{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Kesalahan Tatabahasa with Tagging"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"\n",
"This tutorial is available as an IPython notebook at [Malaya/example/tatabahasa-tagging](https://github.com/huseinzol05/Malaya/tree/master/example/tatabahasa-tagging).\n",
" \n",
"
"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"\n",
"This module only trained on standard language structure, so it is not save to use it for local language structure.\n",
" \n",
"
"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/husein/dev/malaya/malaya/tokenizer.py:214: FutureWarning: Possible nested set at position 3397\n",
" self.tok = re.compile(r'({})'.format('|'.join(pipeline)))\n",
"/home/husein/dev/malaya/malaya/tokenizer.py:214: FutureWarning: Possible nested set at position 3927\n",
" self.tok = re.compile(r'({})'.format('|'.join(pipeline)))\n"
]
}
],
"source": [
"import malaya\n",
"from pprint import pprint"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### List available HuggingFace models"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'mesolitica/finetune-tatabahasa-t5-tiny-standard-bahasa-cased': {'Size (MB)': 139,\n",
" 'exactly-match': 0.7665198237,\n",
" 'f1': 0.970908229,\n",
" 'exactly-match-tags': 0.87404885863,\n",
" 'f1-tags': 0.9878723587,\n",
" 'Suggested length': 256},\n",
" 'mesolitica/finetune-tatabahasa-t5-small-standard-bahasa-cased': {'Size (MB)': 242,\n",
" 'exactly-match': 0.8145774929,\n",
" 'f1': 0.9781278,\n",
" 'exactly-match-tags': 0.89447336,\n",
" 'f1-tags': 0.990597377,\n",
" 'Suggested length': 256},\n",
" 'mesolitica/finetune-tatabahasa-t5-base-standard-bahasa-cased': {'Size (MB)': 892,\n",
" 'exactly-match': 0.760913095,\n",
" 'f1': 0.970136249,\n",
" 'exactly-match-tags': 0.865839,\n",
" 'f1-tags': 0.9868999035,\n",
" 'Suggested length': 256}}"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"malaya.tatabahasa.available_huggingface"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Supported kesalahan tatabahasa\n",
"\n",
"For full description, check out https://tatabahasabm.tripod.com/tata/salahtata.htm"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"[{'class': 0, 'Description': 'PAD', 'salah': '', 'betul': ''},\n",
" {'class': 1, 'Description': 'kesambungan subwords', 'salah': '', 'betul': ''},\n",
" {'class': 2, 'Description': 'tiada kesalahan', 'salah': '', 'betul': ''},\n",
" {'class': 3,\n",
" 'Description': 'kesalahan frasa nama, Perkara yang diterangkan mesti mendahului \"penerang\"',\n",
" 'salah': 'Cili sos',\n",
" 'betul': 'sos cili'},\n",
" {'class': 4,\n",
" 'Description': 'kesalahan kata jamak',\n",
" 'salah': 'mereka-mereka',\n",
" 'betul': 'mereka'},\n",
" {'class': 5,\n",
" 'Description': 'kesalahan kata penguat',\n",
" 'salah': 'sangat tinggi sekali',\n",
" 'betul': 'sangat tinggi'},\n",
" {'class': 6,\n",
" 'Description': 'kata adjektif dan imbuhan \"ter\" tanpa penguat.',\n",
" 'salah': 'Sani mendapat markah yang tertinggi sekali.',\n",
" 'betul': 'Sani mendapat markah yang tertinggi.'},\n",
" {'class': 7,\n",
" 'Description': 'kesalahan kata hubung',\n",
" 'salah': 'Sally sedang membaca bila saya tiba di rumahnya.',\n",
" 'betul': 'Sally sedang membaca apabila saya tiba di rumahnya.'},\n",
" {'class': 8,\n",
" 'Description': 'kesalahan kata bilangan',\n",
" 'salah': 'Beribu peniaga tidak membayar cukai pendapatan.',\n",
