thuiar/TEXTOIR
TEXTOIR is the first opensource toolkit for text open intent recognition. (ACL 2021)
TEXTOIR helps identify and categorize user intentions from text data, even when those intentions haven't been seen before. You provide text inputs, and it outputs classifications for known intentions and flags for unknown ones, or groups all intentions, known and unknown, into fine-grained clusters. This toolkit is ideal for researchers and developers working on natural language understanding systems, especially in areas like chatbot development, customer service automation, or sentiment analysis.
243 stars.
Use this if you need to build a system that can understand a predefined set of user requests but also reliably detect entirely new types of requests or group similar, yet unknown, requests together.
Not ideal if your text analysis only involves classifying text into a strictly closed set of predefined categories, without any need to identify or discover new types of intent.
Stars
243
Forks
31
Language
Python
License
MIT
Category
Last pushed
Nov 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/thuiar/TEXTOIR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
chakki-works/sumeval
Well tested & Multi-language evaluation framework for text summarization.
zhang17173/Event-Extraction
基于法律裁判文书的事件抽取及其应用，包括数据的分词、词性标注、命名实体识别、事件要素抽取和判决结果预测等内容
wasiahmad/paraphrase_identification
Examine two sentences and determine whether they have the same meaning.
artitw/BERT_QA
Accelerating the development of question-answering systems based on BERT and TF 2.0
victordibia/neuralqa
NeuralQA: A Usable Library for Question Answering on Large Datasets with BERT