pith. sign in

arxiv: 2402.19088 · v5 · submitted 2024-02-29 · 💻 cs.CL · cs.AI

Survey in Characterizing Semantic Change

Jader Martins Camboim de S\'a , Marcos Da Silveira , C\'edric Pruski This is my paper

Pith reviewed 2026-05-24 03:35 UTC · model grok-4.3

classification 💻 cs.CL cs.AI
keywords semantic changecharacterizationcomputational linguisticsword meaninglanguage evolutionNLP applicationssurvey
0
0 comments X

The pith

Semantic changes in words are formally grouped into three classes: dimension, orientation, and relation.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This survey reviews existing methods for describing how the meanings of existing words evolve as languages change. It defines three classes of characterization: dimension captures broadening or narrowing of meaning, orientation tracks shifts toward more pejorative or ameliorative senses, and relation covers moves into metaphorical or metonymic uses. These distinctions matter for computational tasks such as translation and information retrieval because unaccounted semantic shifts can degrade algorithm performance. The work summarizes selected publications in a table and outlines current needs and research trends in the area.

Core claim

The paper formally defines three classes of characterizations for semantic change: change in dimension when a word's meaning becomes more general or narrow, change in orientation when a word is used in a more pejorative or positive sense, and change in relation when a word trends toward metaphoric or metonymic contexts.

What carries the argument

The three-class taxonomy (dimension, orientation, relation) that organizes approaches to semantic change characterization.

If this is right

  • Detection methods can be evaluated and compared according to which class of change they target.
  • NLP systems can be designed to handle specific classes of semantic shift to maintain accuracy over time.
  • Research efforts can shift from pure detection toward explicit characterization of each class.
  • Trends identified in the survey point to needs for more work on orientation and relation changes.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The taxonomy could be tested on corpora from non-English languages to check cross-linguistic fit.
  • Automated tools might be built to label changes by class once detection has occurred.
  • The classes could inform models of cultural transmission through language data.

Load-bearing premise

The three classes comprehensively capture the main ways semantic change can be characterized and the selected publications represent the field without major omissions.

What would settle it

A well-documented semantic change that cannot be placed in any of the three classes, such as a shift driven solely by sound change or pragmatic inference outside the defined categories.

Figures

Figures reproduced from arXiv: 2402.19088 by C\'edric Pruski, Jader Martins Camboim de S\'a, Marcos Da Silveira.

Figure 1
Figure 1. Figure 1: Taxonomy for the poles of Lexical Semantic Change, based on the [PITH_FULL_IMAGE:figures/full_fig_p009_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Change in meaning and orientation for the word awful. In the left side, [PITH_FULL_IMAGE:figures/full_fig_p010_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Graph of selected works (green) and related articles (blue). [PITH_FULL_IMAGE:figures/full_fig_p011_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Figure adapted from Inoue et al. (2022). The stacked bar plots rep [PITH_FULL_IMAGE:figures/full_fig_p016_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Adaptation from Ehm¨uller et al. (2020). Ego-network, built from [PITH_FULL_IMAGE:figures/full_fig_p017_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Adapted from Hamilton et al. (2016a). The SentiProp algorithm [PITH_FULL_IMAGE:figures/full_fig_p018_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Plot obtained from Moss (2020). The author represent words as [PITH_FULL_IMAGE:figures/full_fig_p019_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: 19 [PITH_FULL_IMAGE:figures/full_fig_p019_8.png] view at source ↗
Figure 8
Figure 8. Figure 8: Adaptation from Fonteyn and Manjavacas (2021). The line plot shows [PITH_FULL_IMAGE:figures/full_fig_p020_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Illutration adapted from Xie et al. (2019). The figure shows how [PITH_FULL_IMAGE:figures/full_fig_p020_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Definition of semantic change adapted from Koch (2016, p. 23,25). [PITH_FULL_IMAGE:figures/full_fig_p025_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Illustrative example of the word ‘heart’ changing over time. [PITH_FULL_IMAGE:figures/full_fig_p029_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Change in meaning distribution for the word ‘heart’ in SEMCOR [PITH_FULL_IMAGE:figures/full_fig_p032_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Change in meaning distribution for the word ‘plane’ in SEMCOR [PITH_FULL_IMAGE:figures/full_fig_p033_13.png] view at source ↗
read the original abstract

