An open source library for deep learning end-to-end dialog systems and chatbots.

基于金融-司法领域(兼有闲聊性质)的聊天机器人，其中的主要模块有信息抽取、NLU、NLG、知识图谱等，并且利用Django整合了前端展示,目前已经封装了nlp和kg的restful接口

A TensorFlow implementation of Recurrent Neural Networks for Sequence Classification and Sequence Labeling

slot filling, intent detection, joint training, ATIS & SNIPS datasets, the Facebook’s multilingual dataset, MIT corpus, E-commerce Shopping Assistant (ECSA) dataset, CoNLL2003 NER, ELMo, BERT, XLNet

attention based joint model for intent detection and slot filling

基于pytorch的中文意图识别和槽位填充

Open source code for EMNLP-19 Paper "A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding".

Joint Slot Filling and Intent Detection via Capsule Neural Networks (ACL'19) https://arxiv.org/abs/1812.09471

Few-Shot-Intent-Detection includes popular challenging intent detection datasets with/without OOS queries and state-of-the-art baselines and results.

Open-source ecosystem for building AI-powered conversational solutions using RAG, agents, FSMs, and LLMs.

BERT-based joint intent detection and slot filling with intent-slot attention mechanism (INTERSPEECH 2021)

Open source code for EMNLP 2020 Findings Paper "AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling"

Deep Open Intent Classification with Adaptive Decision Boundary (AAAI 2021)

Natural language understanding library for chatbots with intent recognition and entity extraction.

Implementation of Z-BERT-A: a zero-shot pipeline for unknown intent detection.

Open source code and data for AAAI 2022 Oral Paper "Text is no more Enough! A Benchmark for Profile-based Spoken Language Understanding"

MIntRec2.0 is the first large-scale dataset for multimodal intent recognition and out-of-scope detection in multi-party conversations (ICLR 2024)

Natural Language Processing

[RA-L20] Long-Term Pedestrian Trajectory Prediction Using Mutable Intention Filter and Warp LSTM

Complete code for the proposed CNN-Transformer model for natural language understanding.