Word Equations: Inherently Interpretable Sparse Word Embeddingsthrough Sparse Coding

• URL: http://arxiv.org/abs/2004.13847v3
• Date: Mon, 27 Sep 2021 21:43:39 GMT
• Title: Word Equations: Inherently Interpretable Sparse Word Embeddingsthrough Sparse Coding
• Authors: Adly Templeton
• Abstract summary: We create a system where each dimension is associated with some human understandable hint that can describe the meaning of that dimension. We construct these embeddings through sparse coding, where each vector in the basis set is itself a word embedding. We show that models trained using these sparse embeddings can achieve good performance and are more interpretable in practice, including through human evaluations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Word embeddings are a powerful natural language processing technique, but they are extremely difficult to interpret. To enable interpretable NLP models, we create vectors where each dimension is inherently interpretable. By inherently interpretable, we mean a system where each dimension is associated with some human understandable hint that can describe the meaning of that dimension. In order to create more interpretable word embeddings, we transform pretrained dense word embeddings into sparse embeddings. These new embeddings are inherently interpretable: each of their dimensions is created from and represents a natural language word or specific grammatical concept. We construct these embeddings through sparse coding, where each vector in the basis set is itself a word embedding. Therefore, each dimension of our sparse vectors corresponds to a natural language word. We also show that models trained using these sparse embeddings can achieve good performance and are more interpretable in practice, including through human evaluations.

Related papers

• Adjusting Interpretable Dimensions in Embedding Space with Human Judgments [15.311454588182707]
  Embedding spaces contain interpretable dimensions indicating gender, formality in style, or even object properties. The standard way to compute these dimensions uses contrasting seed words and computes difference vectors over them. We combine seed-based vectors with guidance from human ratings of where words fall along a specific dimension, and evaluate on predicting both object properties like size and danger.
  arXiv  Detail & Related papers  (2024-04-03T10:13:18Z)
• Interpretable Neural Embeddings with Sparse Self-Representation [6.969983808566474]
  Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a black-box and prevents them from being human-readable and further manipulation. We propose a novel method to associate data self-representation with a shallow neural network to learn expressive, interpretable word embeddings.
  arXiv  Detail & Related papers  (2023-06-25T05:57:01Z)
• Representation Of Lexical Stylistic Features In Language Models' Embedding Space [28.60690854046176]
  We show that it is possible to derive a vector representation for each of these stylistic notions from only a small number of seed pairs. We conduct experiments on five datasets and find that static embeddings encode these features more accurately at the level of words and phrases. The lower performance of contextualized representations at the word level is partially attributable to the anisotropy of their vector space.
  arXiv  Detail & Related papers  (2023-05-29T23:44:26Z)
• SenteCon: Leveraging Lexicons to Learn Human-Interpretable Language Representations [51.08119762844217]
  SenteCon is a method for introducing human interpretability in deep language representations. We show that SenteCon provides high-level interpretability at little to no cost to predictive performance on downstream tasks.
  arXiv  Detail & Related papers  (2023-05-24T05:06:28Z)
• Linear Spaces of Meanings: Compositional Structures in Vision-Language Models [110.00434385712786]
  We investigate compositional structures in data embeddings from pre-trained vision-language models (VLMs) We first present a framework for understanding compositional structures from a geometric perspective. We then explain what these structures entail probabilistically in the case of VLM embeddings, providing intuitions for why they arise in practice.
  arXiv  Detail & Related papers  (2023-02-28T08:11:56Z)
• Low-Dimensional Structure in the Space of Language Representations is Reflected in Brain Responses [62.197912623223964]
  We show a low-dimensional structure where language models and translation models smoothly interpolate between word embeddings, syntactic and semantic tasks, and future word embeddings. We find that this representation embedding can predict how well each individual feature space maps to human brain responses to natural language stimuli recorded using fMRI. This suggests that the embedding captures some part of the brain's natural language representation structure.
  arXiv  Detail & Related papers  (2021-06-09T22:59:12Z)
• Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel Corpora [63.5286019659504]
  We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus. Our method obtains word embeddings via an LSTM encoder-decoder model that simultaneously translates and reconstructs an input sentence.
  arXiv  Detail & Related papers  (2020-10-27T22:24:01Z)
• Learning Universal Representations from Word to Sentence [89.82415322763475]
  This work introduces and explores the universal representation learning, i.e., embeddings of different levels of linguistic unit in a uniform vector space. We present our approach of constructing analogy datasets in terms of words, phrases and sentences. We empirically verify that well pre-trained Transformer models incorporated with appropriate training settings may effectively yield universal representation.
  arXiv  Detail & Related papers  (2020-09-10T03:53:18Z)
• Using Holographically Compressed Embeddings in Question Answering [0.0]
  This research employs holographic compression of pre-trained embeddings to represent a token, its part-of-speech, and named entity type. The implementation, in a modified question answering recurrent deep learning network, shows that semantic relationships are preserved, and yields strong performance.
  arXiv  Detail & Related papers  (2020-07-14T18:29:49Z)
• Supervised Understanding of Word Embeddings [1.160208922584163]
  We have obtained supervised projections in the form of the linear keyword-level classifiers on word embeddings. We have shown that the method creates interpretable projections of original embedding dimensions.
  arXiv  Detail & Related papers  (2020-06-23T20:13:42Z)
• Anchor & Transform: Learning Sparse Embeddings for Large Vocabularies [60.285091454321055]
  We design a simple and efficient embedding algorithm that learns a small set of anchor embeddings and a sparse transformation matrix. On text classification, language modeling, and movie recommendation benchmarks, we show that ANT is particularly suitable for large vocabulary sizes.
  arXiv  Detail & Related papers  (2020-03-18T13:07:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.