# Learning Recurrent Span Representations for Extractive Question Answering

arXiv: https://arxiv.org/abs/1611.01436 · HTML: https://mlsanity.com/paper/1611.01436/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2016.

## Built on by (most cited first, 14 of 14)

- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Open Domain Question Answering over Tables via Dense Retrieval](https://mlsanity.com/paper/2103.12011/) (2021)
- [A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2101.00816/) (2021)
- [Packed Levitated Marker for Entity and Relation Extraction](https://mlsanity.com/paper/2109.06067/) (2021)
- [Copy Is All You Need](https://mlsanity.com/paper/2307.06962/) (2023)
- [Do Question Answering Modeling Improvements Hold Across Benchmarks?](https://mlsanity.com/paper/2102.01065/) (2021)
- [Parameter-Efficient Abstractive Question Answering over Tables or Text](https://mlsanity.com/paper/2204.03357/) (2022)
- [TREND: Trigger-Enhanced Relation-Extraction Network for Dialogues](https://mlsanity.com/paper/2108.13811/) (2021)
- [ANNA: Enhanced Language Representation for Question Answering](https://mlsanity.com/paper/2203.14507/) (2022)
- [An Empirical Study on Finding Spans](https://mlsanity.com/paper/2210.06824/) (2022)
- [SPOT: Knowledge-Enhanced Language Representations for Information Extraction](https://mlsanity.com/paper/2208.09625/) (2022)
- [Is Sluice Resolution really just Question Answering?](https://mlsanity.com/paper/2105.14347/) (2021)
- [TLAG: An Informative Trigger and Label-Aware Knowledge Guided Model for Dialogue-based Relation Extraction](https://mlsanity.com/paper/2303.17119/) (2023)
- [Highlight & Summarize: RAG without the jailbreaks](https://mlsanity.com/paper/2508.02872/) (2025)

## Abstract (arXiv)

The reading comprehension task, that asks questions about a given evidence document, is a central problem in natural language understanding. Recent formulations of this task have typically focused on answer selection from a set of candidates pre-defined manually or through the use of an external NLP pipeline. However, Rajpurkar et al. (2016) recently released the SQuAD dataset in which the answers can be arbitrary strings from the supplied text. In this paper, we focus on this answer extraction task, presenting a novel model architecture that efficiently builds fixed length representations of all spans in the evidence document with a recurrent network. We show that scoring explicit span representations significantly improves performance over other approaches that factor the prediction into separate predictions about words or start and end markers. Our approach improves upon the best published results of Wang & Jiang (2016) by 5% and decreases the error of Rajpurkar et al.'s baseline by > 50%.