The Latent Relation Mapping Engine: Algorithm and Experiments

  title={The Latent Relation Mapping Engine: Algorithm and Experiments},
  author={Peter D. Turney},
  journal={J. Artif. Intell. Res.},
  • Peter D. Turney
  • Published 1 September 2008
  • Computer Science
  • J. Artif. Intell. Res.
Many AI researchers and cognitive scientists have argued that analogy is the core of cognition. The most influential work on computational modeling of analogy-making is Structure Mapping Theory (SMT) and its implementation in the Structure Mapping Engine (SME). A limitation of SME is the requirement for complex hand-coded representations. We introduce the Latent Relation Mapping Engine (LRME), which combines ideas from SME and Latent Relational Analysis (LRA) in order to remove the requirement… 
Probabilistic Analogical Mapping with Semantic Relation Networks
A new computational model of mapping between two analogs that adopts a Bayesian framework for probabilistic graph matching, operating on semantic relation networks constructed from distributed representations of individual concepts and of relations between concepts is presented.
From Semantic Vectors to Analogical Mapping
This approach combines research in artificial intelligence with work in psychology and cognitive science, with the aim of minimizing hand coding of text inputs for reasoning tasks, and highlights the central role of semantics in analogical mapping.
Analogy perception applied to seven tests of word comprehension
PairClass is presented, an algorithm for analogy perception that recognises lexical proportional analogies using representations that are automatically generated from a large corpus of raw textual data.
Interpretation-driven mapping: A framework for conducting search and rerepresentation in parallel for computational analogy in design
A computational model informed by the framework Idiom, which learns ways to reinterpret the representations of objects as it maps between them is presented, which is useful for both describing existing analogy-making models and designing future ones.
Interpretation-driven mapping : a framework for conducting search and re-representation in parallel for computational analogy in design Submitted to : AIEDAM Special Issue on Analogical Thinking
A computational model informed by the framework, Idiom, that learns ways to reinterpret the representations of objects as it maps between them is presented, which is useful for both describing existing analogy-making models and designing future ones.
Ranking Relations using Analogies in Biological and Information Networks
An approach to relational learning which, given a set of pairs of objects S, measures how well other pairs A : B fit in with the set S, and combines a similarity measure on function spaces with Bayesian analysis to produce a ranking.
Neural Latent Relational Analysis to Capture Lexical Semantic Relations in a Vector Space
A novel model of this pattern-based approach to neural latent relational analysis, NLRA, which can generalize co-occurrences of word pairs and lexico-syntactic patterns, and obtain embeddings of the word pairs that do not co- Occur, overcomes the critical data sparseness problem encountered in previous patterns.
Analogy between concepts
A Relation-Centric View of Semantic Representation Learning
Semantic representations learned automatically from data have proven to be useful for many downstream applications such as question answering, word-sense discrimination and disambiguation, and selectional preference modeling and the term semantic representation learning is used to encompass all these views and techniques.
DISCOver: DIStributional approach based on syntactic dependencies for discovering COnstructions
Abstract One of the goals in Cognitive Linguistics is the automatic identification and analysis of constructions, since they are fundamental linguistic units for understanding language. This article


CorMet: A Computational, Corpus-Based Conventional Metaphor Extraction System
CorMet is a corpus-based system for discovering metaphorical mappings between concepts. It does this by finding systematic variations in domain-specific selectional preferences, which are inferred
A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge.
A new general theory of acquired similarity and knowledge representation, latent semantic analysis (LSA), is presented and used to successfully simulate such learning and several other psycholinguistic phenomena.
Measuring Semantic Similarity by Latent Relational Analysis
The LRA algorithm is described and state-of-the-art results are achieved, reaching human-level performance on the analogy questions and significantly exceeding VSM performance on both tasks.
Distributed representations of structure: A theory of analogical access and mapping.
An integrated theory of analogical access and mapping, instantiated in a computational model called LISA (Learning and Inference with Schemas and Analogies), suggesting that the architecture of LISA can provide computational explanations of properties of the human cognitive architecture.
Corpus-based Learning of Analogies and Semantic Relations
An algorithm for learning from unlabeled text that can solve verbal analogy questions of the kind found in the SAT college entrance exam and is state-of-the-art for both verbal analogies and noun-modifier relations is presented.
Analogical Mapping by Constraint Satisfaction
A theory of analogical mapping between source and target analogs based upon interacting structural, semantic, and pragmatic constraints is proposed here and is able to account for empirical findings regarding the impact of consistency and similarity on human processing of analogies.
Similarity of Semantic Relations
LRA extends the VSM approach in three ways: the patterns are derived automatically from the corpus, the Singular Value Decomposition (SVD) is used to smooth the frequency data, and automatically generated synonyms are used to explore variations of the word pairs.
The Structure-Mapping Engine: Algorithm and Examples
The Subtlety of Sameness: A Theory and Computer Model of Analogy-Making
At the heart of the author's theory and computer model of analogy-making is the idea that the building-up and the manipulation of representations are inseparable aspects of mental functioning, in contrast to traditional AI models of high-level cognitive processes, which have almost always depended on a clean separation.
Metaphor as an Emergent Property of Machine-Readable Dictionaries
It is argued that this approach to metaphor interpretation obviates the need for the traditional "metaphor-handling component" in natural language understanding systems, and will allow these systems to overcome the britdeness of hand-coded approaches.