Challenge: Attempts to find a single technique for general-purpose intrinsic evaluation of word embeddings have so far not been successful.
Approach: They propose a method that quantifies interpretable characteristics of word vector neighborhoods and shows how they correlate with performance on 14 extrinsic and intrinsic task datasets.
Outcome: The proposed approach enables multi-faceted evaluation, parameter search, and generally – a more principled, hypothesis-driven approach to development of distributional semantic representations.

Similar Papers

A Deeper Look into Dependency-Based Word Embeddings (N18-4)

Copied to clipboard

Challenge: Word embeddings trained with dependency contexts excel at different tasks, and enhanced dependencies often improve performance.
Approach: They propose to use dependency-based word embeddings to capture semantic similarity rather than relatedness.
Outcome: The results show that word embeddings trained with Universal and Stanford dependencies excel at different tasks and that enhanced dependencies often improve performance.
Just Rank: Rethinking Evaluation with Word and Sentence Similarities (2022.acl-long)

Copied to clipboard

Challenge: Word and sentence similarity tasks are the de facto evaluation method for embeddings.
Approach: They propose a new intrinsic evaluation method called EvalRank which shows a much stronger correlation with downstream tasks.
Outcome: The proposed method shows a much stronger correlation with downstream tasks and is released for future benchmarking purposes.
Are Word Embeddings Really a Bad Fit for the Estimation of Thematic Fit? (2020.lrec-1)

Copied to clipboard

Challenge: In recent years, vectors derived from neural network training have replaced count-based distributional semantic models as a de facto standard for word representation in NLP.
Approach: They propose to evaluate count models and word embeddings on thematic fit estimation by taking into account a larger number of parameters and verb roles and introducing dependency-based embedders in the comparison.
Outcome: The proposed model outperforms count models and word embeddings in thematic fit estimation tasks while introducing dependency-based embedders.
Benchmarking Meta-embeddings: What Works and What Does Not (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to build meta-embeddings have been evaluated using a variety of methods and datasets, which makes it difficult to draw meaningful conclusions regarding the merits of each approach.
Approach: They propose a unified framework for a fair and objective meta-embedding evaluation using intrinsic and extrinsic tasks.
Outcome: The proposed framework outperforms existing methods on intrinsic and extrinsic evaluation benchmarks and outperformed existing methods.
Do We Really Need All Those Dimensions? An Intrinsic Evaluation Framework for Compressed Embeddings (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluation methods for compressed text embeddings are either expensive or too simplistic.
Approach: They propose a task-agnostic intrinsic evaluation framework that provides a reliable proxy for downstream performance.
Outcome: The proposed framework provides a reliable proxy for downstream performance.
Towards Qualitative Word Embeddings Evaluation: Measuring Neighbors Variation (N18-4)

Copied to clipboard

Challenge: Using extrinsic evaluation methods, embeddings are evaluated on a specific task such as part-of-speech tagging or named-entity recognition.
Approach: They propose a method to study the variation between word embeddings models trained with only one parameter by observing the distributional neighbors variation.
Outcome: The proposed method shows that changing only one parameter can have a massive impact on a given semantic space.
Exploring the Value of Personalized Word Embeddings (2020.coling-main)

Copied to clipboard

Challenge: a subset of words belonging to specific psycholinguistic categories vary more in their representations across users . combining generic and personalized word embeddings yields the best performance .
Approach: They propose personalized word embeddings and compare their performance to generic ones . they show that personalized word representations can be leveraged for improved performance .
Outcome: The proposed model can be used for authorship attribution.
Comparing the Intrinsic Performance of Clinical Concept Embeddings by Their Field of Medicine (D19-62)

Copied to clipboard

Challenge: Existing work has trained medical embeddings to rep-resent medical concepts using specific medical data.
Approach: They use intrinsic methods to evaluate pre-trained word embeddings from the various fields of medicine as defined by their ICD-9 systems.
Outcome: The results show that the embeddings perform better in one field of medicine than in other fields.
Quantifying Compositionality of Classic and State-of-the-Art Embeddings (2025.findings-emnlp)

Copied to clipboard

Challenge: Static word embeddings make strong claims about compositionality, but the SOTA generative models go too far in the other direction.
Approach: a new study evaluates the compositionality of word embeddings by canonical correlation analysis . strong compositional signals are observed in later training stages across data modalities .
Outcome: a new evaluation of compositional models shows that they exploit access meanings when justified . strong compositional signals are observed in later training stages and in deeper layers of the transformer-based model before a decline at the top layer.
Word Embedding Evaluation in Downstream Tasks and Semantic Analogies (2020.lrec-1)

Copied to clipboard

Challenge: Language Models (LMs) are an oft studied area of natural language processing . Word Embeddings (WE) are vector space representations of a vocabulary .
Approach: They evaluate Word Embeddings (WE) models for the Portuguese langauage . results show that a diverse corpus can often outperform a larger, less textually diverse corp.
Outcome: The proposed models outperform a larger, less textually diverse corpus in two tasks . the evaluation shows that a diverse and comprehensive corpus outperformed a smaller, less diverse corp.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations