# Efficient and Robust Question Answering from Minimal Context over Documents

arXiv: https://arxiv.org/abs/1805.08092 · HTML: https://mlsanity.com/paper/1805.08092/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2018.

## Built on by (most cited first, 26 of 26)

- [DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion](https://mlsanity.com/paper/2407.12899/) (2024)
- [Efficient Classification of Long Documents Using Transformers](https://mlsanity.com/paper/2203.11258/) (2022)
- [A Survey for Efficient Open Domain Question Answering](https://mlsanity.com/paper/2211.07886/) (2022)
- [Saving Dense Retriever from Shortcut Dependency in Conversational Search](https://mlsanity.com/paper/2202.07280/) (2022)
- [Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering](https://mlsanity.com/paper/2105.11776/) (2021)
- [Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanation](https://mlsanity.com/paper/2201.05088/) (2022)
- [Complex Factoid Question Answering with a Free-Text Knowledge Graph](https://mlsanity.com/paper/2103.12876/) (2021)
- [From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering](https://mlsanity.com/paper/2205.11729/) (2022)
- [Modeling Context in Answer Sentence Selection Systems on a Latency Budget](https://mlsanity.com/paper/2101.12093/) (2021)
- [Improving Question Answering Performance Using Knowledge Distillation and Active Learning](https://mlsanity.com/paper/2109.12662/) (2021)
- [Citance-Contextualized Summarization of Scientific Papers](https://mlsanity.com/paper/2311.02408/) (2023)
- [Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction](https://mlsanity.com/paper/2111.09029/) (2021)
- [EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering System](https://mlsanity.com/paper/2101.02157/) (2021)
- [Complementary Evidence Identification in Open-Domain Question Answering](https://mlsanity.com/paper/2103.11643/) (2021)
- [Text Guide: Improving the quality of long text classification by a text selection method based on feature importance](https://mlsanity.com/paper/2104.07225/) (2021)
- [Machine Reading Comprehension using Case-based Reasoning](https://mlsanity.com/paper/2305.14815/) (2023)
- [Building a Question and Answer System for News Domain](https://mlsanity.com/paper/2105.05744/) (2021)
- [A Comprehensive Survey on Multi-hop Machine Reading Comprehension Datasets and Metrics](https://mlsanity.com/paper/2212.04070/) (2022)
- [A Comprehensive Survey on Multi-hop Machine Reading Comprehension Approaches](https://mlsanity.com/paper/2212.04072/) (2022)
- [Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding](https://mlsanity.com/paper/2301.03765/) (2023)
- [The Master-Slave Encoder Model for Improving Patent Text Summarization: A New Approach to Combining Specifications and Claims](https://mlsanity.com/paper/2411.14072/) (2024)
- [An Understanding-Oriented Robust Machine Reading Comprehension Model](https://mlsanity.com/paper/2207.00187/) (2022)
- [MRCLens: an MRC Dataset Bias Detection Toolkit](https://mlsanity.com/paper/2207.08943/) (2022)
- [SkIn: Skimming-Intensive Long-Text Classification Using BERT for Medical Corpus](https://mlsanity.com/paper/2209.05741/) (2022)
- [U3E: Unsupervised and Erasure-based Evidence Extraction for Machine Reading Comprehension](https://mlsanity.com/paper/2210.02621/) (2022)
- [Teach model to answer questions after comprehending the document](https://mlsanity.com/paper/2307.08931/) (2023)

## Abstract (arXiv)

Neural models for question answering (QA) over documents have achieved significant performance improvements. Although effective, these models do not scale to large corpora due to their complex modeling of interactions between the document and the question. Moreover, recent work has shown that such models are sensitive to adversarial inputs. In this paper, we study the minimal context required to answer the question, and find that most questions in existing datasets can be answered with a small set of sentences. Inspired by this observation, we propose a simple sentence selector to select the minimal set of sentences to feed into the QA model. Our overall system achieves significant reductions in training (up to 15 times) and inference times (up to 13 times), with accuracy comparable to or better than the state-of-the-art on SQuAD, NewsQA, TriviaQA and SQuAD-Open. Furthermore, our experimental results and analyses show that our approach is more robust to adversarial inputs.