Do Supervised Distributional Methods Really Learn Lexical Inference Relations?

Distributional representations of words have been recently used in supervised settings for recognizing lexical inference relations between word pairs, such as hypernymy and entailment. We investigate a collection of these state-of-the-art methods, and show that they do not actually learn a relation between two words. Instead, they learn an independent property of a single word in the pair: whether that word is a “prototypical hypernym”.

• Publication year

  2015

• Venue

  North American Chapter of the Association for Computational Linguistics

• Publication date

  Unknown publication date

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/v1/N15-1098
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Focused Entailment Graphs for Open IE Propositions

  2014cited by this paper
• Inclusive yet Selective: Supervised Distributional Hypernymy Detection

  2014influential reference
• Chasing Hypernyms in Vector Spaces with Entropy

  2014cited by this paper
• Learning Semantic Hierarchies via Word Embeddings

  2014cited by this paper
• Dependency-Based Word Embeddings

  2014cited by this paper
• Learning to Distinguish Hypernyms and Co-Hyponyms

  2014influential reference
• Experiments with three approaches to recognizing lexical entailment

  2014cited by this paper
• Distributional Lexical Entailment by Topic Coherence

  2014cited by this paper
• Efficient Estimation of Word Representations in Vector Space

  2013cited by this paper
• Text: now in 2D! A framework for lexical expansion with contextual similarity

  2013cited by this paper
• A Dataset of Syntactic-Ngrams over Time from a Very Large Corpus of English Books

  2013cited by this paper
• Distributed Representations of Words and Phrases and their Compositionality

  2013cited by this paper
• SemEval-2012 Task 2: Measuring Degrees of Relational Similarity

  2012cited by this paper
• Entailment above the word level in distributional semantics

  2012cited by this paper
• How we BLESSed distributional semantic evaluation

  2011cited by this paper
• Directional distributional similarity for lexical inference

  2010cited by this paper
• Distributional Memory: A General Framework for Corpus-Based Semantics

  2010cited by this paper
• Context-theoretic Semantics for Natural Language: an Overview

  2009cited by this paper
• Dependency-Based Construction of Semantic Space Models

  2007cited by this paper
• Similarity of Semantic Relations

  2006cited by this paper
• Learning Syntactic Patterns for Automatic Hypernym Discovery

  2004cited by this paper
• A General Framework for Distributional Similarity

  2003cited by this paper
• Experiments with LSA scoring: optimal rank and basis

  2001cited by this paper
• Automatic Retrieval and Clustering of Similar Words

  1998cited by this paper
• Co-Occurrence Vectors From Corpora vs. Distance Vectors From Dictionaries

  1994cited by this paper
• Part-of-Speech Induction From Scratch

  1993cited by this paper
• Automatic Acquisition of Hyponyms from Large Text Corpora

  1992influential reference
• Conference of the

  1991cited by this paper

• Hypernymy Relation in NLP: Tasks, Approaches, Resources, and Future Directions—A Systematic Literature Review

  2025influential citation
• Deep Learning and Natural Language Processing in the Field of Construction

  2025cites this paper
• Automated Expansion of Privacy Data Taxonomy for Compliant Data Breach Notification

  2025cites this paper
• Semantic enrichment of neural word embeddings: Leveraging taxonomic similarity for enhanced distributional semantics

  2025cites this paper
• A multi-projection recurrent model for hypernym detection and discovery

  2024cites this paper
• EP-BoxE: A method for hypernym discovery based on extended patterns and box embeddings

  2024cites this paper
• Meta4XNLI: A Crosslingual Parallel Corpus for Metaphor Detection and Interpretation

  2024cites this paper
• Shortcut Learning Explanations for Deep Natural Language Processing: A Survey on Dataset Biases

  2024cites this paper
• Building MUSCLE, a Dataset for MUltilingual Semantic Classification of Links between Entities

  2024influential citation
• Computational Models of Identity Presentation in Language

  2023cites this paper
• TaxoComplete: Self-Supervised Taxonomy Completion Leveraging Position-Enhanced Semantic Matching

  2023cites this paper
• 3D-EX: A Unified Dataset of Definitions and Dictionary Examples

  2023cites this paper
• Probing Taxonomic and Thematic Embeddings for Taxonomic Information

