Accelerating Innovation Through Analogy Mining

@article{Hope2017AcceleratingIT,
  title={Accelerating Innovation Through Analogy Mining},
  author={Tom Hope and Joel Chan and Aniket Kittur and Dafna Shahaf},
  journal={Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  year={2017}
}
  • Tom Hope, Joel Chan, Dafna Shahaf
  • Published 17 June 2017
  • Computer Science
  • Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
The availability of large idea repositories (e.g., the U.S. patent database) could significantly accelerate innovation and discovery by providing people with inspiration from solutions to analogous problems. [] Key Method Our approach combines crowdsourcing and recurrent neural networks to extract purpose and mechanism vector representations from product descriptions. We demonstrate that these learned vectors allow us to find analogies with higher precision and recall than traditional information-retrieval…

Figures from this paper

SOLVENT
TLDR
SOLVENT is introduced, a mixed-initiative system where humans annotate aspects of research papers that denote their background, purpose, mechanism, and findings, and a computational model constructs a semantic representation from these annotations that can be used to find analogies among the research papers.
Scaling Creative Inspiration with Fine-Grained Functional Facets of Product Ideas
TLDR
This work proposes a novel computational representation that automatically breaks up products into fine-grained functional facets, and designs similarity metrics that support granular matching between functional facets across ideas, and uses them to build a novel functional search capability that enables expressive queries for mechanisms and purposes.
Cognitive Database: A Step towards Endowing Relational Databases with Artificial Intelligence Capabilities
TLDR
This work proposes Cognitive Databases, an approach for transparently enabling Artificial Intelligence (AI) capabilities in relational databases that exemplifies using AI functionality to endow relational databases with capabilities that were previously very hard to realize in practice.
A Computational Inflection for Scientific Discovery
TLDR
The confluence of societal and computational trends suggests that computer science is poised to ignite a revolution in the scientific process itself.
Learning a Lightweight Representation: First Step Towards Automatic Detection of Multidimensional Relationships between Ideas
  • A. Khiat
  • Computer Science
    2020 IEEE 14th International Conference on Semantic Computing (ICSC)
  • 2020
TLDR
This research in progress introduces an approach based on a sequence-to-sequence learning approach, which allows the machine to learn a lightweight structural representation that is used next to establishing multidimensional relationships between ideas (i.e different kind of relations between ideas).
Understanding the Source of Semantic Regularities in Word Embeddings
TLDR
This paper investigates the hypothesis that examples of a lexical relation in a corpus are fundamental to a neural word embedding’s ability to complete analogies involving the relation, and enhances the understanding of neuralword embeddings.
Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity
TLDR
A novel form of textual supervision is used for learning to match aspects across papers, and a fast single-match method achieves competitive results, paving the way for applying fine-grained similarity to large scientific corpora.
A Search Engine for Discovery of Scientific Challenges and Directions (preprint)/ en
TLDR
A novel task of extraction and search of scientific challenges and directions, to facilitate rapid knowledge discovery on a large corpus of interdisciplinary work relating to the COVID-19 pandemic, ranging from biomedicine to areas such as AI and economics.
Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners
TLDR
This paper proposes analogies as a new form of explanation in machine learning to identify diverse analogous pairs of examples that share the same level of similarity as the input pair and provides insight into (latent) factors underlying the model’s prediction.
Cross-domain Correspondences for Explainable Recommendations
TLDR
The notion of ‘correspondence’ between domains is formalised, illustrating this through the example of a simple mathematics problem, and how a correspondence-based recommender system could provide more explainable recommendations.
...
1
2
3
4
...

References

SHOWING 1-10 OF 72 REFERENCES
Scaling up Analogy with Crowdsourcing and Machine Learning
TLDR
This paper proposes to leverage crowdsourcing techniques to construct a dataset with rich “analogy-tuning” signals, used to guide machine learning models towards matches based on relations rather than surface features, and suggests that a deep learning model trained on positive/negative example analogies from the task can find more analogous matches than an LSA baseline.
A Simple but Tough-to-Beat Baseline for Sentence Embeddings
Measuring the similarity between implicit semantic relations from the web
TLDR
This work proposes a relational similarity measure, using a Web search engine, to compute the similarity between semantic relations implied by two pairs of words, and evaluates the proposed method in two tasks: classifying semantic relations between named entities, and solving word-analogy questions.
Encouraging “Outside- the- box” Thinking in Crowd Innovation Through Identifying Domains of Expertise
TLDR
An empirical study demonstrating how crowds can generate domains of expertise and that showing people an abstract representation rather than the original problem helps them identify more distant domains is reported.
GloVe: Global Vectors for Word Representation
TLDR
A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Similarity of Semantic Relations
TLDR
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.
Searching for analogical ideas with crowds
TLDR
This paper presents a novel approach for re-presenting a problem in terms of its abstract structure, and then allowing people to use this structural representation to find analogies, and proposes a crowdsourcing process that helps people navigate a large dataset to finding analogies.
The Roles of Similarity in Transfer: Separating Retrievability From Inferential Soundness
TLDR
There is a dissociation between the similarity that governs access to long-term memory and that which is used in evaluating and reasoning from a present match, and a model is described, called MAC/FAC, that uses a two-stage similarity retrieval process to model these findings.
Linear Algebraic Structure of Word Senses, with Applications to Polysemy
TLDR
It is shown that multiple word senses reside in linear superposition within the word embedding and simple sparse coding can recover vectors that approximately capture the senses.
Efficient Estimation of Word Representations in Vector Space
TLDR
Two novel model architectures for computing continuous vector representations of words from very large data sets are proposed and it is shown that these vectors provide state-of-the-art performance on the authors' test set for measuring syntactic and semantic word similarities.
...
1
2
3
4
5
...