Live languages continuously evolve to integrate the cultural change of human societies. This evolution manifests through neologisms (new words) or \textbf{semantic changes} of words (new meaning to existing words). Understanding the meaning of words is vital for interpreting texts coming from different cultures (regionalism or slang), domains (e.g., technical terms), or periods. In computer science, these words are relevant to computational linguistics algorithms such as translation, information retrieval, question answering, etc. Semantic changes can potentially impact the quality of the outcomes of these algorithms. Therefore, it is important to understand and characterize these changes formally. The study of this impact is a recent problem that has attracted the attention of the computational linguistics community. Several approaches propose methods to detect semantic changes with good precision, but more effort is needed to characterize how the meaning of words changes and to reason about how to reduce the impact of semantic change. This survey provides an understandable overview of existing approaches to the \textit{characterization of semantic changes} and also formally defines three classes of characterizations: if the meaning of a word becomes more general or narrow (change in dimension) if the word is used in a more pejorative or positive/ameliorated sense (change in orientation), and if there is a trend to use the word in a, for instance, metaphoric or metonymic context (change in relation). We summarized the main aspects of the selected publications in a table and discussed the needs and trends in the research activities on semantic change characterization.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper is a survey of approaches to characterizing semantic change in computational linguistics. It reviews selected publications on detecting and describing how word meanings evolve, formally defines a three-class taxonomy (change in dimension: broadening/narrowing; change in orientation: pejoration/amelioration; change in relation: metaphoric/metonymic), summarizes the reviewed works in a table, and discusses research needs and trends.

Significance. If the taxonomy is demonstrated to be exhaustive and sufficiently disjoint, the survey could offer a useful organizing framework for a growing subfield, aiding consistency in how semantic change is described and potentially supporting more robust NLP applications. The summary table is a concrete strength for reference.

major comments (3)
  1. [§3] §3 (formal definition of the three classes): the claim that these classes comprehensively capture the main characterizations of semantic change is not supported by any argument or mapping showing that other attested types (e.g., register shift, change in sense frequency, or domain-specific specialization) are reducible to one of the three or fall outside the scope.
  2. [§3 and Table 1] §3 and Table 1: no analysis is provided of potential overlaps, such as a single change simultaneously exhibiting both a metaphoric relation shift and an orientation (pejoration) shift; without this, the partition's utility as a taxonomy remains unverified.
  3. [§4] §4 (discussion of trends): the needs and trends identified rest on the three-class framing, so the absence of justification for exhaustiveness directly weakens the reliability of the trend analysis and recommendations for future work.
minor comments (2)
  1. [Abstract] Abstract: the sentence introducing the three classes is missing conjunctions and punctuation, reducing readability.
  2. [Table 1] Table 1: column headers and class assignments could be clarified with explicit criteria used for mapping each paper.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive feedback on the taxonomy. We address each major comment below and will revise the manuscript to strengthen the justification and analysis as suggested.

read point-by-point responses

  1. Referee: [§3] §3 (formal definition of the three classes): the claim that these classes comprehensively capture the main characterizations of semantic change is not supported by any argument or mapping showing that other attested types (e.g., register shift, change in sense frequency, or domain-specific specialization) are reducible to one of the three or fall outside the scope.

    Authors: We acknowledge that §3 asserts the three classes capture the main characterizations without providing an explicit supporting argument or mapping from the reviewed literature. In the revision we will expand §3 to include a mapping of the selected publications to the classes and a brief discussion of how other attested types (such as register shift) may be treated as falling outside the semantic scope or reducible to change in relation. revision: yes

  2. Referee: [§3 and Table 1] §3 and Table 1: no analysis is provided of potential overlaps, such as a single change simultaneously exhibiting both a metaphoric relation shift and an orientation (pejoration) shift; without this, the partition's utility as a taxonomy remains unverified.

