1 | \n", + "sentence2 | \n", + "similarity_score | \n", + "
|---|---|---|---|
| 0 | \n", + "A plane is taking off. | \n", + "An air plane is taking off. | \n", + "5.00 | \n", + "
| 1 | \n", + "A man is playing a large flute. | \n", + "A man is playing a flute. | \n", + "3.80 | \n", + "
| 2 | \n", + "A man is spreading shreded cheese on a pizza. | \n", + "A man is spreading shredded cheese on an uncoo... | \n", + "3.80 | \n", + "
| 3 | \n", + "Three men are playing chess. | \n", + "Two men are playing chess. | \n", + "2.60 | \n", + "
| 4 | \n", + "A man is playing the cello. | \n", + "A man seated is playing the cello. | \n", + "4.25 | \n", + "
| \n", + " | sentence1 | \n", + "sentence2 | \n", + "score | \n", + "
|---|---|---|---|
| 0 | \n", + "A plane is taking off. | \n", + "An air plane is taking off. | \n", + "5.000 | \n", + "
| 1 | \n", + "A man is playing a large flute. | \n", + "A man is playing a flute. | \n", + "3.800 | \n", + "
| 2 | \n", + "A man is spreading shreded cheese on a pizza. | \n", + "A man is spreading shredded cheese on an uncoo... | \n", + "3.800 | \n", + "
| 3 | \n", + "Three men are playing chess. | \n", + "Two men are playing chess. | \n", + "2.600 | \n", + "
| 4 | \n", + "A man is playing the cello. | \n", + "A man seated is playing the cello. | \n", + "4.250 | \n", + "
| 5 | \n", + "Some men are fighting. | \n", + "Two men are fighting. | \n", + "4.250 | \n", + "
| 6 | \n", + "A man is smoking. | \n", + "A man is skating. | \n", + "0.500 | \n", + "
| 7 | \n", + "The man is playing the piano. | \n", + "The man is playing the guitar. | \n", + "1.600 | \n", + "
| 8 | \n", + "A man is playing on a guitar and singing. | \n", + "A woman is playing an acoustic guitar and sing... | \n", + "2.200 | \n", + "
| 9 | \n", + "A person is throwing a cat on to the ceiling. | \n", + "A person throws a cat on the ceiling. | \n", + "5.000 | \n", + "
| 10 | \n", + "The man hit the other man with a stick. | \n", + "The man spanked the other man with a stick. | \n", + "4.200 | \n", + "
| 11 | \n", + "A woman picks up and holds a baby kangaroo. | \n", + "A woman picks up and holds a baby kangaroo in ... | \n", + "4.600 | \n", + "
| 12 | \n", + "A man is playing a flute. | \n", + "A man is playing a bamboo flute. | \n", + "3.867 | \n", + "
| 13 | \n", + "A person is folding a piece of paper. | \n", + "Someone is folding a piece of paper. | \n", + "4.667 | \n", + "
| 14 | \n", + "A man is running on the road. | \n", + "A panda dog is running on the road. | \n", + "1.667 | \n", + "
| 15 | \n", + "A dog is trying to get bacon off his back. | \n", + "A dog is trying to eat the bacon on its back. | \n", + "3.750 | \n", + "
| 16 | \n", + "The polar bear is sliding on the snow. | \n", + "A polar bear is sliding across the snow. | \n", + "5.000 | \n", + "
| 17 | \n", + "A woman is writing. | \n", + "A woman is swimming. | \n", + "0.500 | \n", + "
| 18 | \n", + "A cat is rubbing against baby's face. | \n", + "A cat is rubbing against a baby. | \n", + "3.800 | \n", + "
| 19 | \n", + "The man is riding a horse. | \n", + "A man is riding on a horse. | \n", + "5.000 | \n", + "
| 20 | \n", + "A man pours oil into a pot. | \n", + "A man pours wine in a pot. | \n", + "3.200 | \n", + "
| 21 | \n", + "A man is playing a guitar. | \n", + "A girl is playing a guitar. | \n", + "2.800 | \n", + "
| 22 | \n", + "A panda is sliding down a slide. | \n", + "A panda slides down a slide. | \n", + "4.600 | \n", + "
| 23 | \n", + "A woman is eating something. | \n", + "A woman is eating meat. | \n", + "3.000 | \n", + "
| 24 | \n", + "A woman peels a potato. | \n", + "A woman is peeling a potato. | \n", + "5.000 | \n", + "
| 25 | \n", + "The boy fell off his bike. | \n", + "A boy falls off his bike. | \n", + "4.800 | \n", + "
| 26 | \n", + "The woman is playing the flute. | \n", + "A woman is playing a flute. | \n", + "5.000 | \n", + "
