Skip to main content

Advertisement

SpringerLink
Log in

Transparency in AI

  • OPEN FORUM
  • Published:
AI & SOCIETY Aims and scope Submit manuscript

Abstract

In contemporary artificial intelligence, the challenge is making intricate connectionist systems—comprising millions of parameters—more comprehensible, defensible, and rationally grounded. Two prevailing methodologies address this complexity. The inaugural approach amalgamates symbolic methodologies with connectionist paradigms, culminating in a hybrid system. This strategy systematizes extensive parameters within a limited framework of formal, symbolic rules. Conversely, the latter strategy remains staunchly connectionist, eschewing hybridity. Instead of internal transparency, it fabricates an external, transparent proxy system. This ancillary system’s mandate is elucidating the principal system’s decisions, essentially approximating its outcomes. Leveraging natural language processing as our analytical lens, this paper elucidates both methodologies: the hybrid method is underscored by the compositional vector semantics, whereas the purely connectionist method evolves as a derivative of neural semantic parsers. This discourse extols the merits of the purely connectionist approach for its inherent flexibility and for a pivotal delineation: segregating the explanatory apparatus from the operational core, thereby rendering artificial intelligence systems reminiscent of human cognition.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Data Availability

Not applicable.

References

  • Arora S, Li Y, Liang Y, Ma T, Risteski A (2018) Linear algebraic structure of word senses, with applications to polysemy. Trans Assoc Comput Linguist 6:483–495

    Article  Google Scholar 

  • Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473

  • Baker GP, Hacker PM (1984) On misunderstanding Wittgenstein: Kripke's private language argument. Synthese 58:407–450. http://www.jstor.org/stable/20115975. Accessed 20 Jan 2023

  • Baroni M, Zamparelli R (2010) Nouns are vectors, adjectives are matrices: representing adjective-noun constructions in semantic space. In: Proceedings of the 2010 Conference on empirical methods in natural language processing, (s. 1183–1193)

  • Baroni M, Bernardi R, Zamparelli R et al (2014) Frege in space: a program for compositional distributional semantics. Linguist Issues Lang Technol 9:5–110

    Article  Google Scholar 

  • Breiman L (2001) Statistical modeling: the two cultures (with comments and a rejoinder by the author). Stat Sci 16:199–231

    Article  MATH  Google Scholar 

  • Carabantes M (2020) Black-box artificial intelligence: an epistemological and critical analysis. AI & Soc 35:309–317

    Article  Google Scholar 

  • Childers T, Hvorecký J, Majer O (2023) Empiricisim in the foundations of cognition. AI & Soc 38:67–87

    Article  Google Scholar 

  • Chomsky N (1986) Knowledge of language: ıts nature, origin, and use. Greenwood Publishing Group

    Google Scholar 

  • Chomsky N (2011) Language and other cognitive systems. What is special about language? Lang Learn Dev 7:263–278. https://doi.org/10.1080/15475441.2011.584041

    Article  Google Scholar 

  • Clark HH (1983) Making sense of nonce sense. In: Flores D’Arcais GB, Jarvella RJ (eds) The process of language understanding. Wiley, Chicester, pp 297–331

    Google Scholar 

  • Coecke B, Sadrzadeh M, Clark S (2010) Mathematical foundations for a compositional distributional model of meaning. arXiv preprint arXiv:1003.4394

  • Cohen J (1985) A problem about ambiguity in truth-conditional semantics. Analysis 45:129–135

    Article  MathSciNet  MATH  Google Scholar 

  • Dennett D (1987) True Belieers: the intentional strategy and why it works. In: Dennett D (ed) The intentional stance. The MIT Press, Cambridge, pp 13–35

    Google Scholar 

  • Devlin J, Chang M-W, Lee K, Toutanova K (2018) BERT: pre-training of deep bidirectional transformers for language understanding. arXiv. https://arxiv.org/abs/1810.04805adresinden alındı

