Towards Understanding Linear Word Analogies (P19-1)

Copied to clipboard

Challenge: Existing theories of word embeddings make strong assumptions about the embeddable space or word distribution.
Approach: They propose a formal explanation of word analogies by adding arithmetic operators to non-linear embedding models such as skip-gram with negative sampling.
Outcome: The proposed model downweights the more frequent word, as weighting schemes do ad hoc.

Similar Papers

Sentence Analogies: Linguistic Regularities in Sentence Embeddings (2020.coling-main)

Copied to clipboard

Challenge: Word vectors are often evaluated by assessing to what degree they exhibit regularities with regard to relationships considered in word analogies.
Approach: They propose a number of schemes to induce evaluation data based on lexical analogy data as well as semantic relationships between sentences.
Outcome: The proposed models reflect regularities in lexical analogies and semantic relationships between sentences.
The Word Analogy Testing Caveat (N18-2)

Copied to clipboard

Challenge: a number of word analogy tests are used to evaluate word embeddings . word embeds are used as a proxy for semantics and syntax à la Harris .
Approach: They propose to use word embeddings as a proxy for distributional similarity . they propose to apply a transfer learning approach to word embeds to improve performance .
Outcome: The proposed method improves performance across a wide range of NLP tasks.
Paraphrases do not explain word analogies (2021.eacl-main)

Copied to clipboard

Challenge: Several attempts have been made to explain distributional word embeddings as linguistic regularities as directions.
Approach: They propose to use an analogy to explain why linguistic regularities should hold in distributional word embeddings.
Outcome: The proposed explanation does not hold empirically.
The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces (2025.naacl-short)

Copied to clipboard

Challenge: Existing studies have focused on simple factual recall, but we have not explored how this is used in more complex queries.
Approach: They propose to identify low-dimensional subspaces which encode numerical attributes associated with entities in comparison prompts.
Outcome: The proposed model can answer numeric comparison questions using a low-dimensional subspace of theembedding space.
Why is penguin more similar to polar bear than to sea gull? Analyzing conceptual knowledge in distributional models (2020.acl-srw)

Copied to clipboard

Challenge: Several analysis methods have been shown to be limited and are not well understood . thesis aims to understand distributional semantic representations based on linguistic data .
Approach: They propose a framework for investigating the information encoded in distributional semantic models . they combine observations made on corpora with insights obtained from data manipulation experiments .
Outcome: The proposed framework pairs observations made on corpora with insights obtained from data manipulation experiments.
Frustratingly Easy Meta-Embedding – Computing Meta-Embeddings by Averaging Source Word Embeddings (N18-2)

Copied to clipboard

Challenge: Existing methods for producing word embeddings have shown to produce accurate meta-embeddings from pre-trained source embeddables.
Approach: They propose to use arithmetic mean of two distinct word embedding sets to produce an accurate meta-embedding.
Outcome: The proposed method produces meta-embeddings comparable or better than more complex methods.
Analyzing the Surprising Variability in Word Embedding Stability Across Languages (2021.emnlp-main)

Copied to clipboard

Challenge: Word embeddings are powerful representations that form the foundation of many natural language processing architectures.
Approach: They explore word embedding stability in a wide range of languages to gain insight into their stability.
Outcome: The proposed results provide insights into word embedding stability in English and other languages.
Understanding Undesirable Word Embedding Associations (P19-1)

Copied to clipboard

Challenge: Word embeddings are often criticized for capturing undesirable word associations such as gender stereotypes.
Approach: They propose to use subspace projection to debias vectors post hoc using a model that implicitly does matrix factorization to debunk gender bias.
Outcome: The proposed test overestimates gender bias in word embeddings by using subspace projection, a method that is widely used in training.
Investigating Word-Class Distributions in Word Vector Spaces (2020.acl-main)

Copied to clipboard

Challenge: Existing studies have been successful in representing the meaning of a word with a vector in a continuous vector space, but little attention has been paid to the distribution of words belonging to a certain word class in . word vector spaces are useful for a range of natural language processing tasks, including selectional preference acquisition and entity set expansion.
Approach: They investigated the distribution of word vectors belonging to a certain word class in a pre-trained word vector space and compared their models to validate their assumptions.
Outcome: The proposed model fails to estimate how likely a word in the vector space is a member of a given word class, and the geometry of the distribution and existence of subgroups will have limited impact.
Rotate King to get Queen: Word Relationships as Orthogonal Transformations in Embedding Space (D19-1)

Copied to clipboard

Challenge: Word embeddings have a notable property that word relationships can exist as linear substructures in the embeddable space.
Approach: They propose an alternative way in which downstream models might learn these relationships: orthogonal and linear transformations.
Outcome: The proposed model can learn such relationships as geometric translations, but there is no evidence that it is exclusively accurate.

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