" 'betul': 'Beribu-ribu peniaga tidak membayar cukai pendapatan'},\n",
" {'class': 9,\n",
" 'Description': 'kesalahan kata sendi',\n",
" 'salah': 'Umar telah berpindah daripada sekolah ini bulan lalu.',\n",
" 'betul': 'Umar telah berpindah dari sekolah ini bulan lalu.'},\n",
" {'class': 10,\n",
" 'Description': 'kesalahan penjodoh bilangan',\n",
" 'salah': 'Setiap orang pelajar',\n",
" 'betul': 'Setiap pelajar.'},\n",
" {'class': 11,\n",
" 'Description': 'kesalahan kata ganti diri',\n",
" 'salah': 'Pencuri itu telah ditangkap. Beliau dibawa ke balai polis.',\n",
" 'betul': 'Pencuri itu telah ditangkap. Dia dibawa ke balai polis.'},\n",
" {'class': 12,\n",
" 'Description': 'kesalahan ayat pasif',\n",
" 'salah': 'Cerpen itu telah dikarang oleh saya.',\n",
" 'betul': 'Cerpen itu telah saya karang.'},\n",
" {'class': 13,\n",
" 'Description': 'kesalahan kata tanya',\n",
" 'salah': 'Kamu berasal dari manakah ?',\n",
" 'betul': 'Kamu berasal dari mana ?'},\n",
" {'class': 14,\n",
" 'Description': 'kesalahan tanda baca',\n",
" 'salah': 'Kamu berasal dari manakah .',\n",
" 'betul': 'Kamu berasal dari mana ?'},\n",
" {'class': 15,\n",
" 'Description': 'kesalahan kata kerja tak transitif',\n",
" 'salah': 'Dia kata kepada saya',\n",
" 'betul': 'Dia berkata kepada saya'},\n",
" {'class': 16,\n",
" 'Description': 'kesalahan kata kerja transitif',\n",
" 'salah': 'Dia suka baca buku',\n",
" 'betul': 'Dia suka membaca buku'},\n",
" {'class': 17,\n",
" 'Description': 'penggunaan kata yang tidak tepat',\n",
" 'salah': 'Tembuk Besar negeri Cina dibina oleh Shih Huang Ti.',\n",
" 'betul': 'Tembok Besar negeri Cina dibina oleh Shih Huang Ti'}]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"malaya.tatabahasa.describe"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Right now we only able to predict up to 15 different kesalahan tatabahasa, hopefully in the future we can scale this up."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Load HuggingFace model\n",
"\n",
"```python\n",
"def huggingface(\n",
" model: str = 'mesolitica/finetune-tatabahasa-t5-small-standard-bahasa-cased',\n",
" force_check: bool = True,\n",
" **kwargs,\n",
"):\n",
" \"\"\"\n",
" Load HuggingFace model to fix kesalahan tatabahasa.\n",
"\n",
" Parameters\n",
" ----------\n",
" model: str, optional (default='mesolitica/finetune-tatabahasa-t5-small-standard-bahasa-cased')\n",
" Check available models at `malaya.tatabahasa.available_huggingface`.\n",
" force_check: bool, optional (default=True)\n",
" Force check model one of malaya model.\n",
" Set to False if you have your own huggingface model.\n",
"\n",
" Returns\n",
" -------\n",
" result: malaya.torch_model.huggingface.Tatabahasa\n",
" \"\"\"\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading the tokenizer from the `special_tokens_map.json` and the `added_tokens.json` will be removed in `transformers 5`, it is kept for forward compatibility, but it is recommended to update your `tokenizer_config.json` by uploading it again. You will see the new `added_tokens_decoder` attribute that will store the relevant information.\n",
"You are using the default legacy behaviour of the . If you see this, DO NOT PANIC! This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thouroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565\n"
]
}
],
"source": [