  2023cites this paper
• No clues good clues: out of context Lexical Relation Classification

  2023cites this paper
• Construction Artifacts in Metaphor Identification Datasets

  2023cites this paper
• A large-scale evaluation of NLP-derived chemical-gene/protein relationships from the scientific literature: Implications for knowledge graph construction

  2023cites this paper
• Automatic Methods for Extracting Taxonomic Relationships from Texts

  2023cites this paper
• The Universe of Utterances According to BERT

  2023cites this paper
• Relation Extraction: Hypernymy Discovery Using a Novel Pattern Learning Algorithm

  2023cites this paper
• Idioms, Probing and Dangerous Things: Towards Structural Probing for Idiomaticity in Vector Space

  2023cites this paper
• Fine-tuning language models to recognize semantic relations

  2023influential citation
• Large Language Models are not Fair Evaluators

  2023cites this paper
• Towards Visual Taxonomy Expansion

  2023cites this paper
• Hypernymy Detection for Low-resource Languages: A Study for Hindi, Bengali, and Amharic

  2022cites this paper
• HyperBox: A Supervised Approach for Hypernym Discovery using Box Embeddings

  2022cites this paper
• Detecting Stance in Scientific Papers: Did we get more Negative Recently?

  2022cites this paper
• Explainable lexical entailment with semantic graphs

  2022cites this paper
• Exploring Semantic Spaces for Detecting Clustering and Switching in Verbal Fluency

  2022cites this paper
• Combining Vision and Language Representations for Patch-based Identification of Lexico-Semantic Relations

  2022cites this paper
• A Survey of Parameters Associated with the Quality of Benchmarks in NLP

  2022cites this paper
• Lexical semantics enhanced neural word embeddings

  2022influential citation
• Three-order normalized PMI and other lessons in tensor analysis of verbal selectional preferences

  2022cites this paper
• Deep Neural Representations for Multiword Expressions Detection

  2022cites this paper
• Is Context All You Need? Non-contextual vs Contextual Multiword Expressions Detection

  2022cites this paper
• ALL Dolphins Are Intelligent and SOME Are Friendly: Probing BERT for Nouns’ Semantic Properties and their Prototypicality

  2021cites this paper
• Domain-specific Taxonomy Enrichment Based on Meta-Embeddings

  2021cites this paper
• Meta-Embeddings in Taxonomy Enrichment Task

  2021cites this paper
• Fine-Tuning Word Embeddings for Hierarchical Representation of Data Using a Corpus and a Knowledge Base for Various Machine Learning Applications

  2021cites this paper
• Automatic Classification of Attributes in German Adjective-Noun Phrases

  2021cites this paper
• A Theoretical Foundation for Syntactico-Semantic Pattern Recognition

  2021cites this paper
• Unsupervised Grammatical Pattern Discovery from Arabic Extra Large Corpora

  2021cites this paper
• FAST: A carefully sampled and cognitively motivated dataset for distributional semantic evaluation

  2021cites this paper
• A Mixture-of-Experts Model for Antonym-Synonym Discrimination

  2021cites this paper
• Combining text and vision in compound semantics: Towards a cognitively plausible multimodal model

  2021cites this paper
• Modeling Event Plausibility with Consistent Conceptual Abstraction

  2021cites this paper
• Evaluating language models for the retrieval and categorization of lexical collocations

  2021cites this paper
• Definitional Templating: A Novel Approach to Modeling the Compositional Semantics of Noun Compounds

  2021cites this paper
• Understanding Feature Focus in Multitask Settings for Lexico-semantic Relation Identification

  2021influential citation
• Inspecting the concept knowledge graph encoded by modern language models

  2021influential citation
• Coming to its senses: Lessons learned from Approximating Retrofitted BERT representations for Word Sense information

  2021cites this paper
• Dissertation Abstract:Learning High Precision Lexical Inferences

  2021cites this paper
• A 3-phase approach based on sequential mining and dependency parsing for enhancing hypernym patterns performance

  2021cites this paper
• Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classification

  2021cites this paper
• Open-Domain Contextual Link Prediction and its Complementarity with Entailment Graphs

  2021cites this paper
• How to Do Things without Words: Modeling Semantic Drift of Emoji