  • Evang K (2019) Transition-based DRS parsing using stack-LSTMs. In: Proceedings of the IWCS shared task on semantic parsing

  • Fodor JA (1998) Concepts: where cognitive science went wrong. Oxford University Press, New York

    Book  Google Scholar 

  • Fu Q, Zhang Y, Liu J, Zhang M (2020) DRTS parsing with structure-aware encoding and decoding. arXiv preprint arXiv:2005.06901

  • Günther M, Kasirzadeh A (2022) Algorithmic and human decision making: for a double standard of transparency. AI & Soc 37:375–381

    Article  Google Scholar 

  • He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for ımage recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (s. 770–778). https://doi.org/10.1109/CVPR.2016.90

  • Heim I, Kratzer A (1998) Semantics in generative grammar. Blackwell

    Google Scholar 

  • Henin C, Le Métayer D (2022) Beyond explainability: justifiability and contextability of algorithmic decision systems. AI & Soc 37:1397–1410

    Article  Google Scholar 

  • Iacobacci I, Pilehvar MT, Navigli R (2015) SensEmbed: learning sense embeddings for word and relational similarity. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on natural language processing (Volume 1: Long Papers) (s. 95–105). Beijing: Association for Computational Linguistics. https://doi.org/10.3115/v1/P15-1010

  • Johnson M, Schuster M, Le QV, Krikun M, Wu Y, Chen Z, Dean J (2017) Google’s multilingual neural machine translation system: enabling zero-shot translation. Trans Assoc Comput Linguist 5:339–351. https://doi.org/10.1162/tacl_a_00065

    Article  Google Scholar 

  • Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM 60:84–90. https://doi.org/10.1145/3065386

    Article  Google Scholar 

  • Levkovskyi O, Li W (2021) Generating predicate logic expressions from natural language. In: SoutheastCon 2021, (s. 1–8)

  • Lewis M (2019) Compositionality for recursive neural networks. arXiv preprint arXiv:1901.10723

  • Liu J, Cohen SB, Lapata M (2018) Discourse representation structure parsing. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (s. 429–439). Melbourne: Association for Computational Linguistics. https://doi.org/10.18653/v1/P18-1040

  • Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Stoyanov V (2019) Roberta: a robustly optimized bert pretraining approach. arXiv

  • McCoy RT, Linzen T, Dunbar E, Smolensky P (2020) Tensor product decomposition networks: uncovering representations of structure learned by neural networks. Proc Soc Comput Linguist 3:474–475

    Google Scholar 

  • Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. arXiv

  • Montague R (1974a) English as a formal language. In: Thomason RH (ed) Formal philosophy: selected papers of Richard Montague. Yale University Press, New Heaven, pp 188–221

    Google Scholar 

  • Montague R (1974b) Universal grammar. In: Thomason RH (ed) Formal philosophy: selected papers of Richard Montague. Yale University Press, New Heaven, pp 222–246

    Google Scholar 

  • Newell A, Simon HA (1976) Computer science as empirical inquiry: symbols and search. Commun ACM 19:113–126

    Article  MathSciNet  Google Scholar 

  • Nietzsche FW (2009) On truth and lie in an extra-moral sense. In: Geuss R, Nehamas, A (eds) Nietzsche: writings from the early notebooks. Cambridge University Press, Cambridge, pp 253–263

  • Van Noord R, Bos J (2017) Neural semantic parsing by character-based translation: experiments with abstract meaning representations. arXiv preprint arXiv:1705.09980

  • Norvig P (2012) Colorless green ideas learn furiously: Chomsky and the two cultures of statistical learning. Significance 9:30–33

    Article  Google Scholar 

  • Park YJ (2023) How we can create the global agreement on generative AI bias: lessons from climate justice. AI & Soc. https://doi.org/10.1007/s00146-023-01679-0

  • Partee BH, Meulen AT, Wall RE (1990) Mathematical methods in linguistics. Kluwer Academic Publishers, Dordrecht