"model = malaya.tatabahasa.huggingface()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Predict\n",
"\n",
"```python\n",
"def generate(\n",
" self,\n",
" strings: List[str],\n",
" **kwargs,\n",
"):\n",
" \"\"\"\n",
" Fix kesalahan tatatabahasa.\n",
"\n",
" Parameters\n",
" ----------\n",
" strings : List[str]\n",
" **kwargs: vector arguments pass to huggingface `generate` method.\n",
" Read more at https://huggingface.co/docs/transformers/main_classes/text_generation\n",
" Fix kesalahan tatabahasa supported all decoding methods except beam.\n",
"\n",
" Returns\n",
" -------\n",
" result: List[Tuple[str, int]]\n",
" \"\"\"\n",
"```"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Randomly picked string in bahasa melayu wikipedia."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"# https://ms.wikipedia.org/wiki/Bola_sepak\n",
"string = 'Pada amnya, hanya penjaga gol sahaja yang dibenarkan menyentuh bola dengan tangan di dalam kawasan golnya'"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Pada', 2),\n",
" ('amnya', 2),\n",
" (',', 2),\n",
" ('hanya', 2),\n",
" ('penjaga', 2),\n",
" ('gol', 2),\n",
" ('sahaja', 2),\n",
" ('yang', 2),\n",
" ('dibenarkan', 2),\n",
" ('menyentuh', 2),\n",
" ('bola', 2),\n",
" ('dengan', 2),\n",
" ('tangan', 2),\n",
" ('di', 2),\n",
" ('dalam', 2),\n",
" ('kawasan', 2),\n",
" ('golnya', 2)]]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now assumed we have kesalahan frasa nama, from `penjaga gol` become `gol penjaga`."
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"# https://ms.wikipedia.org/wiki/Bola_sepak\n",
"string = 'Pada amnya, hanya gol penjaga sahaja yang dibenarkan menyentuh bola dengan tangan di dalam kawasan golnya'"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/plain": [
"[[('Pada', 2),\n",
" ('amnya', 2),\n",
" (',', 2),\n",
" ('hanya', 2),\n",
" ('penjaga', 3),\n",
" ('gol', 3),\n",
" ('sahaja', 2),\n",
" ('yang', 2),\n",
" ('dibenarkan', 2),\n",
" ('menyentuh', 2),\n",
" ('bola', 2),\n",
" ('dengan', 2),\n",
" ('tangan', 2),\n",
" ('di', 2),\n",
" ('dalam', 2),\n",
" ('kawasan', 2),\n",
" ('golnya', 2)]]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Sani', 2),\n",
" ('mendapat', 2),\n",
" ('markah', 2),\n",
" ('yang', 2),\n",
" ('tertinggi', 6),\n",
" ('.', 2)],\n",
" [('Hassan', 2),\n",
" ('ialah', 2),\n",
" ('peserta', 2),\n",
" ('yang', 2),\n",
" ('termuda', 6),\n",
" ('dalam', 2),\n",
" ('pertandingan', 2),\n",
" ('itu', 2),\n",
" ('.', 2)]]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Sani mendapat markah yang tertinggi sekali.'\n",
"string1 = 'Hassan ialah peserta yang termuda sekali dalam pertandingan itu.'\n",
"model.generate([string, string1], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Dia', 2), ('berkata', 15), ('kepada', 2), ('saya', 2), ('.', 2)]]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Dia kata kepada saya.'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"100"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pickle\n",
"\n",
"with open('tests/dataset-tatabahasa.pkl', 'rb') as fopen:\n",
" test_set = pickle.load(fopen)\n",
" \n",
"len(test_set)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"def get_xy(row):\n",
" x, y, tag = [], [], []\n",
"\n",
" for i in range(len(row[0])):\n",
" t = [row[0][i][0]]\n",
" y.extend(t)\n",
" t = [row[1][i][0]]\n",
" x.extend(t)\n",
" tag.extend([row[1][i][1]] * len(t))\n",
