mlsanityData to 14 Oct 2026

An Empirical Study on Finding Spans

arXiv 2210.06824 ↗First posted 13 Oct 2022cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

We present an empirical study on methods for span finding, the selection of consecutive tokens in text for some downstream tasks. We focus on approaches that can be employed in training end-to-end information extraction systems, and find there is no definitive solution without considering task properties, and provide our observations to help with future design choices: 1) a tagging approach often yields higher precision while span enumeration and boundary prediction provide higher recall; 2) span type information can benefit a boundary prediction approach; 3) additional contextualization does not help span finding in most cases.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

25 of 40 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2018Deep contextualized word representationscited by 2,290
  5. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  6. 2016Neural Architectures for Named Entity Recognitioncited by 550
  7. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  8. 2016Bidirectional Attention Flow for Machine Comprehensioncited by 278
  9. 2019Entity, Relation, and Event Extraction with Contextualized Span Representationscited by 262
  10. 2017End-to-end Neural Coreference Resolutioncited by 241
  11. 2019A Unified MRC Framework for Named Entity Recognitioncited by 199
  12. 2020Event Extraction by Answering (Almost) Natural Questionscited by 177
13 more
  1. 2018Higher-order Coreference Resolution with Coarse-to-fine Inferencecited by 150
  2. 2019A General Framework for Information Extraction using Dynamic Span Graphscited by 93
  3. 2020Automated Concatenation of Embeddings for Structured Predictioncited by 86
  4. 2018Joint entity recognition and relation extraction as a multi-head selection problemcited by 59
  5. 2019Neural Architectures for Nested NER through Linearizationcited by 56
  6. 2021SpanNER: Named Entity Re-/Recognition as Span Predictioncited by 55
  7. 2018Harvesting Paragraph-Level Question-Answer Pairs from Wikipediacited by 49
  8. 2016Joint Extraction of Events and Entities within a Document Contextcited by 48
  9. 2021Coreference Resolution without Span Representationscited by 45
  10. 2019Nested Named Entity Recognition via Second-best Sequence Learning and Decodingcited by 34
  11. 2019Reading the Manual: Event Extraction as Definition Comprehensioncited by 26
  12. 2020Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognitioncited by 23
  13. 2016Learning Recurrent Span Representations for Extractive Question Answeringcited by 14

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2024MedDec: A Dataset for Extracting Medical Decisions from Discharge Summariescited by 4
  2. 2023Span Identification of Epistemic Stance-Taking in Academic Written Englishcited by 1