Name: NJUNLP
Type: Organization
Bio: Natural Language Processing Research Group, Department of Computer Science and Technology, Nanjing University
Location: Computer Science Building, 163 Xianlin Avenue, Nanjing 210023, P.R. China
Blog: http://nlp.nju.edu.cn
NJUNLP's Projects
The implement of AAAI-23 paper "CoP: Factual Inconsistency Detection by Controlling the Preference"
Repo for ACL2023 paper "BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training"
A Fine-grained Domain Adaptation Dataset
Code and data for paper "Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction". Aspect opinion pair datasets and aspect triplet datasets.
The code and datasets of our ACM MM 2024 paper "Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs".
Code for the EMNLP2023 main conference paper "IMTLab: An Open-Source Platform for Building, Evaluating, and Diagnosing Interactive Machine Translation Systems"
an easy-to-use knn-mt toolkit
Pretrain, finetune any LLMs from huggingface on your own data.
The implement of ACL2024: "MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization"
Multi-Candidate Speculative Decoding
Code and data for ACM MM '23 paper “MORE: A Multimodal Object-Entity Relation Extraction Dataset with a Benchmark Evaluation”
This is a named entity recognizer based on pytorch-pretrained-bert.
An open-source neural machine translation system developed by Natural Language Processing Group, Nanjing University.
NJUQE is an open-source toolkit to build machine translation quality estimation models.
Implementation of "Modeling Past and Future for Neural Machine Translation"
Linear decomposition toolkit for neural network.