Spaces:
Build error
Build error
| python -m spacy download en_core_web_sm | |
| import sensegram | |
| from wsd import WSD | |
| from gensim.models import KeyedVectors | |
| # Model files | |
| sense_vectors_fpath = "./best_sense_gram_model/best_model.sense_vectors" | |
| word_vectors_fpath = "./best_sense_gram_model/best_model.word_vectors" | |
| # Model parameters | |
| max_context_words = 3 | |
| context_window_size = 5 | |
| ignore_case = True | |
| lang = "ar" # to filter out stopwords | |
| # Model loading ... takes some time | |
| sv = sensegram.SenseGram.load_word2vec_format(sense_vectors_fpath, binary=False) | |
| wv = KeyedVectors.load_word2vec_format(word_vectors_fpath, binary=False, unicode_errors="ignore") | |
| # Method takes word and context and retirn the results of the model. | |
| def wsd_method(word, context): | |
| output = "" | |
| output += "Probabilities of the senses:\n{}\n\n".format(sv.get_senses(word, ignore_case=ignore_case)) | |
| for sense_id, prob in sv.get_senses(word, ignore_case=ignore_case): | |
| output += sense_id | |
| output += ("\n"+"="*20+"\n") | |
| for rsense_id, sim in sv.wv.most_similar(sense_id): | |
| output += "{} {:f}\n".format(rsense_id, sim) | |
| output +="\n" | |
| # Disambiguate a word in a context | |
| wsd_model = WSD(sv, wv, window=context_window_size, lang=lang, | |
| max_context_words=max_context_words, ignore_case=ignore_case) | |
| output += str(wsd_model.disambiguate(context, word)) | |
| return output | |
| import gradio as gr | |
| # Lanuching live demo | |
| demo = gr.Interface( | |
| fn=wsd_method, | |
| inputs=[gr.Textbox(lines=1, placeholder="الكلمة"),gr.Textbox(lines=2, placeholder="السياق")], | |
| outputs="text", | |
| title="فـك الالتباس الدلالي", | |
| description="فضلًا أدخل الكلمة ثم السياق ثم اضغط على زر إرسال، ولاستعراض المخرجات كاملة يرجى استخدام زر التمرير لأسفل.", | |
| ) | |
| demo.launch() | |