Alternatives and similar repositories for dice_loss:

Users that are interested in dice_loss are comparing it to the libraries listed below

• soumyac1999 / hyperbolic-label-emb-for-hmc
  Code for the paper Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification (EACL '21)
  ☆23Updated 3 years ago
• FranxYao / Partially-Observed-TreeCRFs
  Implementation of AAAI 21 paper: Nested Named Entity Recognition with Partially Observed TreeCRFs
  ☆52Updated 3 years ago
• lzy1732008 / GaussionTransformer
  For paper《Gaussian Transformer: A Lightweight Approach for Natural Language Inference》
  ☆29Updated 4 years ago
• LinyangLee / Token-Aware-VAT
  Code for our AAAI2021 paper: Token-Aware Virtual Adversarial Training For Language Understanding.
  ☆25Updated 4 years ago
• XL2248 / AGDT
  Code for "A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis." on EMNLP 2019.
  ☆21Updated 5 years ago
• xiaolin1207 / HTTN-master
  The code for "Does Head Label Help for Long-Tailed Multi-Label Text Classific"
  ☆29Updated 3 years ago
• EiraZhang / LACO
  This repository contains the code for our paper [Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task L…
  ☆33Updated 3 years ago
• shashwattrivedi / Attention_visualizer
  A visualizer to display attention weights on text
  ☆23Updated 5 years ago
• caiyinqiong / study_notes
  This is my study notes for my PhD in AI, NLP, IR, and more.
  ☆17Updated 3 years ago
• zzysay / KD4NRE
  Example code for paper "Distilling Knowledge from Well-informed Soft Labels for Neural Relation Extraction" (AAAI 2020).
  ☆22Updated 4 years ago
• kyzhouhzau / Relation_Extration
  Relation Classification via Convolutional Deep Neural Network
  ☆12Updated 6 years ago
• scewiner / Leveraging
  Leveraging Local and Global Patterns for Self-Attention Networks
  ☆12Updated 5 years ago
• JiachengLi1995 / JointIE
  A span-based joint named entity recognition (NER) and relation extraction model.
  ☆10Updated 4 years ago
• napoler / reformer-chinese
  reformer-pytorch中文版本，简单高效的生成模型。类似GPT2的效果
  ☆16Updated last year
• yym6472 / back_translate
  基于回译增强数据，目前整合了百度、有道、谷歌（需翻墙）翻译。
  ☆20Updated 4 years ago
• LindgeW / MetaAug4NER
  Robust Self-augmentation for NER with Meta-reweighting
  ☆29Updated 2 years ago
• jiachenwestlake / Multi-Cell_LSTM
  Multi-cell compositional LSTM for NER domain adaptation, code for ACL 2020 paper
  ☆30Updated 4 years ago
• zjunlp / DocED
  [ACL 2021] MLBiNet: A Cross-Sentence Collective Event Detection Network
  ☆35Updated 3 years ago
• Qqinmaster / FP-Net
  Feature Projection for Improved Text Classification
  ☆45Updated 4 years ago
• Alibaba-NLP / ProtoRE
  Code for 'Prototypical Representation Learning for Relation Extraction'.
  ☆30Updated 3 years ago
• kangISU / Conf-MPU-DS-NER
  Code for "Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning" published at AC…
  ☆23Updated 2 years ago
• rtmaww / LR-CNN
  ☆23Updated 5 years ago
• RUCAIBox / Context-Tuning
  This is the repository for COLING 2022 paper "Context-Tuning: Learning Contextualized Prompts for Natural Language Generation".
  ☆11Updated 2 years ago
• bojone / nezha
  精简版NEZHA模型权重
  ☆21Updated 4 years ago
• FFTYYY / RoR_relation_extraction
  Code for the paper "Relation of the Relations: A New Formalization of the Relation Extraction Problem"
  ☆27Updated last year
• unveiled-the-red-hat / SEE-Few
  Code for "SEE-Few: Seed, Expand and Entail for Few-shot Named Entity Recognition", accepted at COLING 2022.
  ☆12Updated 2 years ago
• bcol23 / HyperIM
  PyTorch implementation of the paper "Hyperbolic Interaction Model For Hierarchical Multi-Label Classification"
  ☆48Updated 5 years ago
• rz-zhang / SeqMix
  The repository for our EMNLP'20 paper SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup.
  ☆43Updated 3 years ago
• yizhen20133868 / Retriever-Dialogue
  end-to-end dialog system dataset
  ☆12Updated 5 years ago
• Vincent131499 / Language_Understanding_based_BERT
  基于BERT的预训练语言模型实现，分为两步：预训练和微调。目前已包括BERT、Roberta、ALbert三个模型，且皆可支持Whole Word Mask模式。
  ☆16Updated 4 years ago