paper-with-me

홈 › Papers

Interpreting Word Embeddings with Eigenvector Analysis

2018-10-22 · NIPS Workshop IRASL 2018 · Anonymous

Dense word vectors have proven their values in many downstream NLP tasks over the past few years. However, the dimensions of such embeddings are not easily interpretable. Out of the d-dimensions in a word vector, we would not be able to understand what high or low values mean. Previous approaches addressing this issue have mainly focused on either training sparse/non-negative constrained word embeddings, or post-processing standard pre-trained word embeddings. On the other hand, we analyze conventional word embeddings trained with Singular Value Decomposition, and reveal similar interpretability. We use a novel eigenvector analysis method inspired from Random Matrix Theory and show that semantically coherent groups not only form in the row space, but also the column space. This allows us to view individual word vector dimensions as human-interpretable semantic features.

📄 PDF Abstract BibTeX

Code (1)

hltchkust/eigenvector-analysis 공식 구현

Tasks

Word Embeddings

Similar Papers 제목 키워드 기반

Interpreting Emoji with Emoji

2022-07-01 · NAACL (Emoji) 2022 7 · Jens Reelfs, Timon Mohaupt, Sandipan Sikdar, Markus Strohmaier 외

We study the extent to which emoji can be used to add interpretability to embeddings of text and emoji. To do so, we extend the POLAR-framework that transforms word embeddings to interpretable counterparts and apply it t…

Word Embeddings

Tracing variation in discourse connectives in translation and interpreting through neural semantic spaces

2021-11-01 · CODI 2021 11 · Ekaterina Lapshinova-Koltunski, Heike Przybyl, Yuri Bizzoni

In the present paper, we explore lexical contexts of discourse markers in translation and interpreting on the basis of word embeddings. Our special interest is on contextual variation of the same discourse markers in (wr…

TranslationWord Embeddings

Non-Linear Relational Information Probing in Word Embeddings

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Pre-trained word embeddings such as SkipGram and GloVe are known to contain a myriad of useful information about words. In this work, we use multilayer perceptrons (MLP) to probe the relational information contained in t…

RelationWord Embeddings

Axis Tour: Word Tour Determines the Order of Axes in ICA-transformed Embeddings

2024-01-11 · Hiroaki Yamagiwa, Yusuke Takase, Hidetoshi Shimodaira

Word embedding is one of the most important components in natural language processing, but interpreting high-dimensional embeddings remains a challenging problem. To address this problem, Independent Component Analysis (…

Word Embeddings

On the Emergence of Linear Analogies in Word Embeddings

2025-05-24 · Daniel J. Korchinski, Dhruva Karkada, Yasaman Bahri, Matthieu Wyart

Models such as Word2Vec and GloVe construct word embeddings based on the co-occurrence probability $P(i,j)$ of words $i$ and $j$ in text corpora. The resulting vectors $W_i$ not only group semantically similar words but …

AttributeWord Embeddings