allenai / bi-att-flow
Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization.
☆1,535Updated last year
Related projects ⓘ
Alternatives and complementary repositories for bi-att-flow
- A Tensorflow implementation of QANet for machine reading comprehension☆983Updated 6 years ago
- Tensorflow implementation of contextualized word representations from bi-directional language models☆1,620Updated last year
- Code for the ACL 2017 paper "Get To The Point: Summarization with Pointer-Generator Networks"☆2,179Updated 2 years ago
- InferSent sentence embeddings☆2,280Updated 3 years ago
- Tensorflow Implementation of R-Net☆578Updated 6 years ago
- Empower Sequence Labeling with Task-Aware Language Model☆846Updated 2 years ago
- A python tool for evaluating the quality of sentence embeddings.☆2,087Updated 8 months ago
- Named Entity Recognition Tool☆1,159Updated 5 years ago
- A list of datasets/corpora for NLP tasks, in reverse chronological order.☆919Updated 4 years ago
- MASS: Masked Sequence to Sequence Pre-training for Language Generation☆1,118Updated last year
- Semantic Text Similarity Dataset Hub☆715Updated 6 years ago
- BiLSTM-CNN-CRF architecture for sequence tagging☆828Updated 3 years ago
- Open-Source Neural Machine Translation in Tensorflow☆797Updated last year
- ☆472Updated 2 years ago
- Text classifier for Hierarchical Attention Networks for Document Classification☆1,069Updated 3 years ago
- Summary of deep learning models for dialog systems (Tiancheng Zhao LTI, CMU)☆651Updated 4 years ago
- Unsupervised Word Segmentation for Neural Machine Translation and Text Generation☆2,197Updated 3 months ago
- Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.☆1,481Updated last year
- Pre-trained ELMo Representations for Many Languages☆1,463Updated 3 years ago
- Keras implementation of BERT with pre-trained weights☆813Updated 5 years ago
- ☆829Updated 7 years ago
- A text generation benchmarking platform☆863Updated 3 years ago
- ☆434Updated 9 months ago
- Pre-training of Deep Bidirectional Transformers for Language Understanding: pre-train TextCNN☆959Updated 5 years ago
- A pytorch implementation of Reading Wikipedia to Answer Open-Domain Questions.☆401Updated 2 years ago
- User Simulation for Task-Completion Dialogues☆807Updated last year
- Resources, datasets, papers on Question Answering☆670Updated last year
- NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character …☆1,890Updated 2 years ago
- Named Entity Recognition (LSTM + CRF) - Tensorflow☆1,946Updated 4 years ago
- General purpose unsupervised sentence representations☆1,193Updated 2 years ago