FastQA: A Simple and Efficient Neural Architecture for Question Answering

By Dirk Weissenborn, Georg Wiese, Laura Seiffe. 2017

69 citations recorded by the source corpus.

Subfields: Information Retrieval & Search, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Simple and Effective Multi-Paragraph Reading Comprehension (2017, methodology): “…47.06 49.54 55.80 MEMEN* (Pan et al., 2017) 43.16 46.90 49.28 55.83 Mnemonic Reader (Hu et al., 2017) 46.94 52.85 54.45 59.46 Reading Twice for NLU (Weissenborn et al., 2017a) approaches as the model is used to independently process an increasing number of these paragraphs and the model’s most…”
NewsQA: A Machine Comprehension Dataset (2016, methodology): “We additionally report the results obtained by Weissenborn et al. (2017) using their FastQA model, which was near state-of-the-art on SQuAD at the time of writing.”
The NarrativeQA Reading Comprehension Challenge (2017, methodology): “Models which do well on SQuAD (e.g. Wang and Jiang (2016), Weissenborn et al. (2017)), extracting spans or pointing, do well here too, and the same concerns as above about the general applicability of solutions to this dataset to larger reading comprehension problems applies.”
Gated Self-Matching Networks for Reading Comprehension and Question Answering (2017, neutral): “1 FastQAExt (Weissenborn et al., 2017) - / - 70.”
Constructing Datasets for Multi-hop Reading Comprehension Across Documents (2017, methodology): “For both datasets we then establish several strong baselines and evaluate the performance of two previ-3 ously proposed competitive RC models (Seo et al., 2017; Weissenborn et al., 2017).”
Neural Approaches to Conversational AI (2018, positive): “Single-step reasoning is simple yet efficient and the model parameters can be trained using the classical back-propagation algorithm, thus it is adopted by most of the systems (Chen et al., 2016b; Seo et al., 2016; Wang et al., 2017b; Liu et al., 2017; Chen et al., 2017a; Weissenborn et al., 2017; H”
ReasoNet: Learning to Stop Reading in Machine Comprehension (2016, positive): “…[26] 64.7 73.7 67.9 77.0 RaSoR [14] - - 67.4 75.5 Multi-Perspective Matching [28] 68 Iterative Co-attention Network α 67.5 76.8 - - FastQA [30] 68.4 77.1 70.8 78.9 jNet [36] 68.7 77.4 - - Document Reader [4] 69.9 78.9 - - R-Net [27] 71.3 79.7 75.9 82.9 Vocab Size : We use the python NLTK…”
Stochastic Answer Networks for Machine Reading Comprehension (2017, methodology): “It is simple yet efficient and can be trained using the classical back-propagation algorithm, thus it is adopted by most of systems (Chen et al., 2016; Seo et al., 2016; Wang et al., 2017; Liu et al., 2017; Chen et al., 2017; Weissenborn et al., 2017; Hu et al., 2017).”
Quasar: Datasets for Question Answering by Search and Reading (2017, background): “Squad in particular has attracted considerable interest, but recent work (Weissenborn et al., 2017) suggests that answering the questions does not require a great deal of reasoning.”
Interpretation of Natural Language Rules in Conversational Machine Reading (2018, background): “In this sense, it is most related to work in Machine Reading (Ra-jpurkar et al., 2016; Seo et al., 2017; Weissenborn et al., 2017).”
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language (2019, methodology): “To this end, we examined all instances in which one of the neural QA models (with SENT2VEC) produced a correct prediction 6Note, that these numbers are taken from Welbl et al. (2017) and were obtained with different implementations of BIDAF and FASTQA and NLPROLOG did not, and labeled them with pred”
Reinforced Mnemonic Reader for Machine Comprehension (2017, methodology): “In the pointer layer, previous models (Weissenborn, Wiese, and Seiffe 2017; Chen et al. 2017) use the pointer network to calculate two probability distributions for the start and end position of the answer.”
Making Neural Machine Reading Comprehension Faster (2019, methodology): “Most of the papers that approach to solve SQuAD problem have utilized RNN based models [3, 5, 7, 9, 13, 14, 16, 17, 20, 22–24, 26, 29–31, 34–39, 41, 43] and they follow a similar chain of processes.”
Mnemonic Reader for Machine Comprehension (2017, background): “The architecture of these models is quite shallow, usually containing only one interaction layer (Weissenborn et al., 2017; Zhang et al., 2017).”
Globally Normalized Reader (2017, background): “Weissenborn et al. (2017) is a locally normalized model that ﬁrst predicts start and then end words of each span.”
Systematic Error Analysis of the Stanford Question Answering Dataset (2018, methodology): “FastQA (Weissenborn et al., 2017) added simple word matching features, indicating that a word was in both the passage and question, to a simple MRC model.”
Neural Models for Reasoning over Multiple Mentions Using Coreference (2018, methodology): “Following (Weissenborn et al., 2017), we also appended a feature to the word embeddings in the passage which indicated if the token appeared in the query or not.”
Question Answering by Reasoning Across Documents with Graph Convolutional Networks (2018, methodology): “The methods reported by Welbl et al. (2018) approach the task by merely concatenating all documents into a single long text and training a standard RNN-based reading comprehension model, namely, BiDAF (Seo et al., 2017) and FastQA (Weissenborn et al., 2017).”