# Where's My Head? Definition, Dataset and Models for Numeric Fused-Heads Identification and Resolution

arXiv: https://arxiv.org/abs/1905.10886 · HTML: https://mlsanity.com/paper/1905.10886/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2019.

## Built on by (most cited first, 11 of 11)

- [Representing Numbers in NLP: a Survey and a Vision](https://mlsanity.com/paper/2103.13136/) (2021)
- [Contrastive Explanations for Model Interpretability](https://mlsanity.com/paper/2103.01378/) (2021)
- [Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation](https://mlsanity.com/paper/2202.07654/) (2022)
- [Prompting with Pseudo-Code Instructions](https://mlsanity.com/paper/2305.11790/) (2023)
- [Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context](https://mlsanity.com/paper/2112.08616/) (2021)
- [CARE: Extracting Experimental Findings From Clinical Literature](https://mlsanity.com/paper/2311.09736/) (2023)
- [Superlatives in Context: Modeling the Implicit Semantics of Superlatives](https://mlsanity.com/paper/2405.20967/) (2024)
- [BERT Has Uncommon Sense: Similarity Ranking for Word Sense BERTology](https://mlsanity.com/paper/2109.09780/) (2021)
- [Great Service! Fine-grained Parsing of Implicit Arguments](https://mlsanity.com/paper/2106.02561/) (2021)
- [Meaning Representation of Numeric Fused-Heads in UCCA](https://mlsanity.com/paper/2106.07364/) (2021)
- [LLMs Infer Cultural Context but Fail to Apply It When Responding](https://mlsanity.com/paper/2606.17688/) (2026)

## Abstract (arXiv)

We provide the first computational treatment of fused-heads constructions (FH), focusing on the numeric fused-heads (NFH). FHs constructions are noun phrases (NPs) in which the head noun is missing and is said to be `fused' with its dependent modifier. This missing information is implicit and is important for sentence understanding. The missing references are easily filled in by humans but pose a challenge for computational models. We formulate the handling of FH as a two stages process: identification of the FH construction and resolution of the missing head. We explore the NFH phenomena in large corpora of English text and create (1) a dataset and a highly accurate method for NFH identification; (2) a 10k examples (1M tokens) crowd-sourced dataset of NFH resolution; and (3) a neural baseline for the NFH resolution task. We release our code and dataset, in hope to foster further research into this challenging problem.