Part & Whole Extraction: Towards A Deep Understanding of Quantitative Facts for Percentages in Text
Not on the map. Why?
Abstract (arXiv)
We study the problem of quantitative facts extraction for text with percentages. For example, given the sentence "30 percent of Americans like watching football, while 20% prefer to watch NBA.", our goal is to obtain a deep understanding of the percentage numbers ("30 percent" and "20%") by extracting their quantitative facts: part ("like watching football" and "prefer to watch NBA") and whole ("Americans). These quantitative facts can empower new applications like automated infographic generation. We formulate part and whole extraction as a sequence tagging problem. Due to the large gap between part/whole and its corresponding percentage, we introduce skip mechanism in sequence modeling, and achieved improved performance on both our task and the CoNLL-2003 named entity recognition task. Experimental results demonstrate that learning to skip in sequence tagging is promising.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 26 Oct 2021.
Builds on
17 of 29 references.
References · 17
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2018Deep contextualized word representationscited by 2,290
- 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
- 2016Neural Architectures for Named Entity Recognitioncited by 550
- 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 546
- 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
- 2016End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRFcited by 341
- 2015Named Entity Recognition with Bidirectional LSTM-CNNscited by 201
- 2017Semi-supervised sequence tagging with bidirectional language modelscited by 86
- 2017Skip RNN: Learning to Skip State Updates in Recurrent Neural Networkscited by 49
- 2018Jointly Predicting Predicates and Arguments in Neural Semantic Role Labelingcited by 34
- 2019Text-to-Viz: Automatic Generation of Infographics from Proportion-Related Natural Language Statementscited by 31
5 more
- 2017Learning to Skim Textcited by 18
- 2019Neural Speed Reading with Structural-Jump-LSTMcited by 17
- 2017Neural Speed Reading via Skim-RNNcited by 14
- 2018Textual Analogy Parsing: What's Shared and What's Compared among Analogous Factscited by 5
- 2019Leap-LSTM: Enhancing Long Short-Term Memory for Text Categorizationcited by 2
Built on by
Citing papers per year: 2022: 2.
2 papers.