    MATH  Google Scholar 

  • Partee B (1984) Compositionality. In: Veltman F (eds) Varieties of formal semantics. Foris Publications, Dordrecht, pp 281–311

  • Pennington J, Socher R, Manning C (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on empirical methods in natural language processing (EMNLP), (s. 1532–1543)

  • Peters ME, Ammar W, Bhagavatula C, Power R (2017) Semi-supervised sequence tagging with bidirectional language models. arXiv preprint arXiv:1705.00108

  • Peters ME, Neumann M, Iyyer M, Gardner M, Clark C, Lee K, Zettlemoyer L (2018) Deep contextualized word representations. arXiv preprint arXiv:1802.05365

  • Pustejovsky J (1996) The generative lexicon. MIT Press

    Google Scholar 

  • Quine WV (1969) Epistemology naturalized. In: Quine, WVO (ed) Ontological relativity and other essays. Columbia University Press, New York, pp 69–90

  • Recanati F (2004) Literal meaning. Cambridge University Press

    Google Scholar 

  • Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536. https://doi.org/10.1038/323533a0

    Article  MATH  Google Scholar 

  • Sadrzadeh M, Muskens R (2019) Static and dynamic vector semantics for lambda calculus models of natural language. J Lang Model 6:319–351. https://doi.org/10.15398/jlm.v6i2.228

    Article  Google Scholar 

  • Singh H, Aggrawal M, Krishnamurthy B (2020) Exploring neural models for parsing natural language into first-order logic. arXiv preprint arXiv:2002.06544

  • Skinner BF (1974) About behaviorism. Vintage, New York

    Google Scholar 

  • Smolensky P (1990) Tensor product variable binding and the representation of symbolic structures in connectionist systems. Artif Intell 46:159–216

    Article  MathSciNet  MATH  Google Scholar 

  • Smolensky P (1995a) Connectionism, constituency and the language of thought. In: MacDonald C, MacDonald G (eds) Connectionism: debates on psychological explanation. Basil Blackwell, Oxford

    Google Scholar 

  • Smolensky P (1995b) On the proper treatment of connectionism. In: MacDonald C, MacDonald G (eds) Connectionism: debates on psychological explanation. Basil Blackwell, Oxford

    Google Scholar 

  • Socher R, Karpathy A, Le QV, Manning CD, Ng AY (2014) Grounded compositional semantics for finding and describing images with sentences. Trans Assoc Comput Linguist 2:207–218

    Article  Google Scholar 

  • Socher R, Huval B, Manning CD, Ng AY (2012) Semantic compositionality through recursive matrix-vector spaces. In: Proceedings of the 2012 Joint Conference on empirical methods in natural language processing and computational natural language learning, (s. 1201–1211)

  • Socher R, Perelygin A, Wu JY, Chuang JM, Ng CD (2013) Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the conference on empirical methods in natural language processing (EMNLP)

  • Strawson PF (1950) On referring. Mind 59:320–344

    Article  Google Scholar 

  • Sutskever I, Vinyals O, Le Quoc V (2014) Sequence to sequence learning with neural networks. In: Proceedings of the 27th international conference on neural information processing systems. MIT Press, pp 3104–3112

  • van Noord R, Abzianidze L, Toral A, Bos J (2018) Exploring neural methods for parsing discourse representation structures. Trans Assoc Comput Linguist 6:619–633. https://doi.org/10.1162/tacl_a_00241

    Article  Google Scholar 

  • Zerilli J, Knott A, Maclaurin J, Gavaghan C (2019) Transparency in algorithmic and human decision-making: ıs there a double standard? Philos Technol 32:661–683

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Middle East Technical University: Orta Dogu Teknik Universitesi, Ankara, Turkey

    Tolgahan Toy

Authors
  1. Tolgahan Toy
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tolgahan Toy.

Ethics declarations

Conflict of interest

The authors have no conflicts of interest to declare.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Toy, T. Transparency in AI. AI & Soc (2023). https://doi.org/10.1007/s00146-023-01786-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00146-023-01786-y

Keywords

Search

Navigation