    Authors: We agree that potential overlaps between classes are not analyzed. The revised manuscript will add a short subsection in §3 that examines possible intersections (with concrete examples from the literature) and discusses whether the taxonomy should permit multi-label classification. Table 1 will be updated to flag any reviewed works that exhibit multiple classes. revision: yes

  3. Referee: [§4] §4 (discussion of trends): the needs and trends identified rest on the three-class framing, so the absence of justification for exhaustiveness directly weakens the reliability of the trend analysis and recommendations for future work.

    Authors: The trends in §4 are drawn from the surveyed works that employ characterizations aligned with the three classes. We will revise §4 to cross-reference the expanded justification added to §3 and to qualify the recommendations as applying within the scope of the proposed taxonomy. revision: yes

Circularity Check

0 steps flagged

No circularity: survey taxonomy draws from external literature without self-referential derivations

full rationale

This paper is a literature survey that reviews selected publications on semantic change and proposes a three-class taxonomy (dimension, orientation, relation) as a summarizing formalization. No equations, fitted parameters, predictions, or derivations exist that could reduce to the paper's own inputs by construction. The taxonomy is presented as an overview of external work rather than a result derived from self-citation chains or ansatzes internal to the paper. All content references prior publications without load-bearing self-referential steps.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper is a literature survey and introduces no free parameters, axioms, or invented entities; its contribution is organizational.

pith-pipeline@v0.9.0 · 5812 in / 1080 out tokens · 41211 ms · 2026-05-24T03:35:52.219277+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

117 extracted references · 117 canonical work pages · 7 internal anchors

  1. [1]

    Allan, K. 2013. The Oxford handbook of the history of linguistics . OUP Oxford

    work page 2013

  2. [2]

    and Robinson, J

    Allan, K. and Robinson, J. A. 2012. Current methods in historical semantics . De Gruyter Mouton Berlin

    work page 2012

  3. [3]

    and Mimno, D

    Antoniak, M. and Mimno, D. M. 2021. Bad seeds: Evaluating lexical methods for bias measurement. In Annual Meeting of the Association for Computational Linguistics

    work page 2021

  4. [4]

    Apidianaki, M. 2022. From word types to tokens and back: A survey of approaches to word meaning representation and interpretation. Computational Linguistics , 49:465--523

    work page 2022

  5. [5]

    Ardley, G. 1968. God and the soul. Philosophical Studies , 18:325--326

    work page 1968

  6. [6]

    , Kurtz, R

    Barnes, J. , Kurtz, R. , Oepen, S. , Ovrelid, L. , and Velldal, E. 2021. Structured sentiment analysis as dependency graph parsing. ArXiv , abs/2105.14504

    work page arXiv 2021

  7. [7]

    Biemann, C. 2006. C hinese whispers - an efficient graph clustering algorithm and its application to natural language processing problems. In Proceedings of T ext G raphs: the First Workshop on Graph Based Methods for Natural Language Processing , pp. 73--80, New York City. Association for Computational Linguistics

    work page 2006

  8. [8]

    and others 2003

    Blank, A. and others 2003. Polysemy in the lexicon and in discourse. Polysemy: Flexible patterns of meaning in mind and language

    work page 2003

  9. [9]

    Bochkarev, V. V. , Khristoforov, S. , Shevlyakova, A. V. , and Solovyev, V. D. 2022. Neural network algorithm for detection of new word meanings denoting named entities. IEEE Access , PP:1--1

    work page 2022

  10. [10]

    Bowern, C. 2019. Semantic change and semantic stability: Variation is key. In LChange@ACL

    work page 2019

  11. [11]

    Brezina, V. 2018. Statistics in Corpus Linguistics: A Practical Guide . Cambridge University Press

    work page 2018

  12. [12]

    Broad, C. D. 1938. Examination of McTaggart's Philosophy , volume Vol. II. Cambridge University Press

    work page 1938

  13. [13]

    , Hellrich, J

    Buechel, S. , Hellrich, J. , and Hahn, U. 2016. Feelings from the past—adapting affective lexicons for historical emotion analysis. In LT4DH@COLING

    work page 2016

  14. [14]

    Burke, K. 1969. A grammar of motives , volume 177. Univ of California Press

    work page 1969

  15. [15]

    and Pilehvar, M

    Camacho-Collados, J. and Pilehvar, M. T. 2018. From word to sense embeddings: A survey on vector representations of meaning. J. Artif. Intell. Res. , 63:743--788

    work page 2018

  16. [16]