| 27 | \n", + "A rabbit is running from an eagle. | \n", + "A hare is running from a eagle. | \n", + "4.200 | \n", + "
| 28 | \n", + "The woman is frying a breaded pork chop. | \n", + "A woman is cooking a breaded pork chop. | \n", + "4.200 | \n", + "
| 29 | \n", + "A girl is flying a kite. | \n", + "A girl running is flying a kite. | \n", + "4.000 | \n", + "
| 30 | \n", + "A man is riding a mechanical bull. | \n", + "A man rode a mechanical bull. | \n", + "4.000 | \n", + "
| 31 | \n", + "The man is playing the guitar. | \n", + "A man is playing a guitar. | \n", + "4.909 | \n", + "
| 32 | \n", + "A woman is dancing and singing with other women. | \n", + "A woman is dancing and singing in the rain. | \n", + "3.000 | \n", + "
| 33 | \n", + "A man is slicing a bun. | \n", + "A man is slicing an onion. | \n", + "2.400 | \n", + "
| 34 | \n", + "A man is pouring oil into a pan. | \n", + "A man is pouring oil into a skillet. | \n", + "4.200 | \n", + "
| 35 | \n", + "A lion is playing with people. | \n", + "A lion is playing with two men. | \n", + "3.400 | \n", + "
| 36 | \n", + "A dog rides a skateboard. | \n", + "A dog is riding a skateboard. | \n", + "5.000 | \n", + "
| 37 | \n", + "Someone is carving a statue. | \n", + "A man is carving a statue. | \n", + "3.750 | \n", + "
| 38 | \n", + "A woman is slicing an onion. | \n", + "A man is cutting an onion. | \n", + "2.750 | \n", + "
| 39 | \n", + "A woman peels shrimp. | \n", + "A woman is peeling shrimp. | \n", + "5.000 | \n", + "
| 40 | \n", + "A woman is frying fish. | \n", + "A woman is cooking fish. | \n", + "4.000 | \n", + "
| 41 | \n", + "A woman is playing an electric guitar. | \n", + "A woman is playing a guitar. | \n", + "3.600 | \n", + "
| 42 | \n", + "A baby tiger is playing with a ball. | \n", + "A baby is playing with a doll. | \n", + "1.600 | \n", + "
| 43 | \n", + "A person is slicing a tomato. | \n", + "A person is slicing some meat. | \n", + "1.750 | \n", + "
| 44 | \n", + "A person cuts an onion. | \n", + "A person is cutting an onion. | \n", + "5.000 | \n", + "
| 45 | \n", + "A man is playing the piano. | \n", + "A woman is playing the violin. | \n", + "1.000 | \n", + "
| 46 | \n", + "A woman is playing the flute. | \n", + "A man is playing the guitar. | \n", + "1.000 | \n", + "
| 47 | \n", + "A man is cutting up a potato. | \n", + "A man is cutting up carrots. | \n", + "2.375 | \n", + "
| 48 | \n", + "A kid is playing guitar. | \n", + "A boy is playing a guitar. | \n", + "3.800 | \n", + "
| 49 | \n", + "A boy is playing guitar. | \n", + "A man is playing a guitar. | \n", + "3.200 | \n", + "
| \n", + " | sentence1 | \n", + "sentence2 | \n", + "score | \n", + "
|---|---|---|---|
| 0 | \n", + "एउटा विमान उडिरहेको छ। | \n", + "हवाई जहाज उडिरहेको छ। | \n", + "5.00 | \n", + "
| 1 | \n", + "एउटा मान्छे ठूलो बाँसुरी बज���इरहेको छ। | \n", + "एउटा मान्छे बाँसुरी बजाउँदै छ। | \n", + "3.80 | \n", + "
| 2 | \n", + "एक व्यक्ति पिज्जामा टुक्रा चिज फैलाउँदै छ। | \n", + "एक जना मानिसले न पकाएको पिज्जामा टुक्रा पारेको... | \n", + "3.80 | \n", + "
| 3 | \n", + "तीन जना चेस खेल्दै छन्। | \n", + "दुई जना पुरुष चेस खेलिरहेका छन्। | \n", + "2.60 | \n", + "
| 4 | \n", + "एउटा मान्छे सेलो बजाउँदै छ। | \n", + "बसेको मान्छे सेलो खेलिरहेको छ। | \n", + "4.25 | \n", + "
| ... | \n", + "... | \n", + "... | \n", + "... | \n", + "
| 95 | \n", + "दुई जना केटाले गाडी चलाइरहेका छन् । | \n", + "दुई खाडीहरू नाचिरहेका छन्। | \n", + "0.60 | \n", + "
| 96 | \n", + "एउटा मानिस घोडामा सवार छ। | \n", + "एउटी केटी घोडा चढ्दै छिन्। | \n", + "2.60 | \n", + "
| 97 | \n", + "एकजना मानिस साइकल चलाइरहेका छन्। | \n", + "बाँदर बाइक चलाउँदै छ। | \n", + "2.00 | \n", + "
| 98 | \n", + "एउटा मान्छे आलु काट्दै छ। | \n", + "एउटी महिला आलु बोक्दै छिन्। | \n", + "2.20 | \n", + "
| 99 | \n", + "एउटी महिला आलु बोक्दै छिन्। | \n", + "एउटा मान्छे आलु काट्दै छ। | \n", + "2.40 | \n", + "
100 rows × 3 columns
\n", + "