# Part & Whole Extraction: Towards A Deep Understanding of Quantitative Facts for Percentages in Text

arXiv: https://arxiv.org/abs/2110.13505 · HTML: https://mlsanity.com/paper/2110.13505/

## 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 (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF](https://mlsanity.com/paper/1603.01354/) (2016)
- [Named Entity Recognition with Bidirectional LSTM-CNNs](https://mlsanity.com/paper/1511.08308/) (2015)
- [Semi-supervised sequence tagging with bidirectional language models](https://mlsanity.com/paper/1705.00108/) (2017)
- [Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks](https://mlsanity.com/paper/1708.06834/) (2017)
- [Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling](https://mlsanity.com/paper/1805.04787/) (2018)
- [Text-to-Viz: Automatic Generation of Infographics from Proportion-Related Natural Language Statements](https://mlsanity.com/paper/1907.09091/) (2019)
- [Learning to Skim Text](https://mlsanity.com/paper/1704.06877/) (2017)
- [Neural Speed Reading with Structural-Jump-LSTM](https://mlsanity.com/paper/1904.00761/) (2019)
- [Neural Speed Reading via Skim-RNN](https://mlsanity.com/paper/1711.02085/) (2017)
- [Textual Analogy Parsing: What's Shared and What's Compared among Analogous Facts](https://mlsanity.com/paper/1809.02700/) (2018)
- [Leap-LSTM: Enhancing Long Short-Term Memory for Text Categorization](https://mlsanity.com/paper/1905.11558/) (2019)

## Built on by (most cited first, 2 of 2)

- [Generalized Quantifiers as a Source of Error in Multilingual NLU Benchmarks](https://mlsanity.com/paper/2204.10615/) (2022)
- [QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning](https://mlsanity.com/paper/2205.03075/) (2022)

## 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.