TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Comprehensive Supersense Disambiguation of English Preposi...

Comprehensive Supersense Disambiguation of English Prepositions and Possessives

Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Jakob Prange, Austin Blodgett, Sarah R. Moeller, Aviram Stern, Adi Bitan, Omri Abend

2018-05-13ACL 2018 7Natural Language Understanding
PaperPDFCode(official)

Abstract

Semantic relations are often signaled with prepositional or possessive marking--but extreme polysemy bedevils their analysis and automatic interpretation. We introduce a new annotation scheme, corpus, and task for the disambiguation of prepositions and possessives in English. Unlike previous approaches, our annotations are comprehensive with respect to types and tokens of these markers; use broadly applicable supersense classes rather than fine-grained dictionary definitions; unite prepositions and possessives under the same class inventory; and distinguish between a marker's lexical contribution and the role it marks in the context of a predicate or scene. Strong interannotator agreement rates, as well as encouraging disambiguation results with established supervised methods, speak to the viability of the scheme and task.

Results

TaskDatasetMetricValueModel
Natural Language UnderstandingSTREUSLEFull F1 (Preps)58.9BiLSTM + MLP (gold syntax)
Natural Language UnderstandingSTREUSLEFunction F1 (Preps)73.4BiLSTM + MLP (gold syntax)
Natural Language UnderstandingSTREUSLERole F1 (Preps)62.2BiLSTM + MLP (gold syntax)
Natural Language UnderstandingSTREUSLEFull F1 (Preps)59.5SVM (feature-rich, gold syntax)
Natural Language UnderstandingSTREUSLEFunction F1 (Preps)71SVM (feature-rich, gold syntax)
Natural Language UnderstandingSTREUSLERole F1 (Preps)62.2SVM (feature-rich, gold syntax)
Natural Language UnderstandingSTREUSLEFull F1 (Preps)55.7SVM (feature-rich, auto syntax)
Natural Language UnderstandingSTREUSLEFunction F1 (Preps)66.7SVM (feature-rich, auto syntax)
Natural Language UnderstandingSTREUSLERole F1 (Preps)58.2SVM (feature-rich, auto syntax)
Natural Language UnderstandingSTREUSLEFull F1 (Preps)53.6BiLSTM + MLP (auto syntax)
Natural Language UnderstandingSTREUSLEFunction F1 (Preps)66.7BiLSTM + MLP (auto syntax)
Natural Language UnderstandingSTREUSLERole F1 (Preps)56.3BiLSTM + MLP (auto syntax)

Related Papers

Vision Language Action Models in Robotic Manipulation: A Systematic Review2025-07-14A Survey on Vision-Language-Action Models for Autonomous Driving2025-06-30State and Memory is All You Need for Robust and Reliable AI Agents2025-06-30skLEP: A Slovak General Language Understanding Benchmark2025-06-26SV-LLM: An Agentic Approach for SoC Security Verification using Large Language Models2025-06-25Semantic similarity estimation for domain specific data using BERT and other techniques2025-06-23An Interdisciplinary Review of Commonsense Reasoning and Intent Detection2025-06-16Towards Pervasive Distributed Agentic Generative AI -- A State of The Art2025-06-16