Starred repositories
Multimodal language model benchmark, featuring challenging examples
This repository introduces PIXIU, an open-source resource featuring the first financial large language models (LLMs), instruction tuning data, and evaluation benchmarks to holistically assess finan…
This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.
Papers and Datasets on Instruction Tuning and Following. ✨✨✨
modest natural-language processing
Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets
Survey of Surveys for Natural Language Processing (SOS4NLP)
Dirichlet Latent Variable Hierarchical Recurrent Encoder-Decoder in dialogue generation(EMNLP2019)
PyTorch Implementation of "A Hierarchical Latent Structure for Variational Conversation Modeling" (NAACL 2018 Oral)
The code and corpus of the work DiscProReco.
Transformer encoder-decoder for emotion detection in dialogues
PyTorch implementation for Interpretable Dialog Generation ACL 2018, It is released by Tiancheng Zhao (Tony) from Dialog Research Center, LTI, CMU
CrossNER: Evaluating Cross-Domain Named Entity Recognition (AAAI-2021)
Code and data for the paper "Facilitating the Communication of Politeness through Fine-Grained Paraphrasing". EMNLP 2020.
Interpretable Evaluation for (Almost) All NLP Tasks
Doc-ARC: Attending to Long-Distance Document Context for Sequence Labeling
A corpus of comments tagged for multiple attributes of unhealthiness.
Code for our EMNLP 2020 paper "Uncertainty-Aware Label Refinement for Sequence Labeling"
Datasets and codes for the paper "RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling". (EMNLP 2020)
[EMNLP'20][Findings] Official Repository for the paper "Why and when should you pool? Analyzing Pooling in Recurrent Architectures."