Analyzing the Surprising Variability in Word Embedding Stability Across Languages

• URL: http://arxiv.org/abs/2004.14876v2
• Date: Thu, 9 Sep 2021 20:15:09 GMT
• Title: Analyzing the Surprising Variability in Word Embedding Stability Across Languages
• Authors: Laura Burdick, Jonathan K. Kummerfeld, Rada Mihalcea
• Abstract summary: We discuss linguistic properties that are related to stability, drawing out insights about correlations with affixing, language gender systems, and other features. This has implications for embedding use, particularly in research that uses them to study language trends.
• Score: 46.84861591608146
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Word embeddings are powerful representations that form the foundation of many natural language processing architectures, both in English and in other languages. To gain further insight into word embeddings, we explore their stability (e.g., overlap between the nearest neighbors of a word in different embedding spaces) in diverse languages. We discuss linguistic properties that are related to stability, drawing out insights about correlations with affixing, language gender systems, and other features. This has implications for embedding use, particularly in research that uses them to study language trends.

Related papers

• Entropy and type-token ratio in gigaword corpora [0.0]
  We investigate entropy and text-token ratio, two metrics for lexical diversities, in six massive linguistic datasets in English, Spanish, and Turkish. We find a functional relation between entropy and text-token ratio that holds across the corpora under consideration. Our results contribute to the theoretical understanding of text structure and offer practical implications for fields like natural language processing.
  arXiv  Detail & Related papers  (2024-11-15T14:40:59Z)
• Lexical Diversity in Kinship Across Languages and Dialects [6.80465507148218]
  We introduce a method to enrich computational lexicons with content relating to linguistic diversity. The method is verified through two large-scale case studies on kinship terminology.
  arXiv  Detail & Related papers  (2023-08-24T19:49:30Z)
• Transparency Helps Reveal When Language Models Learn Meaning [71.96920839263457]
  Our systematic experiments with synthetic data reveal that, with languages where all expressions have context-independent denotations, both autoregressive and masked language models learn to emulate semantic relations between expressions. Turning to natural language, our experiments with a specific phenomenon -- referential opacity -- add to the growing body of evidence that current language models do not well-represent natural language semantics.
  arXiv  Detail & Related papers  (2022-10-14T02:35:19Z)
• Corpus-Guided Contrast Sets for Morphosyntactic Feature Detection in Low-Resource English Varieties [3.3536302616846734]
  We present a human-in-the-loop approach to generate and filter effective contrast sets via corpus-guided edits. We show that our approach improves feature detection for both Indian English and African American English, demonstrate how it can assist linguistic research, and release our fine-tuned models for use by other researchers.
  arXiv  Detail & Related papers  (2022-09-15T21:19:31Z)
• When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer [15.578267998149743]
  We show that the absence of sub-word overlap significantly affects zero-shot transfer when languages differ in their word order. There is a strong correlation between transfer performance and word embedding alignment between languages. Our results call for focus in multilingual models on explicitly improving word embedding alignment between languages.
  arXiv  Detail & Related papers  (2021-10-27T21:25:39Z)
• Dynamic Contextualized Word Embeddings [20.81930455526026]
  We introduce dynamic contextualized word embeddings that represent words as a function of both linguistic and extralinguistic context. Based on a pretrained language model (PLM), dynamic contextualized word embeddings model time and social space jointly. We highlight potential application scenarios by means of qualitative and quantitative analyses on four English datasets.
  arXiv  Detail & Related papers  (2020-10-23T22:02:40Z)
• Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer [101.58431011820755]
  We study gender bias in multilingual embeddings and how it affects transfer learning for NLP applications. We create a multilingual dataset for bias analysis and propose several ways for quantifying bias in multilingual representations.
  arXiv  Detail & Related papers  (2020-05-02T04:34:37Z)
• Linguistic Typology Features from Text: Inferring the Sparse Features of World Atlas of Language Structures [73.06435180872293]
  We construct a recurrent neural network predictor based on byte embeddings and convolutional layers. We show that some features from various linguistic types can be predicted reliably.
  arXiv  Detail & Related papers  (2020-04-30T21:00:53Z)
• Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations [83.27475281544868]
  We use singular vector canonical correlation analysis to study what kind of information is induced from each source. We observe that our representations embed typology and strengthen correlations with language relationships. We then take advantage of our multi-view language vector space for multilingual machine translation, where we achieve competitive overall translation accuracy.
  arXiv  Detail & Related papers  (2020-04-30T16:25:39Z)
• Evaluating Transformer-Based Multilingual Text Classification [55.53547556060537]
  We argue that NLP tools perform unequally across languages with different syntactic and morphological structures. We calculate word order and morphological similarity indices to aid our empirical study.
  arXiv  Detail & Related papers  (2020-04-29T03:34:53Z)

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.