"\n",
" return ' '.join(x), ' '.join(y), tag"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"('Dirk Jan Klaas \" Klaas-Jan \" Huntelaar ( lahir 12 Ogos 1983 ) merupakan pemain bola sepak Belanda yang bermain seperti posisi penyerang !',\n",
" 'Dirk Jan Klaas \" Klaas-Jan \" Huntelaar ( lahir 12 Ogos 1983 ) merupakan pemain bola sepak Belanda yang bermain di posisi penyerang .',\n",
" [2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 9, 2, 2, 14])"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"x, y, t = get_xy(test_set[0])\n",
"x, y, t"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Dirk', 2),\n",
" ('Jan', 2),\n",
" ('Klaas', 2),\n",
" ('\"', 2),\n",
" ('Klaas-Jan', 2),\n",
" ('\"', 2),\n",
" ('Huntelaar', 2),\n",
" ('(', 2),\n",
" ('lahir', 2),\n",
" ('12', 2),\n",
" ('Ogos', 2),\n",
" ('1983', 2),\n",
" (')', 2),\n",
" ('merupakan', 2),\n",
" ('pemain', 2),\n",
" ('bola', 2),\n",
" ('sepak', 2),\n",
" ('Belanda', 2),\n",
" ('yang', 2),\n",
" ('bermain', 2),\n",
" ('di', 9),\n",
" ('posisi', 2),\n",
" ('penyerang', 2),\n",
" ('.', 14)]]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.generate([x], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"('Pada tahun 2002 , kedua-dua gol beliau menduduki tempat ke-6 dalam 100 Greatest Sporting Moments oleh saluran Channel 4 UK .',\n",
" 'Pada tahun 2002 , kedua-dua gol ini menduduki tempat ke-6 dalam 100 Greatest Sporting Moments oleh saluran Channel 4 UK .',\n",
" [2, 2, 2, 2, 2, 2, 11, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"x, y, t = get_xy(test_set[-1])\n",
"x, y, t"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Pada', 2),\n",
" ('tahun', 2),\n",
" ('2002', 2),\n",
" (',', 2),\n",
" ('kedua-dua', 2),\n",
" ('gol', 2),\n",
" ('beliau', 11),\n",
" ('menduduki', 2),\n",
" ('tempat', 2),\n",
" ('ke-6', 2),\n",
" ('dalam', 2),\n",
" ('100', 2),\n",
" ('Greatest', 2),\n",
" ('Sporting', 2),\n",
" ('Moments', 2),\n",
" ('oleh', 2),\n",
" ('saluran', 2),\n",
" ('Channel', 2),\n",
" ('4', 2),\n",
" ('UK', 2),\n",
" ('.', 2)]]"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.generate([x], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"('Gol inilah yang bergelar Goal of the Century dengan undian Internet 2000 sejak FIFA .',\n",
" 'Gol inilah yang bergelar Goal of the Century di undian Internet 2000 oleh FIFA .',\n",
" [2, 2, 2, 2, 2, 2, 2, 2, 9, 2, 2, 2, 9, 2, 2])"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"x, y, t = get_xy(test_set[-2])\n",
"x, y, t"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Gol', 2),\n",
" ('inilah', 2),\n",
" ('yang', 2),\n",
" ('bergelar', 2),\n",
" ('Goal', 2),\n",
" ('of', 2),\n",
" ('the', 2),\n",
" ('Century', 2),\n",
" ('dalam', 9),\n",
" ('undian', 2),\n",
" ('Internet', 2),\n",
" ('2000', 2),\n",
" ('oleh', 9),\n",
" ('FIFA', 2),\n",
" ('.', 2)]]"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.generate([x], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"('Beliau mengambil bola dalam kawasan kepul diri lalu pusing dan luru lebih separuh padang sambil menyentuh bola 11 kali , memintas lima pemain England : ( Glenn Hoddle , Peter Reid , Kenny Sansom , Terry Butcher , dan Terry Fenwick ) serta penjaga gawang Peter Shilton .',\n",
