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.
☆1,536Updated last year
Alternatives and similar repositories for bi-att-flow:
Users that are interested in bi-att-flow are comparing it to the libraries listed below
- Tensorflow implementation of contextualized word representations from bi-directional language models☆1,619Updated 2 years ago
- A Tensorflow implementation of QANet for machine reading comprehension☆981Updated 6 years ago
- A python tool for evaluating the quality of sentence embeddings.☆2,105Updated last year
- Pre-trained ELMo Representations for Many Languages☆1,460Updated 3 years ago
- Unsupervised Word Segmentation for Neural Machine Translation and Text Generation☆2,230Updated 8 months ago
- Tensorflow Implementation of R-Net☆578Updated 6 years ago
- A list of datasets/corpora for NLP tasks, in reverse chronological order.☆924Updated 5 years ago
- InferSent sentence embeddings☆2,284Updated 3 years ago
- Summary of deep learning models for dialog systems (Tiancheng Zhao LTI, CMU)☆651Updated 4 years ago
- Open-Source Neural Machine Translation in Tensorflow☆797Updated 2 years ago
- A pytorch implementation of Reading Wikipedia to Answer Open-Domain Questions.☆402Updated 3 years ago
- Resources, datasets, papers on Question Answering☆675Updated 2 years ago
- A text generation benchmarking platform☆864Updated 3 years ago
- Pre-training of Deep Bidirectional Transformers for Language Understanding: pre-train TextCNN☆964Updated 6 years ago
- Code for the ACL 2017 paper "Get To The Point: Summarization with Pointer-Generator Networks"☆2,189Updated 2 years ago
- Empower Sequence Labeling with Task-Aware Language Model☆847Updated 2 years ago
- General purpose unsupervised sentence representations☆1,204Updated 2 years ago
- ☆617Updated 8 years ago
- sentence embedding by Smooth Inverse Frequency weighting scheme☆1,088Updated 5 years ago
- ☆472Updated 3 years ago
- Keras implementation of BERT with pre-trained weights☆814Updated 5 years ago
- User Simulation for Task-Completion Dialogues☆805Updated last year
- ☆833Updated 7 years ago
- Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)☆1,212Updated 6 months ago
- The Natural Language Decathlon: A Multitask Challenge for NLP☆2,349Updated last year
- Semantic Text Similarity Dataset Hub☆719Updated 6 years ago
- Neural machine translation and sequence learning using TensorFlow☆1,469Updated last year
- Text classifier for Hierarchical Attention Networks for Document Classification☆1,077Updated 3 years ago
- Sequence-to-sequence model with LSTM encoder/decoders and attention☆1,273Updated 4 years ago
- Phrase-Based & Neural Unsupervised Machine Translation☆1,503Updated 3 years ago