Interpreting Embedding Spaces by Conceptualization

by   Adi Simhi, et al.

One of the main methods for semantic interpretation of text is mapping it into a vector in some embedding space. Such vectors can then be used for a variety of text processing tasks. Recently, most embedding spaces are a product of training large language models. One major drawback of this type of representation is its incomprehensibility to humans. Understanding the embedding space is crucial for several important needs, including the need to explain the decision of a system that uses the embedding, the need to debug the embedding method and compare it to alternatives, and the need to detect biases hidden in the model. In this paper, we present a novel method of transforming any embedding space into a comprehensible conceptual space. We first present an algorithm for deriving a conceptual space with dynamic on-demand granularity. We then show a method for transferring any vector in the original incomprehensible space to an understandable vector in the conceptual space. We combine human tests with cross-model tests to show that the conceptualized vectors indeed represent the semantics of the original vectors. We also show how the conceptualized vectors can be used for various tasks including identifying weaknesses in the semantics underlying the original spaces and differences in the semantics of alternative models.


Network2Vec Learning Node Representation Based on Space Mapping in Networks

Complex networks represented as node adjacency matrices constrains the a...

Analyzing Transformer Dynamics as Movement through Embedding Space

Transformer language models exhibit intelligent behaviors such as unders...

Stolen Probability: A Structural Weakness of Neural Language Models

Neural Network Language Models (NNLMs) generate probability distribution...

Modelling Semantic Categories using Conceptual Neighborhood

While many methods for learning vector space embeddings have been propos...

Grounding and Distinguishing Conceptual Vocabulary Through Similarity Learning in Embodied Simulations

We present a novel method for using agent experiences gathered through a...

Embedding Vector Differences Can Be Aligned With Uncertain Intensional Logic Differences

The DeepWalk algorithm is used to assign embedding vectors to nodes in t...

Topological Interpretations of GPT-3

This is an experiential study of investigating a consistent method for d...

Please sign up or login with your details

Forgot password? Click here to reset