    , Daum \'e , H

    Carpuat, M. , Daum \'e , H. , Henry, K. , Irvine, A. , Jagarlamudi, J. , and Rudinger, R. 2013. Sensespotting: Never let your parallel data tie you to an old domain. In Annual Meeting of the Association for Computational Linguistics

    work page 2013

  17. [17]

    , Greaves, C

    Cheng, W. , Greaves, C. , and Warren, M. 2006. From n-gram to skipgram to concgram. International journal of corpus linguistics , 11(4):411--433

    work page 2006

  18. [18]

    , Lee, S

    Choi, M. , Lee, S. , Choi, E. , Park, H. , Lee, J. , Lee, D. , and Lee, J. 2021. M el BERT : Metaphor detection via contextualized late interaction using metaphorical identification theories. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , pp. 1763--1773, O...

    work page 2021

  19. [19]

    , Lau, J

    Cook, P. , Lau, J. H. , Rundell, M. , McCarthy, D. , and Baldwin, T. 2013. A lexicographic appraisal of an automatic approach for detecting new word-senses. In Proceedings of eLex

    work page 2013

  20. [20]

    and Stevenson, S

    Cook, P. and Stevenson, S. 2010. Automatically identifying changes in the semantic orientation of words. In International Conference on Language Resources and Evaluation

    work page 2010

  21. [21]

    , Qian, K

    Danilevsky, M. , Qian, K. , Aharonov, R. , Katsis, Y. , Kawas, B. , and Sen, P. 2020. A survey of the state of explainable ai for natural language processing. In AACL

    work page 2020

  22. [22]

    BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

    Devlin, J. , Chang, M.-W. , Lee, K. , and Toutanova, K. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. ArXiv , abs/1810.04805

    work page internal anchor Pith review Pith/arXiv arXiv 2019

  23. [23]

    , Weinshall, D

    Dubossarsky, H. , Weinshall, D. , and Grossman, E. 2017. Outta control: Laws of semantic change and inherent biases in word representation models. In Conference on Empirical Methods in Natural Language Processing

    work page 2017

  24. [24]

    , Kohlmeyer, L

    Ehm \"u ller, J. , Kohlmeyer, L. , McKee, H. , Paeschke, D. , Repke, T. , Krestel, R. , and Naumann, F. 2020. Sense tree: Discovery of new word senses with graph-based scoring. In Lernen, Wissen, Daten, Analysen

    work page 2020

  25. [25]

    and Jayapal, A

    Emms, M. and Jayapal, A. K. 2016. Dynamic generative model for diachronic sense emergence detection. In International Conference on Computational Linguistics

    work page 2016

  26. [26]

    Ethayarajh, K. 2019. How contextual are contextualized word representations? comparing the geometry of bert, elmo, and gpt-2 embeddings. In Conference on Empirical Methods in Natural Language Processing

    work page 2019

  27. [27]

    and Manjavacas, E

    Fonteyn, L. and Manjavacas, E. 2021. Adjusting scope: A computational approach to case-driven research on semantic change. In Workshop on Computational Humanities Research

    work page 2021

  28. [28]

    , Žliobaitė, I

    Gama, J. , Žliobaitė, I. , Bifet, A. , Pechenizkiy, M. , and Bouchachia, A. 2014. A survey on concept drift adaptation. ACM Computing Surveys (CSUR) , 46:1 -- 37

    work page 2014

  29. [29]

    SimCSE: Simple Contrastive Learning of Sentence Embeddings

    Gao, T. , Yao, X. , and Chen, D. 2021. Simcse: Simple contrastive learning of sentence embeddings. ArXiv , abs/2104.08821

    work page internal anchor Pith review Pith/arXiv arXiv 2021

  30. [30]

