FastQA Neural Network
(Redirected from FastQA model)
Jump to navigation
Jump to search
A FastQA Neural Network is a bidirectional recurrent neural network for sequentially encoding that is training on SQuAD, NewsQA and MS-MARCO datasets to solve question answering tasks.
- Context:
- It consists of 3 different layers:
- …
- Example(s):
- Counter-Example(s):
- See: Question-Answering System, Natural Language Processing Task, Natural Language Understanding Task, Natural Language Generation Task.
References
2017
- (Weissenborn et al., 2017) ⇒ Dirk Weissenborn, Georg Wiese, and Laura Seiffe. (2017). “FastQA: A Simple and Efficient Neural Architecture for Question Answering.” In: CoRR, abs/1703.04816v1.
- QUOTE: On a high level, the FastQA model consists of three basic layers, namely the embedding, encoding and answer layer, that are described in detail in the following. We denote the hidden dimensionality of the model by $n$, the question tokens by $Q = \left(q_1, \cdots, q_{LQ} \right)$, and the context tokens by $X = \left(x_1, \cdots, x_{LX} \right)$. An illustration of the basic architecture is provided in Figure 1.
- QUOTE: On a high level, the FastQA model consists of three basic layers, namely the embedding, encoding and answer layer, that are described in detail in the following. We denote the hidden dimensionality of the model by $n$, the question tokens by $Q = \left(q_1, \cdots, q_{LQ} \right)$, and the context tokens by $X = \left(x_1, \cdots, x_{LX} \right)$. An illustration of the basic architecture is provided in Figure 1.
|