# Lexical Semantic Recognition

arXiv: https://arxiv.org/abs/2004.15008 · HTML: https://mlsanity.com/paper/2004.15008/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2020.

## Built on by (most cited first, 8 of 8)

- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [On the Relation between Syntactic Divergence and Zero-Shot Performance](https://mlsanity.com/paper/2110.04644/) (2021)
- [Knowledge Graph Construction and Its Application in Automatic Radiology Report Generation from Radiologist's Dictation](https://mlsanity.com/paper/2206.06308/) (2022)
- [CoAM: Corpus of All-Type Multiword Expressions](https://mlsanity.com/paper/2412.18151/) (2024)
- [Supersense and Sensibility: Proxy Tasks for Semantic Annotation of Prepositions](https://mlsanity.com/paper/2103.14961/) (2021)
- [Making Heads and Tails of Models with Marginal Calibration for Sparse Tagsets](https://mlsanity.com/paper/2109.07494/) (2021)
- [MASALA: Modelling and Analysing the Semantics of Adpositions in Linguistic Annotation of Hindi](https://mlsanity.com/paper/2205.03955/) (2022)
- [MWE as WSD: Solving Multiword Expression Identification with Word Sense Disambiguation](https://mlsanity.com/paper/2303.06623/) (2023)

## Abstract (arXiv)

In lexical semantics, full-sentence segmentation and segment labeling of various phenomena are generally treated separately, despite their interdependence. We hypothesize that a unified lexical semantic recognition task is an effective way to encapsulate previously disparate styles of annotation, including multiword expression identification / classification and supersense tagging. Using the STREUSLE corpus, we train a neural CRF sequence tagger and evaluate its performance along various axes of annotation. As the label set generalizes that of previous tasks (PARSEME, DiMSUM), we additionally evaluate how well the model generalizes to those test sets, finding that it approaches or surpasses existing models despite training only on STREUSLE. Our work also establishes baseline models and evaluation metrics for integrated and accurate modeling of lexical semantics, facilitating future work in this area.