    , Luden, I

    Giulianelli, M. , Luden, I. , Fern \'a ndez, R. , and Kutuzov, A. 2023. Interpretable word sense representations via definition generation: The case of semantic change analysis. In Annual Meeting of the Association for Computational Linguistics

    work page 2023

  31. [31]

    and Drozd, A

    Gladkova, A. and Drozd, A. 2016. Intrinsic evaluations of word embeddings: What can we do better? In Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, RepEval@ACL 2016, Berlin, Germany, August 2016 , pp. 36--42. Association for Computational Linguistics

    work page 2016

  32. [32]

    , Rinaldi, L

    G \"u nther, F. , Rinaldi, L. , and Marelli, M. 2019. Vector-space models of semantic representation from a cognitive perspective: A discussion of common misconceptions. Perspectives on Psychological Science , 14:1006 -- 1033

    work page 2019

  33. [33]

    Guo, X. , Yu, W. , and Wang, X. 2021. An overview on fine-grained text sentiment analysis: Survey and challenges. Journal of Physics: Conference Series , 1757

    work page 2021

  34. [34]

    Hamilton, W. L. , Leskovec, J. , and Jurafsky, D. 2016. Diachronic word embeddings reveal statistical laws of semantic change. ArXiv , abs/1605.09096

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  35. [35]

    o m, H. , R \

    Hammarstr \"o m, H. , R \"o nchen, P. , Elgh, E. , and Wiklund, T. 2019. On computational historical linguistics in the 21st century. Theoretical Linguistics , 45:233 -- 245

    work page 2019

  36. [36]

    DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing

    He, P. , Gao, J. , and Chen, W. 2021. Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. ArXiv , abs/2111.09543

    work page internal anchor Pith review Pith/arXiv arXiv 2021

  37. [37]

    , Gabbard, R

    Heintz, I. , Gabbard, R. , Srivastava, M. , Barner, D. , Black, D. , Friedman, M. , and Weischedel, R. M. 2013. Automatic extraction of linguistic metaphors with lda topic modeling. In Proceedings of the First Workshop on Metaphor in NLP , pp. 58--66

    work page 2013

  38. [38]

    and Hahn, U

    Hellrich, J. and Hahn, U. 2016. Bad company - neighborhoods in neural embedding spaces considered harmful. In Calzolari, N. , Matsumoto, Y. , and Prasad, R. , editors, COLING 2016, 26th International Conference on Computational Linguistics, Proceedings of the Conference: Technical Papers, December 11-16, 2016, Osaka, Japan , pp. 2785--2796. ACL

    work page 2016

  39. [39]

    , Tahmasebi, N

    Hengchen, S. , Tahmasebi, N. , Schlechtweg, D. , and Dubossarsky, H. 2021. Challenges for computational lexical semantic change. ArXiv , abs/2101.07668

    work page arXiv 2021

  40. [40]

    Hock, H. H. and Joseph, B. D. 2019. Chapter 7: Semantic change . De Gruyter Mouton, Berlin, Boston

    work page 2019

  41. [41]

    , Shrivastava, S

    Hovy, D. , Shrivastava, S. , Jauhar, S. K. , Sachan, M. , Goyal, K. , Li, H. , Sanders, W. E. , and Hovy, E. H. 2013. Identifying metaphorical word use with tree kernels. In Proceedings of the First Workshop on Metaphor in NLP

    work page 2013

  42. [42]

    Hu, R. , Li, S. , and Liang, S. 2019. Diachronic sense modeling with deep contextualized word embeddings: An ecological view. In Annual Meeting of the Association for Computational Linguistics

    work page 2019

  43. [43]

    , Tsubouchi, K

    Ito, T. , Tsubouchi, K. , Sakaji, H. , Yamashita, T. , and Izumi, K. 2020. Word-level contextual sentiment analysis with interpretability. In AAAI Conference on Artificial Intelligence

    work page 2020

  44. [44]

    and Duh, K

    Jatowt, A. and Duh, K. 2014. A framework for analyzing semantic change of words across time. IEEE/ACM Joint Conference on Digital Libraries , pp. 229--238

    work page 2014

  45. [45]

    and Koptjevskaja-Tamm, M

    Juvonen, P. and Koptjevskaja-Tamm, M. 2016. The lexical typology of semantic shifts , volume 58. Walter de Gruyter GmbH & Co KG

    work page 2016

  46. [46]

