import gradio as gr from transformers import pipeline from transformers_interpret import SequenceClassificationExplainer from bs4 import BeautifulSoup # Setup model classifier = pipeline("text-classification", model="simonschoe/TransformationTransformer") explainer = SequenceClassificationExplainer(classifier.model, classifier.tokenizer) legend = """
Legend: Generic Transformation
""" def classify(_input): """ wrapper method to compute label 1 probability and explanation for given input """ result = classifier(_input)[0] score = result['score'] if result['label'] == 'LABEL_0': score = 1-score # getting visualization attributions = explainer(_input) html = explainer.visualize().__html__() soup = BeautifulSoup(html, 'html.parser') explanation = soup.find_all('td')[-1].__str__().replace('td', 'div') # adding legend to word importance explanation result_html = explanation + legend return score, result_html app = gr.Blocks() with app: gr.Markdown("# Call2Vec") gr.Markdown("## Semantic Search in Quarterly Earnings Conference Calls") with gr.Row(): with gr.Column(): text_in = gr.Textbox(lines=1, placeholder="Insert text", label="Search Query") with gr.Row(): compute_bt = gr.Button("Calculate") score_out = gr.Number(label="Label 1 probability", interactive=False) html_out = gr.HTML(label="Explanation") with gr.Column(): gr.Markdown( """ #### Project Description Call2Vec is a [fastText](https://fasttext.cc/) word embedding model trained via [Gensim](https://radimrehurek.com/gensim/). It maps each token in the vocabulary into a dense, 300-dimensional vector space, designed for performing semantic search. The model is trained on a large sample of quarterly earnings conference calls, held by U.S. firms during the 2006-2022 period. In particular, the training data is restriced to the (rather sponentous) executives' remarks of the Q&A section of the call. The data has been preprocessed prior to model training via stop word removal, lemmatization, named entity masking, and coocurrence modeling. """ ) gr.Markdown( """ #### App usage The model is intented to be used for **semantic search**: It encodes the search query (entered in the textbox on the right) in a dense vector space and finds semantic neighbours, i.e., token which frequently occur within similar contexts in the underlying training data. The model allows for two use cases: 1. *Single Search:* The input query consists of a single word. When provided a bi-, tri-, or even fourgram, the quality of the model output depends on the presence of the query token in the model's vocabulary. N-grams should be concated by an underscore (e.g., "machine_learning" or "artifical_intelligence"). 2. *Multi Search:* The input query may consist of several words or n-grams, seperated by comma, semi-colon or newline. It then computes the average vector over all inputs and performs semantic search based on the average input token. """ ) gr.Examples( examples=[["Now Accord networks is a company in video, and he led the sales team, and the marketing group at Accord, and he took it from start up, sound familiar, it's from start up to $60 million company in two years."], ["Another test sentence"], ["Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam"]], inputs=[text_in], outputs=[score_out, html_out], fn=classify, cache_examples=True ) gr.Markdown( """

Call2Vec by X and Y
visitor badge

""" ) compute_bt.click(classify, inputs=[text_in], outputs=[score_out, html_out]) app.launch()