15 skills found
dhwajraj / Deep Siamese Text SimilarityTensorflow based implementation of deep siamese LSTM network to capture phrase/sentence similarity using character/word embeddings
kavgan / Nlp In PracticeStarter code to solve real world text data problems. Includes: Gensim Word2Vec, phrase embeddings, Text Classification with Logistic Regression, word count with pyspark, simple text preprocessing, pre-trained embeddings and more.
ehsansherkat / ConVecIn this project, we use skip-gram model to embed Wikipedia Concepts and Entities. The English version of Wikipedia contains more than five million pages, which suggest its capability to cover many English Entities, Phrases, and Concepts. Each Wikipedia page is considered as a concept.
JiachengLi1995 / UCTopicAn easy-to-use tool for phrase encoding and topic mining (unsupervised aspect extraction); Code base for ACL 2022 paper, UCTopic: Unsupervised Contrastive Learning for Phrase Representations and Topic Mining.
AnjaliDharmik / Text Similarity Using Siamese Deep Neural NetworkIt is a keras based implementation of Deep Siamese Bidirectional LSTM network to capture phrase/sentence similarity using word embedding.
hassyGo / SVOembeddingLearning embeddings for transitive verb phrases
easonlai / Product Recommendations With GptI have improved the demo by using Azure OpenAI’s Embedding model (text-embedding-ada-002), which has a powerful word embedding capability. This model can also vectorize product key phrases and recommend products based on cosine similarity, but with better results. You can find the updated repo here.
XMUDeepLIT / BattRAECode for "BattRAE: Bidimensional Attention-Based Recursive Autoencoders for Learning Bilingual Phrase Embeddings" (AAAI 2017)
jloveric / NeuralPhraseXMixed neural network / fuzzy similarity based phrase database matching. Uses universal sentence embeddings from Tensorflow combined with KNN and fuzzy similarity to perform slot filling based on a list of potential phrases. The approach allows for one shot learning and the efficiency will be determined by KNN (or other approximate nearest neighbor). The name "PhraseX" comes from "Regex", as it is a more flexible way of matching phrases than using regex and better suited for natural language.
anandaswarup / Phrase Break Prediction IS16Code for the paper titled "An investigation of recurrent neural network architectures using word embeddings for phrase break prediction", submitted to Interspeech 2016
bgnkim / NeuralPhraseEmbeddingImplementation of Phrase Embedding methods.
BridgeMia / Tencent Word2Vec AugmentationModification and Augmentation for Tencent AI Lab Embedding Corpus for Chinese Words and Phrases
ashwathkris / Keyphrase Extraction Using BERT As A Sentence EmbedderKeyphrases are words or short phrases that best describe a given input text document. The project uses BERT as a sentence embedder to better understand the context in a given sentence. The project makes use of cosine similarity to find the similarity between the document embedding and phrase embedding and rank them accordingly.
SannyZhou / WURAE Paraphrase Identification CNN LSTMProject of Paraphrase Identification Based on Weighted URAE, Unit Similarity and Context Correlation Feature
Team-TechLegionz / MediCareBot SIH 2020A chatbot that responds to the queries by the user/patient for clinical assistance by searching the Dataset for responses and this dataset will be in the form of .JSON file. Our chatbot is capable enough to interpret to all queries of the user/patient, analyze them and understand the intent of the queries. The chatbot shall search the entire dataset for response to the medical query. ChatBot will also be able to tackle and response to gibberish phrases by the user which is possible due to an appropriate Fallback Content. Chatbot gets trained owing to previously entered medical information and becomes more capable of responding to forthcoming medical queries. The Database has been maintained using MySQL and will be integrated with the NLP engine using Dialogflow API’s which can accomplish word embedding language modeling, part-of-speech tagging, intent and entity detection.