    Koch, P. 2016. Meaning change and semantic shifts. The lexical typology of semantic shifts , 58:21--66

    work page 2016

  47. [47]

    , vrelid, L

    Kutuzov, A. , vrelid, L. , Szymanski, T. , and Velldal, E. 2018. Diachronic word embeddings and semantic shifts: a survey. In International Conference on Computational Linguistics

    work page 2018

  48. [48]

    , Velldal, E

    Kutuzov, A. , Velldal, E. , and vrelid, L. 2022. Contextualized embeddings for semantic change detection: Lessons learned. ArXiv , abs/2209.00154

    work page arXiv 2022

  49. [49]

    and Johnson, M

    Lakoff, G. and Johnson, M. 2008. Metaphors we live by . University of Chicago press

    work page 2008

  50. [50]

    Lau, J. H. , Cook, P. , McCarthy, D. , Gella, S. , and Baldwin, T. 2014. Learning word sense distributions, detecting unattested senses and identifying novel senses using topic models. In Annual Meeting of the Association for Computational Linguistics

    work page 2014

  51. [51]

    Lau, J. H. , Cook, P. , McCarthy, D. , Newman, D. , and Baldwin, T. 2012. Word sense induction for novel sense detection. In Conference of the European Chapter of the Association for Computational Linguistics

    work page 2012

  52. [52]

    , May, A

    Leszczynski, M. , May, A. , Zhang, J. , Wu, S. , Aberger, C. R. , and R \' e , C. 2020. Understanding the downstream instability of word embeddings. CoRR , abs/2003.04983

    work page arXiv 2020

  53. [53]

    and Tagg, C

    Littlemore, J. and Tagg, C. 2018. Metonymy and text messaging: A framework for understanding creative uses of metonymy. Applied Linguistics , 39(4):481--507

    work page 2018

  54. [54]

    , Tam, D

    Liu, H. , Tam, D. , Muqeeth, M. , Mohta, J. , Huang, T. , Bansal, M. , and Raffel, C. 2022. Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. ArXiv , abs/2205.05638

    work page arXiv 2022

  55. [55]

    , Liu, Z

    Liu, Y. , Liu, Z. , Chua, T.-S. , and Sun, M. 2015. Topical word embeddings. In AAAI Conference on Artificial Intelligence

    work page 2015

  56. [56]

    , Cheng, X

    Lu, Y. , Cheng, X. , Liang, Z. , and Rao, Y. 2022. Graph-based dynamic word embeddings. In International Joint Conference on Artificial Intelligence

    work page 2022

  57. [57]

    , Maity, S

    Mathew, B. , Maity, S. K. , Sarkar, P. , Mukherjee, A. , and Goyal, P. 2017. Adapting predominant and novel sense discovery algorithms for identifying corpus-specific sense differences. In Proceedings of T ext G raphs-11: the Workshop on Graph-based Methods for Natural Language Processing , pp. 11--20, Vancouver, Canada. Association for Computational Linguistics

    work page 2017

  58. [58]

    Mathews, K. A. and Strube, M. 2021. Impact of target word and context on end-to-end metonymy detection. ArXiv , abs/2112.03256

    work page arXiv 2021

  59. [59]

    Maudslay, R. H. and Teufel, S. 2022. Metaphorical polysemy detection: Conventional metaphor meets word sense disambiguation. ArXiv , abs/2212.08395

    work page arXiv 2022

  60. [60]

    , Zhang, J

    May, A. , Zhang, J. , Dao, T. , and R \' e , C. 2019. On the downstream performance of compressed word embeddings. CoRR , abs/1909.01264

    work page arXiv 2019

  61. [61]

    , Koeling, R

    McCarthy, D. , Koeling, R. , Weeds, J. , and Carroll, J. 2004. Finding predominant word senses in untagged text. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics ( ACL -04) , pp. 279--286, Barcelona, Spain

    work page 2004

  62. [62]

    McWhorter, J. 2011. The power of Babel: A natural history of language . Random House

    work page 2011

  63. [63]

    'sick,' entry 6

    Merriam-Webster 2023. 'sick,' entry 6. https://www.merriam-webster.com/dictionary/sick. Accessed: 2023-09-15

    work page 2023

  64. [64]

