An official website of the United States government
Computational models of verbal analogy and relational similarity judgments can employ different types of vector representations of word meanings (embeddings) generated by machine-learning algorithms. An important question is whether human-like relational processing depends on explicit representations of relations (i.e., representations separable from those of the concepts being related), or whether implicit relation representations suffice. Earlier machine-learning models produced static embeddings for individual words, identical across all contexts. However, more recent Large Language Models (LLMs), which use transformer architectures applied to much larger training corpora, are able to produce contextualized embeddings that have the potential to capture implicit knowledge of semantic relations. Here we compare multiple models based on different types of embeddings to human data concerning judgments of relational similarity and solutions of verbal analogy problems. For two datasets, a model that learns explicit representations of relations, Bayesian Analogy with Relational Transformations (BART), captured human performance more successfully than either a model using static embeddings (Word2vec) or models using contextualized embeddings created by LLMs (BERT, RoBERTa, and GPT-2). These findings support the proposal that human thinking depends on representations that separate relations from the concepts they relate.
more »
« less
Transforming neural network representations to predict human judgments of similarity
Deep-learning vision models have shown intriguing similarities and differences with respect to human vision. We investigate how to bring machine visual represen- tations into better alignment with human representations. Human representations are often inferred from behavioral evidence such as the selection of an image most similar to a query image. We find that with appropriate linear transformations of deep embeddings, we can improve prediction of human binary choice on a data set of bird images from 72% at baseline to 89%. We hypothesized that deep embeddings have redundant, high (4096) dimensional representations; however, reducing the rank of these representations results in a loss of explanatory power. We hypothesized that the dilation transformation of representations explored in past research is too restrictive, and indeed we found that model explanatory power can be significantly improved with a more expressive linear transform. Most surprising and exciting, we found that, consistent with classic psychological literature, human similarity judgments are asymmetric: the similarity of X to Y is not necessarily equal to the similarity of Y to X, and allowing models to express this asymmetry improves explanatory power.
more »
« less
- Award ID(s):
- 1631428
- PAR ID:
- 10299597
- Date Published:
- Journal Name:
- Workshop on Shared Visual Representations in Human and Machine Intelligence (SVRHM 2020)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract As inspirational stimuli can assist designers with achieving enhanced design outcomes, supporting the retrieval of impactful sources of inspiration is important. Existing methods facilitating this retrieval have relied mostly on semantic relationships, e.g., analogical distances. Increasingly, data-driven methods can be leveraged to represent diverse stimuli in terms of multi-modal information, enabling designers to access stimuli in terms of less explored, non-text-based relationships. Toward improved retrieval of multi-modal representations of inspirational stimuli, this work compares human-evaluated and computationally derived similarities between stimuli in terms of non-text-based visual and functional features. A human subjects study (n = 36) was conducted where similarity assessments between triplets of 3D-model parts were collected and used to construct psychological embedding spaces. Distances between unique part embeddings were used to represent similarities in terms of visual and functional features. Obtained distances were compared with computed distances between embeddings of the same stimuli generated using artificial intelligence (AI)-based deep-learning approaches. When used to assess similarity in appearance and function, these representations were found to be largely consistent, with highest agreement found when assessing pairs of stimuli with low similarity. Alignment between models was otherwise lower when identifying the same pairs of stimuli with higher levels of similarity. Importantly, qualitative data also revealed insights regarding how humans made similarity assessments, including more abstract information not captured using AI-based approaches. Toward providing inspiration to designers that considers design problems, ideas, and solutions in terms of non-text-based relationships, further exploration of how these relationships are represented and evaluated is encouraged.more » « less
-
Learning sentence representations which capture rich semantic meanings has been crucial for many NLP tasks. Pre-trained language models such as BERT have achieved great success in NLP, but sentence embeddings extracted directly from these models do not perform well without fine-tuning. We propose Contrastive Learning of Sentence Representations (CLSR), a novel approach which applies contrastive learning to learn universal sentence representations on top of pre-trained language models. CLSR utilizes semantic similarity of two sentences to construct positive instance for contrastive learning. Semantic information that has been captured by the pre-trained models is kept by getting sentence embeddings from these models with proper pooling strategy. An encoder followed by a linear projection takes these embeddings as inputs and is trained under a contrastive objective. To evaluate the performance of CLSR, we run experiments on a range of pre-trained language models and their variants on a series of Semantic Contextual Similarity tasks. Results show that CLSR gains significant performance improvements over existing SOTA language models.more » « less
-
Exploring Human and Language Model Alignment in Perceived Design Similarity Using Ordinal EmbeddingsAbstract In recent years, large language models (LLMs) and vision language models (VLMs) have excelled at tasks requiring human-like reasoning, inspiring researchers in engineering design to use language models (LMs) as surrogate evaluators of design concepts. But do these models actually evaluate designs like humans? While recent work has shown that LM evaluations sometimes fall within human variance on Likert-scale grading tasks, those tasks often obscure the reasoning and biases behind the scores. To address this limitation, we compare LM word embeddings (trained to capture semantic similarity) with human-rated similarity embeddings derived from triplet comparisons (“is A closer to B than C?”) on a dataset of design sketches and descriptions. We assess alignment via local tripletwise similarity and embedding distances, allowing for deeper insights than raw Likert-scale scores provide. We also explore whether describing the designs to LMs through text or images improves alignment with human judgments. Our findings suggest that text alone may not fully capture the nuances humans key into, yet text-based embeddings outperform their multimodal counterparts on satisfying local triplets. On the basis of these insights, we offer recommendations for effectively integrating LMs into design evaluation tasks.more » « less
-
null (Ed.)Representational Learning in the form of high dimensional embeddings have been used for multiple pattern recognition applications. There has been a significant interest in building embedding based systems for learning representations in the mathematical domain. At the same time, retrieval of structured information such as mathematical expressions is an important need for modern IR systems. In this work, our motivation is to introduce a robust framework for learning representations for similarity based retrieval of mathematical expressions. Given a query by example, the embedding can find the closest matching expression as a function of euclidean distance between them. We leverage recent advancements in image-based and graph-based deep learning algorithms to learn our similarity embeddings. We do this first, by using unimodal encoders in graph space and image space and then, a multi-modal combination of the same. To overcome the lack of training data, we force the networks to learn a deep metric using triplets generated with a heuristic scoring function. We also adopt a custom strategy for mining hard samples to train our neural networks. Our system produces rankings similar to those generated by the original scoring function, but using only a fraction of the time. Our results establish the viability of using such a multi-modal embedding for this task.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
