Query-Reduction Networks for Question Answering

By Minjoon Seo, Sewon Min, Ali Farhadi, Hannaneh Hajishirzi. 2016

101 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Universal Transformers (2018, methodology): “Model 10K examples 1K examples train single train joint train single train joint Previous best results: QRNet [24] 0.”
Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge (2018, methodology): “As BiDAF is a direct answer system, we adapted it to multiple-choice QA following the approach used in several previous projects (Khashabi et al., 2018b; Welbl et al., 2017a; Kembhavi et al., 2017) as follows: First, given a question, we create a single paragraph by concatenating a set of retrieved ”
Coarse-to-Fine Question Answering for Long Documents (2016, background): “State-of-the-art question answering models (Chen et al., 2016; Seo et al., 2016) use RNN models to encode the document and question and selects the answer.”
ParlAI: A Dialog Research Software Platform (2017, neutral): “Overall, while DrQA can solve some of the bAbI tasks and performs well on SQuAD, it does not match the best performing methods on bAbI (Seo et al., 2016; Henaff et al., 2016), and multitasking does not help.”
Constructing Datasets for Multi-hop Reading Comprehension Across Documents (2017, background): “times (Sordoni et al., 2016; Neumann et al., 2016; Seo et al., 2017b; Hu et al., 2017) and may contain trainable stopping mechanisms (Graves, 2016; Shen et al.”
Regularizing and Optimizing LSTM Language Models (2017, background): “This can be done either through restricting the capacity of the matrix (Arjovsky et al., 2016; Wisdom et al., 2016; Jing et al., 2016) or through element-wise interactions (Balduzzi & Ghifary, 2016; Bradbury et al., 2016; Seo et al., 2016).”
Cognitive Graph for Multi-Hop Reading Comprehension at Scale (2019, background): “The idea of “multi-step reasoning” also breeds multi-turn methods in single paragraph QA (Kumar et al., 2016; Seo et al., 2017b; Shen et al., 2017), assuming that models can capture information at deeper level implicitly by reading the text again.”
Ask the Right Questions: Active Question Reformulation with Reinforcement Learning (2017, methodology): “AQA outperforms a deep network built for QA, BiDAF [Seo et al., 2017a], which has produced state-of-the-art results on multiple tasks, by 11% absolute F1, a 32% relative F1 improvement.”
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems (2018, methodology): “End-to-end task-oriented dialog systems train a single model directly on text transcripts of di-alogs (Wen et al., 2017; Serban et al., 2016; Williams et al., 2017; Zhao et al., 2017; Seo et al., 2017; Serban et al., 2017).”
Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems (2018, background): “In the same line of research, people explored using query-regression networks (Seo et al., 2016), gated memory networks (Liu and Perez, 2017), and copy-augmented networks (Eric and Manning, 2017) to learn the dialogue state.”
Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension (2018, background): “, 2016) and Query-reduction Networks (Seo et al., 2017b), we find that they do not perform well on ProPara and the results are only slightly better than the majority baselines.”
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language (2019, methodology): “Following Welbl et al. (2017), we use two neural QA models, namely B I DAF (Seo et al., 2016a) and F AST QA (Weissenborn et al., 2017b), as base-lines for the considered W IKI H OP predicates.”
Global-to-local Memory Pointer Networks for Task-Oriented Dialogue (2019, methodology): “Baselines are reported from Query Reduction Network (Seo et al., 2017), End-to-end Memory Network (Bordes & Weston, 2017), Gated Memory Network (Liu & Perez, 2017), Point to Unknown Word (Gulcehre et al.”
Be Consistent! Improving Procedural Text Comprehension using Label Consistency (2019, unknown): “EntNet (Hena ﬀ et al., 2017) 54.7 30.7 39.4 QRN (Seo et al., 2017) 60.9 31.1 41.1 ProLocal (Dalvi et al., 2018) 81.7 36.8 50.7 ProGlobal (Dalvi et al., 2018) 61.7 44.8 51.9 P ro S truct (Tandon et al., 2018) The results are shown in Table 1.”
Neural Speed Reading via Skim-RNN (2017, methodology): “3% of BiDAF to 77 .”
A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue (2017, methodology): “Other cited work using the DSTC2 dataset (Bordes and We-ston, 2016; Liu and Perez, 2016; Seo et al., 2016) implement similar mechanisms whereby they expand the feature representations of candidate sys-tem responses based on whether there is lexical entity class matching with provided dialogue…”
Neural Models for Reasoning over Multiple Mentions Using Coreference (2018, background): “, 2016), QRNs (Seo et al., 2017b) (the best published results on bAbi-1K), and our models.”
Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading (2018, background): “Sukhbaatar et al. (2015) and Seo et al. (2016) focused on solving the bAbI tasks.”