| from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer | |
| import gradio as gr | |
| from spacy import displacy | |
| tokenizer = AutoTokenizer.from_pretrained("lirondos/anglicisms-spanish-mbert") | |
| model = AutoModelForTokenClassification.from_pretrained( | |
| "lirondos/anglicisms-spanish-mbert" | |
| ) | |
| nlp = pipeline("ner", model=model, tokenizer=tokenizer) | |
| diplacy_dict_template = { | |
| "text": "But Google is starting from behind.", | |
| "ents": [{"start": 4, "end": 10, "label": "ORG"}], | |
| "title": None, | |
| } | |
| def infer(input_text): | |
| displacy_ents = [] | |
| borrowings = nlp(input_text) | |
| for borrowing in borrowings: | |
| displacy_ent_dict = { | |
| "start": borrowing["start"], | |
| "end": borrowing["end"], | |
| "label": borrowing["entity"], | |
| } | |
| displacy_ents.append(displacy_ent_dict) | |
| colors = {"B-ENG": "linear-gradient(90deg, #aa9cfc, #fc9ce7)", | |
| "I-ENG": "linear-gradient(90deg, #99bfff, #a57cf0)", | |
| "B-OTHER": "linear-gradient(90deg, #79d0a5, #f6e395)", | |
| "I-OTHER": "linear-gradient(90deg, #f79a76, #fb6d6d)"} | |
| options = {"ents": ["B-ENG", "I-ENG", "B-OTHER", "I-OTHER"], "colors": colors} | |
| displacy_dict_template = {"text": input_text, "ents": displacy_ents, "title": None} | |
| html = displacy.render(displacy_dict_template, style="ent", page=True, manual=True, options=options) | |
| html = ( | |
| "" | |
| + html | |
| + "" | |
| ) | |
| return html | |
| description="""This space is a demo for the paper [Detecting Unassimilated Borrowings in Spanish: | |
| An Annotated Corpus and Approaches to Modeling](https://arxiv.org/pdf/2203.16169.pdf) | |
| The goal of the underlying model is to detect foreign words, e.g. anglicisms, in spanish texts. | |
| In general it has two types of tags for foreign words: *ENG* and *OTHER*. The authors used [BIO-tagging](https://en.wikipedia.org/wiki/Inside%E2%80%93outside%E2%80%93beginning_(tagging)), | |
| which is why in practice you will see a *B-* or *I-* in front of the tags. | |
| """ | |
| demo = gr.Interface( | |
| title="Borrowing Detection Español", | |
| description=description, | |
| fn=infer, | |
| inputs=gr.Text(), | |
| outputs=gr.HTML(), | |
| examples=["Buscamos data scientist para proyecto de machine learning.", | |
| "Las fake news sobre la celebrity se reprodujeron por los 'mass media' en prime time.", | |
| "Me gusta el cine noir y el anime."], | |
| ) | |
| demo.launch() | |