File size: 10,239 Bytes
e81e0c8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 |
import streamlit as st
import pandas as pd
import streamlit.components.v1 as components
import textwrap as tw
#st.set_page_config( initial_sidebar_state="expanded", margin_top = 20, margin_left = 20, margin_right = 10, margin_bottom=50, footer_text = "Creative Commons ... " )
st.set_page_config(page_title='Portparser', layout="wide")
##9bc2d1,#9bc2d1,#2f76a3
page_bg_img = f"""
<style>
[data-testid="stAppViewContainer"] > .main {{
background: linear-gradient(180deg, #88bbcf,#f1f1f1,#f1f1f1,#f1f1f1); /**#ccebff 10%, #f1f1f1 90% #0088be);
padding-left:4rem;
padding-right:4rem;
background-image: url("img/nilc.png");
background-repeat: repeat;
background-position: center center;
background-attachment: local;
/**#f1f1f1/** #008fb3/**#accad2;/**#b3b3ff;**/
/**background-image: url("https://i.postimg.cc/4xgNnkfX/Untitled-design.png");
background-position: center center;
background-repeat: no-repeat;
background-attachment: local;**/
}}
[data-testid="stForm"] {{
background-color: #9bc2d1;/**#7ebac9;/**#0086b3;**/
}}
.appview-container .main .block-container {{
padding-top: 1rem;
padding-bottom: 3rem;
}}
h1 {{
color:#003d66;/**#143350**/;
padding-left:1rem;
padding-right:1rem;
}}
[class="css-1n543e5 e1ewe7hr5"] {{
background-color: #ffffff /**#000066; /**#9bc2d1;/**#7ebac9;/**#0086b3;**/
}}
[class="css-1n543e5 e1ewe7hr5"]:hover {{
background-color: #8080ff; /**#9bc2d1;/**#7ebac9;/**#0086b3;**/
color:white;
border: solid 1px #000066;
}}
a:link{{
color:#0088be;
}}
a:hover {{
color: #7733ff/**#8080ff**/;
}}
button{{
padding-left:1rem;
padding-right:1rem;
border-radius: 15%;
}}
button:hover {{
color:#7733ff;
border:solid 1px #7733ff;
}}
</style>
"""
# head style
head_css = """
<style>
[class="css-ocqkz7 esravye3"] {
/**background-color: #9bc2d1;**/
}
[class="css-ocqkz7 esravye3"]{
/**row1**/
margin:0px 0px 0px 0px;
padding:0;
}
.stApp {
background-image: url("portparser_brasil1.jpg");
background-repeat: repeat;
background-position: center;
}
</style>
"""
#class="css-o7kwkx esravye0"]
a = """
<style>
div.css-10r1649 esravye0 {
background-color: red;
}
</style>
"""
custom_html = """
<div class="banner" style="background-color:#0088be; color:white">
<h1>PortParser</h1>
<!--<img src="https://img.freepik.com/premium-photo/wide-banner-with-many-random-square-hexagons-charcoal-dark-black-color_105589-1820.jpg" alt="Banner Image">-->
</div>
<style>
.banner {
width: 160%;
height: 200px;
overflow: hidden;
}
.banner img {
width: 100%;
object-fit: cover;
}
</style>
"""
#<div width="449" data-testid="stVerticalBlock" class="css-10r1649 esravye0">
#components.html(custom_html)
st.markdown(page_bg_img, unsafe_allow_html=True)
st.markdown(head_css, unsafe_allow_html=True)
row2 = st.columns([6,2,3])
with row2[0]:
st.markdown("<p style='padding-bottom:25px; padding-top:50px'><b style='font-size:calc(40px + 2vw); color:#003d66;line-height: 40px'><i>Portparser</i></b><br><b style='font-size:18px;color:#266087;line-height:4px'>\
A parsing model for Brazilian Portuguese</b></p>",unsafe_allow_html=True)
st.write('This is Portparser, a parsing model for Brazilian Portuguese that follows the Universal Dependencies (UD) framework.\
We built our model by using a recently released manually annotated corpus, the Porttinari-base, \
and we explored different parsing methods and parameters for training. We also test multiple embedding models and parsing methods. \
Portparse is the result of the best combination achieved in our experiments.')
st.write('Our model is explained in the paper https://aclanthology.org/2024.propor-1.41.pdf, and all datasets and full instructions to reproduce our experiments \
freely available at https://github.com/LuceleneL/Portparser. More details about this work may also be found at \
the POeTiSA project webpage at https://sites.google.com/icmc.usp.br/poetisa/.')
