---
title: bidaf
canonical_url: "https://www.modelscope.cn/models/LLM-Research/bidaf"
md_url: "https://www.modelscope.cn/models/LLM-Research/bidaf.md"
repository: LLM-Research/bidaf
last_updated: 2024-09-08
pipeline_tag: question-answering
tasks:
  - question-answering
library_name:
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 2730
stars: 0
tags:
  - allennlp
  - question-answering
---

# bidaf

> bidaf - LLM-Research 在 ModelScope 开源的模型。This is an implementation of the BiDAF model with GloVe embeddings. The basic layout is pretty simple: encode words as a combination of word embeddings and a character-level encoder, pass the word representations…

- **Repository**: LLM-Research/bidaf
- **Tasks**: question-answering
- **Tags**: allennlp, question-answering
- **Downloads**: 2730
- **Stars**: 0
- **Last updated**: 2024-09-08

Source: https://www.modelscope.cn/models/LLM-Research/bidaf

---

This is an implementation of the BiDAF model with GloVe embeddings. The basic layout is pretty simple: encode words as a combination of word embeddings and a character-level encoder, pass the word representations through a bi-LSTM/GRU, use a matrix of attentions to put question information into the passage word representations (this is the only part that is at all non-standard), pass this through another few layers of bi-LSTMs/GRUs, and do a softmax over span start and span end.