    , Paperno, D

    Mickus, T. , Paperno, D. , Constant, M. , and van Deemter, K. 2020. What do you mean, BERT ? In Proceedings of the Society for Computation in Linguistics 2020 , pp. 279--290, New York, New York. Association for Computational Linguistics

    work page 2020

  65. [65]

    , Chen, K

    Mikolov, T. , Chen, K. , Corrado, G. S. , and Dean, J. 2013. Efficient estimation of word representations in vector space. In International Conference on Learning Representations

    work page 2013

  66. [66]

    , Lyu, X

    Min, S. , Lyu, X. , Holtzman, A. , Artetxe, M. , Lewis, M. , Hajishirzi, H. , and Zettlemoyer, L. 2022. Rethinking the role of demonstrations: What makes in-context learning work? In Conference on Empirical Methods in Natural Language Processing

    work page 2022

  67. [67]

    and Lapata, M

    Mitchell, J. and Lapata, M. 2010. Composition in distributional models of semantics. Cognitive science , 34 8:1388--429

    work page 2010

  68. [68]

    , Mitra, R

    Mitra, S. , Mitra, R. , Maity, S. K. , Riedl, M. , Biemann, C. , Goyal, P. , and Mukherjee, A. 2015. An automatic approach to identify word sense changes in text media across timescales. Natural Language Engineering , 21:773 -- 798

    work page 2015

  69. [69]

    Mohammed, E. T. 2009. Polysemy as a lexical problem in translation. Online Submission , 55:1--19

    work page 2009

  70. [70]

    and Periti, F

    Montanelli, S. and Periti, F. 2023. A survey on contextualised semantic shift detection. ArXiv , abs/2304.01666

    work page arXiv 2023

  71. [71]

    Moss, A. 2020. Detecting lexical semantic change using probabilistic gaussian word embeddings

    work page 2020

  72. [72]

    , Judea, A

    Nastase, V. , Judea, A. , Markert, K. , and Strube, M. 2012. Local and global context for supervised and unsupervised metonymy resolution. In Conference on Empirical Methods in Natural Language Processing

    work page 2012

  73. [73]

    Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space

    Neelakantan, A. , Shankar, J. , Passos, A. , and McCallum, A. 2014. Efficient non-parametric estimation of multiple embeddings per word in vector space. ArXiv , abs/1504.06654

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  74. [74]

    Rapid Adaptation of Neural Machine Translation to New Languages

    Neubig, G. and Hu, J. 2018. Rapid adaptation of neural machine translation to new languages. ArXiv , abs/1808.04189

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  75. [75]

    and Traugott, E

    Nevalainen, T. and Traugott, E. C. 2016. The Oxford handbook of the history of English . Oxford University Press

    work page 2016

  76. [76]

    , de Marneffe, M.-C

    Nivre, J. , de Marneffe, M.-C. , Ginter, F. , Hajivc, J. , Manning, C. D. , Pyysalo, S. , Schuster, S. , Tyers, F. M. , and Zeman, D. 2020. Universal dependencies v2: An evergrowing multilingual treebank collection. In International Conference on Language Resources and Evaluation

    work page 2020

  77. [77]

    and Lenci, A

    Pedinotti, P. and Lenci, A. 2020. Don ' t invite BERT to drink a bottle: Modeling the interpretation of metonymies using BERT and distributional representations. In Proceedings of the 28th International Conference on Computational Linguistics , pp. 6831--6837, Barcelona, Spain (Online). International Committee on Computational Linguistics

    work page 2020

  78. [78]

    Peters, M. E. , Neumann, M. , Iyyer, M. , Gardner, M. , Clark, C. , Lee, K. , and Zettlemoyer, L. 2018. Deep contextualized word representations. In North American Chapter of the Association for Computational Linguistics

    work page 2018

  79. [79]

    Pinker, S. 2003. The language instinct: How the mind creates language . Penguin UK

    work page 2003

  80. [80]

    and Bloom, P

    Pinker, S. and Bloom, P. J. 1990. Natural language and natural selection. Behavioral and Brain Sciences , 13:707 -- 727

    work page 1990

Showing first 80 references.