" 'Beliau mengambil bola di kawasan pasukan diri lalu berpusing-pusing dan meluru lebih separuh padang sambil menyentuh bola 11 kali , memintas lima pemain England : ( Glenn Hoddle , Peter Reid , Kenny Sansom , Terry Butcher , dan Terry Fenwick ) serta penjaga gawang Peter Shilton .',\n",
" [2,\n",
" 2,\n",
" 2,\n",
" 9,\n",
" 2,\n",
" 10,\n",
" 2,\n",
" 2,\n",
" 15,\n",
" 2,\n",
" 15,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2,\n",
" 2])"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"x, y, t = get_xy(test_set[-3])\n",
"x, y, t"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Beliau', 2),\n",
" ('mengambil', 2),\n",
" ('bola', 2),\n",
" ('dalam', 2),\n",
" ('kawasan', 2),\n",
" ('pasukan', 10),\n",
" ('berdiri', 15),\n",
" ('lalu', 2),\n",
" ('berpusing', 15),\n",
" ('dan', 2),\n",
" ('meluru', 15),\n",
" ('lebih', 2),\n",
" ('separuh', 2),\n",
" ('padang', 2),\n",
" ('sambil', 2),\n",
" ('menyentuh', 2),\n",
" ('bola', 2),\n",
" ('11', 2),\n",
" ('kali', 2),\n",
" (',', 2),\n",
" ('memintas', 2),\n",
" ('lima', 2),\n",
" ('pemain', 2),\n",
" ('England', 2),\n",
" (':', 2),\n",
" ('(', 2),\n",
" ('Glenn', 2),\n",
" ('Hoddle', 2),\n",
" (',', 2),\n",
" ('Peter', 2),\n",
" ('Reid', 2),\n",
" (',', 2),\n",
" ('Kenny', 2),\n",
" ('Sansom', 2),\n",
" (',', 2),\n",
" ('Terry', 2),\n",
" ('Butcher', 2),\n",
" (',', 2),\n",
" ('dan', 2),\n",
" ('Terry', 2),\n",
" ('Fenwick', 2),\n",
" (')', 2),\n",
" ('serta', 2),\n",
" ('penjaga', 2),\n",
" ('gawang', 2),\n",
" ('Peter', 2),\n",
" ('Shilton', 2),\n",
" ('.', 2)]]"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.generate([x], max_length = 256)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### More examples\n",
"\n",
"I just copy pasted from https://ms.wikipedia.org/wiki/Kesalahan_biasa_tatabahasa_Melayu"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Tidak', 2),\n",
" ('ada', 2),\n",
" ('apa', 2),\n",
" ('yang', 2),\n",
" ('mereka', 2),\n",
" ('risaukan', 2),\n",
" ('waktu', 2),\n",
" ('itu.', 2)]]"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Tidak ada apa yang mereka risaukan waktu itu.'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Ayahnya', 2),\n",
" ('setuju', 2),\n",
" ('dan', 7),\n",
" ('melanggar', 2),\n",
" ('syarat', 2),\n",
" ('yang', 2),\n",
" ('dia', 2),\n",
" ('sendiri', 2),\n",
" ('menetapkan', 2),\n",
" ('.', 2)]]"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Ayahnya setuju walaupun melanggar syarat yang dia sendiri menetapkan.'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Semuanya', 2), ('dia', 2), ('kenal', 2), ('.', 2)]]"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Semuanya dia kenal.'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Dia', 2),\n",
" ('menjawab', 2),\n",
" ('seperti', 2),\n",
" ('disuruh-suruh', 2),\n",
" ('oleh', 2),\n",
" ('kuasa', 2),\n",
" ('yang', 2),\n",
" ('dia', 2),\n",
" ('tidak', 2),\n",
" ('tahu', 2),\n",
" ('dari', 2),\n",
" ('mana', 2),\n",
" ('puncanya.', 2)]]"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Dia menjawab seperti disuruh-suruh oleh kuasa yang dia tidak tahu dari mana puncanya.'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Bola', 2),\n",
" ('ini', 2),\n",
" ('ditendang', 2),\n",
" ('oleh', 2),\n",
" ('saya', 2),\n",
" ('.', 2)]]"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Bola ini ditendang oleh saya.'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Makanan', 2),\n",
" ('ini', 11),\n",
" ('kamu', 2),\n",
" ('telah', 2),\n",
" ('makan', 2),\n",
" ('.', 14)]]"
