Contextualized language models for semantic change detection: lessons learned

• URL: http://arxiv.org/abs/2209.00154v1
• Date: Wed, 31 Aug 2022 23:35:24 GMT
• Title: Contextualized language models for semantic change detection: lessons learned
• Authors: Andrey Kutuzov, Erik Velldal, Lilja {\O}vrelid
• Abstract summary: We present a qualitative analysis of the outputs of contextualized embedding-based methods for detecting diachronic semantic change. Our findings show that contextualized methods can often predict high change scores for words which are not undergoing any real diachronic semantic shift. Our conclusion is that pre-trained contextualized language models are prone to confound changes in lexicographic senses and changes in contextual variance.
• Score: 4.436724861363513
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a qualitative analysis of the (potentially erroneous) outputs of contextualized embedding-based methods for detecting diachronic semantic change. First, we introduce an ensemble method outperforming previously described contextualized approaches. This method is used as a basis for an in-depth analysis of the degrees of semantic change predicted for English words across 5 decades. Our findings show that contextualized methods can often predict high change scores for words which are not undergoing any real diachronic semantic shift in the lexicographic sense of the term (or at least the status of these shifts is questionable). Such challenging cases are discussed in detail with examples, and their linguistic categorization is proposed. Our conclusion is that pre-trained contextualized language models are prone to confound changes in lexicographic senses and changes in contextual variance, which naturally stem from their distributional nature, but is different from the types of issues observed in methods based on static embeddings. Additionally, they often merge together syntactic and semantic aspects of lexical entities. We propose a range of possible future solutions to these issues.

Related papers

• Survey in Characterization of Semantic Change [0.1474723404975345]
  Understanding the meaning of words is vital for interpreting texts from different cultures. Semantic changes can potentially impact the quality of the outcomes of computational linguistics algorithms.
  arXiv  Detail & Related papers  (2024-02-29T12:13:50Z)
• Pixel Sentence Representation Learning [67.4775296225521]
  In this work, we conceptualize the learning of sentence-level textual semantics as a visual representation learning process. We employ visually-grounded text perturbation methods like typos and word order shuffling, resonating with human cognitive patterns, and enabling perturbation to be perceived as continuous. Our approach is further bolstered by large-scale unsupervised topical alignment training and natural language inference supervision.
  arXiv  Detail & Related papers  (2024-02-13T02:46:45Z)
• Reliable Detection and Quantification of Selective Forces in Language Change [3.55026004901472]
  We apply a recently-introduced method to corpus data to quantify the strength of selection in specific instances of historical language change. We show that this method is more reliable and interpretable than similar methods that have previously been applied.
  arXiv  Detail & Related papers  (2023-05-25T10:20:15Z)
• Unsupervised Lexical Substitution with Decontextualised Embeddings [48.00929769805882]
  We propose a new unsupervised method for lexical substitution using pre-trained language models. Our method retrieves substitutes based on the similarity of contextualised and decontextualised word embeddings. We conduct experiments in English and Italian, and show that our method substantially outperforms strong baselines.
  arXiv  Detail & Related papers  (2022-09-17T03:51:47Z)
• A Latent-Variable Model for Intrinsic Probing [93.62808331764072]
  We propose a novel latent-variable formulation for constructing intrinsic probes. We find empirical evidence that pre-trained representations develop a cross-lingually entangled notion of morphosyntax.
  arXiv  Detail & Related papers  (2022-01-20T15:01:12Z)
• Grammatical Profiling for Semantic Change Detection [6.3596637237946725]
  We use grammatical profiling as an alternative method for semantic change detection. We demonstrate that it can be used for semantic change detection and even outperforms some distributional semantic methods.
  arXiv  Detail & Related papers  (2021-09-21T18:38:18Z)
• On the Faithfulness Measurements for Model Interpretations [100.2730234575114]
  Post-hoc interpretations aim to uncover how natural language processing (NLP) models make predictions. To tackle these issues, we start with three criteria: the removal-based criterion, the sensitivity of interpretations, and the stability of interpretations. Motivated by the desideratum of these faithfulness notions, we introduce a new class of interpretation methods that adopt techniques from the adversarial domain.
  arXiv  Detail & Related papers  (2021-04-18T09:19:44Z)
• Fake it Till You Make it: Self-Supervised Semantic Shifts for Monolingual Word Embedding Tasks [58.87961226278285]
  We propose a self-supervised approach to model lexical semantic change. We show that our method can be used for the detection of semantic change with any alignment method. We illustrate the utility of our techniques using experimental results on three different datasets.
  arXiv  Detail & Related papers  (2021-01-30T18:59:43Z)
• Lexical semantic change for Ancient Greek and Latin [61.69697586178796]
  Associating a word's correct meaning in its historical context is a central challenge in diachronic research. We build on a recent computational approach to semantic change based on a dynamic Bayesian mixture model. We provide a systematic comparison of dynamic Bayesian mixture models for semantic change with state-of-the-art embedding-based models.
  arXiv  Detail & Related papers  (2021-01-22T12:04:08Z)
• Multi-sense embeddings through a word sense disambiguation process [2.2344764434954256]
  Most Suitable Sense. (MSSA) disambiguates and annotates each word by its specific sense, considering the semantic effects of its context. We test our approach on six different benchmarks for the word similarity task, showing that our approach can produce state-of-the-art results.
  arXiv  Detail & Related papers  (2021-01-21T16:22:34Z)
• Analysing Lexical Semantic Change with Contextualised Word Representations [7.071298726856781]
  We propose a novel method that exploits the BERT neural language model to obtain representations of word usages. We create a new evaluation dataset and show that the model representations and the detected semantic shifts are positively correlated with human judgements.
  arXiv  Detail & Related papers  (2020-04-29T12:18:14Z)

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.