amansrivastava17/bns-short-text-similarity
📖 Use Bi-normal Separation to find document vectors which is used to compute similarity for shorter sentences.
This helps classify short pieces of text, like customer queries or social media posts, by identifying key words that strongly relate to specific categories. You provide examples of short texts already assigned to categories, and it outputs a way to score new, unclassified texts for similarity to those categories. Anyone needing to automatically sort or respond to brief textual inputs, such as customer support agents or marketing analysts, would find this useful.
No commits in the last 6 months.
Use this if you need to accurately group or find similar short sentences or phrases, especially when traditional methods like TF-IDF struggle due to the brevity of the text.
Not ideal if your documents are long, complex articles, or if you do not have pre-categorized examples to train the system.
Stars
27
Forks
3
Language
Python
License
MIT
Category
Last pushed
Aug 21, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/amansrivastava17/bns-short-text-similarity"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shibing624/similarity
similarity: Text similarity calculation Toolkit for Java. 文本相似度计算工具包，java编写，可用于文本相似度计算、情感分析等任务，开箱即用。
eBay/Sequence-Semantic-Embedding
Tools and recipes to train deep learning models and build services for NLP tasks such as text...
RandolphVI/Text-Pairs-Relation-Classification
About Text Pairs (Sentence Level) Classification (Similarity Modeling) Based on Neural Network.
MartinoMensio/spacy-universal-sentence-encoder
Google USE (Universal Sentence Encoder) for spaCy
piotrmaciejbednarski/text-similarity-node
High-performance and memory efficient native C++ text similarity algorithms for Node.js