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Makanan ini kamu telah makan?'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Segala', 2),\n",
" ('perubahan', 2),\n",
" ('yang', 2),\n",
" ('berlaku', 2),\n",
" ('kita', 2),\n",
" ('akan', 2),\n",
" ('menghadapi', 2),\n",
" ('sama-sama', 2),\n",
" ('.', 2)]]"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Segala perubahan yang berlaku kita akan menghadapi sama-sama.'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Kakak', 2),\n",
" ('saya', 2),\n",
" ('sedang', 2),\n",
" ('memasak', 2),\n",
" ('gulai', 2),\n",
" ('nangka.', 2),\n",
" ('Dia', 2),\n",
" ('menyenduk', 2),\n",
" ('seketul', 2),\n",
" ('gulai', 3),\n",
" ('nangka', 3),\n",
" ('dan', 2),\n",
" ('menyuruh', 2),\n",
" ('saya', 2),\n",
" ('merasanya.', 2)]]"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Kakak saya sedang memasak gulai nangka. Dia menyenduk seketul nangka gulai dan menyuruh saya merasanya.'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Sally', 2),\n",
" ('sedang', 2),\n",
" ('membaca', 2),\n",
" ('bila', 2),\n",
" ('saya', 11),\n",
" ('tiba', 2),\n",
" ('di', 2),\n",
" ('rumahnya.', 2)]]"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Sally sedang membaca bila saya tiba di rumahnya.'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Badannya', 2),\n",
" ('besar', 2),\n",
" ('dan', 7),\n",
" ('kakinya', 2),\n",
" ('kecil', 2),\n",
" ('.', 2)]]"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Badannya besar kecuali kakinya kecil.'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Beribu', 2),\n",
" ('peniaga', 2),\n",
" ('tidak', 2),\n",
" ('membayar', 2),\n",
" ('cukai', 2),\n",
" ('pendapatan.', 2)]]"
]
},
"execution_count": 31,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Beribu peniaga tidak membayar cukai pendapatan.'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Setengah', 2),\n",
" ('remaja', 2),\n",
" ('suka', 2),\n",
" ('membuang', 2),\n",
" ('masa', 2),\n",
" ('di', 2),\n",
" ('pasar', 2),\n",
" ('raya.', 2)]]"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Setengah remaja suka membuang masa di pasar raya.'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Umar', 2),\n",
" ('telah', 2),\n",
" ('berpindah', 2),\n",
" ('ke', 9),\n",
" ('sekolah', 2),\n",
" ('ini', 2),\n",
" ('bulan', 2),\n",
" ('lalu', 2),\n",
" ('.', 2)]]"
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Umar telah berpindah daripada sekolah ini bulan lalu.'\n",
"model.generate([string], max_length = 256)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[[('Para', 4), ('peserta', 2), ('sedang', 2), ('berbaris', 2), ('.', 2)]]"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"string = 'Para-para peserta sedang berbaris.'\n",
"model.generate([string], max_length = 256)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.10"
},
"varInspector": {
"cols": {
"lenName": 16,
"lenType": 16,
"lenVar": 40
},
"kernels_config": {
"python": {
"delete_cmd_postfix": "",
"delete_cmd_prefix": "del ",
"library": "var_list.py",
"varRefreshCmd": "print(var_dic_list())"
},
"r": {
"delete_cmd_postfix": ") ",
"delete_cmd_prefix": "rm(",
"library": "var_list.r",
"varRefreshCmd": "cat(var_dic_list()) "
}
},
"types_to_exclude": [
"module",
"function",
"builtin_function_or_method",
"instance",
"_Feature"
],
"window_display": false
}
},
"nbformat": 4,
"nbformat_minor": 4
}