  2021cites this paper
• Recipes for Success: Data Science in the Home Kitchen

  2020cites this paper
• Mining Knowledge for Natural Language Inference from Wikipedia Categories

  2020cites this paper
• Cultural Cartography with Word Embeddings

  2020cites this paper
• An Empirical Study on Model-agnostic Debiasing Strategies for Robust Natural Language Inference

  2020cites this paper
• Order Embeddings for Supervised Hypernymy Detection

  2020cites this paper
• Supervised Hypernymy Detection in Spanish through Order Embeddings

  2020cites this paper
• Distinguishing between paradigmatic semantic relations across word classes: human ratings and distributional similarity

  2020cites this paper
• BiRRE: Learning Bidirectional Residual Relation Embeddings for Supervised Hypernymy Detection

  2020influential citation
• Recognizing Semantic Relations by Combining Transformers and Fully Connected Models

  2020cites this paper
• Multi task learning with general vector space for cross-lingual semantic relation detection

  2020cites this paper
• Data Augmentation for Hypernymy Detection

  2020cites this paper
• What are the Goals of Distributional Semantics?

  2020cites this paper
• Emergence of Syntax Needs Minimal Supervision

  2020cites this paper
• RUSSE'2020: Findings of the First Taxonomy Enrichment Task for the Russian language

  2020cites this paper
• Robustness in Coreference Resolution

  2020influential citation
• Core-Concept-seeded based LDA towards Ontology Learning

  2020cites this paper
• COMBINED APPROACH TO HYPERNYM DETECTION FOR THESAURUS ENRICHMENT

  2020cites this paper
• DQI: Measuring Data Quality in NLP

  2020cites this paper
• Brand-Product Relation Extraction Using Heterogeneous Vector Space Representations

  2020influential citation
• Within-Between Lexical Relation Classification Using Path-based and Distributional Data

  2020cites this paper
• Do Word Embeddings Capture Spelling Variation?

  2020influential citation
• On the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT

  2020cites this paper
• Evaluating visually grounded language capabilities using microworlds

  2020cites this paper
• Patch-Based Identification of Lexical Semantic Relations

  2020cites this paper
• An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification

  2020cites this paper
• Recognizing Semantic Relations: Attention-Based Transformers vs. Recurrent Models

  2020cites this paper
• Joint approaches for learning word representations from text corpora and knowledge bases

  2020cites this paper
• Target Word Masking for Location Metonymy Resolution

  2020cites this paper
• HypoNLI: Exploring the Artificial Patterns of Hypothesis-only Bias in Natural Language Inference

  2020cites this paper
• CogALex-VI Shared Task: Bidirectional Transformer based Identification of Semantic Relations

  2020cites this paper
• Word Attribute Prediction Enhanced by Lexical Entailment Tasks

  2020cites this paper
• Stress Test Evaluation of Transformer-based Models in Natural Language Understanding Tasks

  2020cites this paper
• KEML: A Knowledge-Enriched Meta-Learning Framework for Lexical Relation Classification

  2020influential citation
• Learning Word-pair Embeddings from Co-occurrences of Word Pairs and Lexico-syntactic Patterns to Recognize Semantic Relations between Nouns

  2020cites this paper
• Expanding Taxonomies with Implicit Edge Semantics

  2020cites this paper
• A Retrofitting Model for Incorporating Semantic Relations into Word Embeddings

  2020cites this paper
• A Combined Approach to Automatic Taxonomy Extraction

  2019cites this paper
• Can a Gorilla Ride a Camel? Learning Semantic Plausibility from Text

  2019cites this paper
• Learning Analogy-Preserving Sentence Embeddings for Answer Selection

  2019cites this paper
• Semantic Relata for the Evaluation of Distributional Models in Mandarin Chinese

  2019cites this paper
• Idiomaticity Prediction of Chinese Noun Compounds and Its Applications

  2019cites this paper
• Assessing the Lexico-Semantic Relational Knowledge Captured by Word and Concept Embeddings

  2019cites this paper
• What do Deep Networks Like to Read?

  2019cites this paper
• Exploiting Cross-Lingual Representations For Natural Language Processing

  2019cites this paper
• Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity

  2019cites this paper