File size: 6,867 Bytes
d4a2937
 
 
 
03e97cd
c4a0750
d4a2937
 
03e97cd
d4a2937
 
 
03e97cd
 
c4a0750
03e97cd
d4a2937
 
 
e6fb89b
03e97cd
e6fb89b
c4a0750
 
 
e6fb89b
d4a2937
 
 
03e97cd
 
 
 
 
d4a2937
c4a0750
d4a2937
 
 
c4a0750
 
b3f551c
d4a2937
 
 
 
 
03e97cd
d4a2937
 
03e97cd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d4a2937
 
 
 
 
 
 
 
 
 
 
 
 
03e97cd
c4a0750
d4a2937
 
03e97cd
d4a2937
 
 
 
03e97cd
 
d4a2937
 
 
03e97cd
d4a2937
 
 
 
03e97cd
d4a2937
 
 
 
 
 
 
 
 
 
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
import gradio as gr
from gradio_rich_textbox import RichTextbox

from helper.text_preprocess import space_punc
from helper.alignment_mappers import select_model, get_alignments_table
from helper.translators import select_target_lang_code, google_translation, get_better_translation


def process_alignments(src, language_name, model_name):
    """
    Bangla PoS Tagger
    """

    tgt = None
    tgt_base = None
    html_table = None
    
    src = space_punc(src)

    tgt_lang_code = select_target_lang_code(language_name)

    tgt = get_better_translation(src, tgt_lang_code)

    tgt = space_punc(tgt)

    tgt_base = google_translation(src, tgt_lang_code)

    model_name = select_model(model_name)

    html_table, alignment_accuracy = get_alignments_table(
        source=src,
        target=tgt,
        model_name=model_name 
    )

    return tgt_base, html_table, alignment_accuracy
    

with gr.Blocks(css="styles.css") as demo:
    gr.HTML("<h1>Multilingual Sentence Alignments</h1>")
    gr.HTML("<p>Align Parallel Sentences using mBERT</p>")
    gr.HTML("<a href='https://github.com/google-research/bert/blob/master/multilingual.md#list-of-languages' alt='mBERT Repo'>Support Alignments Between 104 Languages</a>")

    with gr.Row():
        with gr.Column():
            inputs = [
                gr.Textbox(
                    label="Enter a Sentence (Auto Detect Language)", 
                ),
                gr.Dropdown(
                    choices=
                    [
                        "Afrikaans",
                        "Albanian",
                        "Arabic",
                        "Aragonese",
                        "Armenian",
                        "Asturian",
                        "Azerbaijani",
                        "Bashkir",
                        "Basque",
                        "Bavarian",
                        "Belarusian",
                        "Bengali",
                        "Bishnupriya Manipuri",
                        "Bosnian",
                        "Breton",
                        "Bulgarian",
                        "Burmese",
                        "Catalan",
                        "Cebuano",
                        "Chechen",
                        "Chinese (Simplified)",
                        "Chinese (Traditional)",
                        "Chuvash",
                        "Croatian",
                        "Czech",
                        "Danish",
                        "Dutch",
                        "English",
                        "Estonian",
                        "Finnish",
                        "French",
                        "Galician",
                        "Georgian",
                        "German",
                        "Greek",
                        "Gujarati",
                        "Haitian",
                        "Hebrew",
                        "Hindi",
                        "Hungarian",
                        "Icelandic",
                        "Ido",
                        "Indonesian",
                        "Irish",
                        "Italian",
                        "Japanese",
                        "Javanese",
                        "Kannada",
                        "Kazakh",
                        "Kirghiz",
                        "Korean",
                        "Latin",
                        "Latvian",
                        "Lithuanian",
                        "Lombard",
                        "Low Saxon",
                        "Luxembourgish",
                        "Macedonian",
                        "Malagasy",
                        "Malay",
                        "Malayalam",
                        "Marathi",
                        "Minangkabau",
                        "Nepali",
                        "Newar",
                        "Norwegian (Bokmal)",
                        "Norwegian (Nynorsk)",
                        "Occitan",
                        "Persian (Farsi)",
                        "Piedmontese",
                        "Polish",
                        "Portuguese",
                        "Punjabi",
                        "Romanian",
                        "Russian",
                        "Scots",
                        "Serbian",
                        "Serbo-Croatian",
                        "Sicilian",
                        "Slovak",
                        "Slovenian",
                        "South Azerbaijani",
                        "Spanish",
                        "Sundanese",
                        "Swahili",
                        "Swedish",
                        "Tagalog",
                        "Tajik",
                        "Tamil",
                        "Tatar",
                        "Telugu",
                        "Turkish",
                        "Ukrainian",
                        "Urdu",
                        "Uzbek",
                        "Vietnamese",
                        "Volapük",
                        "Waray-Waray",
                        "Welsh",
                        "West Frisian",
                        "Western Punjabi",
                        "Yoruba",
                        "Thai",
                        "Mongolian"
                    ], 
                    label="Select Target Language"
                ),
                gr.Dropdown(
                    choices=["Google-mBERT (Base-Multilingual)", "Neulab-AwesomeAlign (Bn-En-0.5M)", "BUET-BanglaBERT (Large)", "SagorSarker-BanglaBERT (Base)", "SentenceTransformers-LaBSE (Multilingual)"], 
                    label="Select a Model"
                )
            ]

            btn = gr.Button(value="Submit", elem_classes="mybtn")
            gr.ClearButton(inputs)

        with gr.Column():
            outputs = [
                gr.Textbox(label="English Translation"), 
                RichTextbox(label="Alignments Mapping (Source to Target)"),
                gr.Textbox(label="Alignment Accuracy")
            ]

    btn.click(process_alignments, inputs, outputs)

    gr.Examples([
        [
            "বাংলাদেশ দক্ষিণ এশিয়ার একটি সার্বভৌম রাষ্ট্র।", 
            "English", 
            "SentenceTransformers-LaBSE (Multilingual)", 
        ],
        [
            "বাংলাদেশের সংবিধানিক নাম কি?", 
            "English", 
            "Google-mBERT (Base-Multilingual)",
        ],
        [
            "বাংলাদেশের সাংবিধানিক নাম গণপ্রজাতন্ত্রী বাংলাদেশ।", 
            "Hindi", 
            "Google-mBERT (Base-Multilingual)",
        ]

    ], inputs)



# Launch the Gradio app
if __name__ == "__main__":
    demo.launch()