with st.expander('How to cite?', expanded=False):
st.code("""
@inproceedings{lopes2024towards,
title={Towards Portparser-a highly accurate parsing system for Brazilian Portuguese following the Universal Dependencies framework},
author={Lopes, Lucelene and Pardo, Thiago},
booktitle={Proceedings of the 16th International Conference on Computational Processing of Portuguese},
pages={401--410},
year={2024}
}""")
with row2[2]:
st.image('img/wordcloud_brasil5.png')
#wordcloud_vertical1.png
#st.markdown('##### Write a sentence and run to parse:')
#with st.sidebar:
# st.header("About Portparser")
# with st.expander('How was Portparser developed?'):
# st.write('We build our model by using a recently released manually annotated corpus, the Porttinari-base, \
# and explored different parsing methods and parameters for training. We also test multiple embedding models and parsing methods. \
# Portparse is the result of the best combination achieved in our experiments.' )
print('---------------------------')
st.markdown("""
<script language="JavaScript" type="text/javascript" src="arborator-draft.js"></script>
<script language="JavaScript" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/d3/4.10.0/d3.js"></script>
<script src="https://code.jquery.com/jquery-3.2.1.min.js" integrity="sha256-hwg4gsxgFZhOsEEamdOYGBf13FyQuiTwlAQgxVSNgt4=" crossorigin="anonymous"></script>
<link rel="stylesheet" href="arborator-draft.css" type="text/css" />
<script src="d3.js"></script>
<script src="jquery-3.2.1.min.js"></script>
<script>
new ArboratorDraft();
</script>"""
,unsafe_allow_html=True)
def make_conllu(path_text, path_input):
try:
os.system(f'python portTokenizer/portTok.py -o {path_input} -m -t -s S0000 {path_text}')
return 'Converti o texto para conllu.'
#st.text(open(path_input,'r',encoding='utf-8').read())
except Exception as e:
return str(e)
def make_embedding(path_input, path_embedding, model_selected):
try:
os.system(f'python ./wembedding_service/compute_wembeddings.py {path_input} {path_embedding} --model {model_selected}')
return 'Fiz as embeddings.'
except Exception as e:
return str(e)
def make_predictions(path_input, path_prediction):
try:
os.system(f'python ./udpipe2/udpipe2.py Portparser_model --predict --predict_input {path_input} --predict_output {path_prediction}')
return f'Fiz a predição.'# {path_input}, {path_prediction}'
except Exception as e:
return str(e)
def get_predictions(path_prediction):
try:
with open(path_prediction, 'r') as f:
st.text(f.read())
except Exception as e:
st.text('Resposta: '+e)
st.write('Write a sentence and run to parse:')
with st.form("parser"):
text = st.text_input('Text: ')
model = st.selectbox('Pick a model (Pick a embedding model:):', ['bert-base-portuguese-cased','bert-base-multilingual-uncased','robeczech-base','xlm-roberta-base'])
model_selected = model+'-last4'
submit = st.form_submit_button('Run')
tab1, tab2, tab3, tab4 = st.tabs(["Running status" ,"Table", "Raw", "Tree"])
if submit:
import sys, os
print(type(text))
tab1.text('input: '+text)
files = 'temp'
input_text = 'text_input.txt'
input_conllu = 'input.conllu' #'h2104_0_test.conllu'
embedding_conllu = 'input.conllu.npz' #'h2104_0_test.conllu.npz'
prediction_conllu = 'input_prediction.conllu'
model = 'Portparser_model'
path_text = os.path.join(files, input_text)
path_input = os.path.join(files, input_conllu)
path_prediction = os.path.join(files, prediction_conllu)
path_embedding = os.path.join(files,embedding_conllu)
with open(path_text,'w',encoding='utf-8') as f:
f.write(text)
import time
with st.spinner('Transforming text into .conllu...'): #st.progress(0,text="Transformando texto para o formato .conllu"):
time.sleep(3)
tab1.text(make_conllu(path_text, path_input))
with st.spinner('Processing embeddings...'): #st.progress(0,text="Processando embeddings"):
time.sleep(6)
tab1.text(make_embedding(path_input, path_embedding, model_selected))
with st.spinner('Making predictions...'): #st.progress(0,text="Realizando a predição"):
time.sleep(6)
tab1.text(make_predictions(path_input, path_prediction))
try:
with open(path_prediction, 'r', encoding='utf-8') as f:
content = f.read()
tab3.text(content)
#tab4.markdown(f'<conll>{content[4:]}</conll>',unsafe_allow_html=True)
content = content.split('\n')
#tab2.text(content[:4])
table = pd.DataFrame([line.split('\t') for line in content[4:]])
table.columns = ['ID','FORM','LEMMA','UPOS','XPOS','FEATS','HEAD','DEPREL','DEPS','MISC']
tab2.dataframe(table, use_container_width=True)
except Exception as e:
st.text('Não deu certo a predição.'+str(e)+repr(e))
row1 = st.columns([18,3,4,4])
with row1[1]:
st.image('img/nilc-removebg.png')
with row1[2]:
st.image('img/poetisa2.png')
with row1[3]:
st.image('img/icmc.png')
st.markdown("""
<script language="JavaScript" type="text/javascript" src="arborator-draft.js"></script>
<script language="JavaScript" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/d3/4.10.0/d3.js"></script>
<script src="https://code.jquery.com/jquery-3.2.1.min.js" integrity="sha256-hwg4gsxgFZhOsEEamdOYGBf13FyQuiTwlAQgxVSNgt4=" crossorigin="anonymous"></script>
<link rel="stylesheet" href="arborator-draft.css" type="text/css" />
<script src="d3.js"></script>
<script src="jquery-3.2.1.min.js"></script>
<script>
new ArboratorDraft();
</script>"""
,unsafe_allow_html=True) |