pith. sign in

arxiv: 1907.10676 · v1 · pith:OYKEWIFJnew · submitted 2019-07-23 · 💻 cs.CL

Semantic Web for Machine Translation: Challenges and Directions

Diego Moussallem , Matthias Wauer , Axel-Cyrille Ngonga Ngomo This is my paper

Pith reviewed 2026-05-24 17:25 UTC · model grok-4.3

classification 💻 cs.CL
keywords machine translationsemantic websystematic reviewlexical ambiguitysyntactic ambiguitynatural language processing
0
0 comments X

The pith

Semantic Web technologies can improve machine translation by addressing ambiguity but their combination remains in its infancy.

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

This paper conducts a systematic review of machine translation approaches that incorporate Semantic Web technologies to tackle obstacles such as lexical and syntactic ambiguity. It establishes that these technologies offer enhancements to translation quality across several problem areas. The review finds the overall integration of the two fields is still early and underdeveloped. A reader would care because effective machine translation enables fluid cross-language content movement, and knowing the current maturity level informs where additional work is most needed.

Core claim

A systematic review of machine translation approaches that rely on Semantic Web technologies shows they can enhance output quality for various problems including lexical and syntactic ambiguity, yet the combination of Semantic Web and machine translation is still in its infancy.

What carries the argument

The systematic review that surveys machine translation methods using Semantic Web technologies to resolve ambiguity and evaluates their current development stage.

If this is right

  • Semantic Web resources can be applied to reduce specific translation errors caused by ambiguity.
  • Opportunities exist to combine Semantic Web data with existing machine translation pipelines for targeted improvements.
  • Further development is required before these combined methods reach widespread practical use.
  • Challenges in data integration and scalability must be addressed to advance the field.

Where Pith is reading between the lines

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

  • Future work could test whether particular Semantic Web ontologies yield larger gains in specific language pairs.
  • The review's findings suggest machine translation research might benefit from closer ties to linked data initiatives.
  • If the infancy claim holds, funding bodies could prioritize hybrid projects that bridge the two areas.

Load-bearing premise

The review captured a representative sample of relevant approaches and accurately judged how mature each one is.

What would settle it

Discovery of multiple mature, production-deployed machine translation systems that make substantial use of Semantic Web technologies would contradict the infancy assessment.

read the original abstract

A large number of machine translation approaches have recently been developed to facilitate the fluid migration of content across languages. However, the literature suggests that many obstacles must still be dealt with to achieve better automatic translations. One of these obstacles is lexical and syntactic ambiguity. A promising way of overcoming this problem is using Semantic Web technologies. This article is an extended abstract of our systematic review on machine translation approaches that rely on Semantic Web technologies for improving the translation of texts. Overall, we present the challenges and opportunities in the use of Semantic Web technologies in Machine Translation. Moreover, our research suggests that while Semantic Web technologies can enhance the quality of machine translation outputs for various problems, the combination of both is still in its infancy.

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

2 major / 0 minor

Summary. This extended abstract of a systematic review surveys machine translation (MT) approaches that rely on Semantic Web (SW) technologies to address obstacles such as lexical and syntactic ambiguity. The central claim is that SW technologies can enhance MT output quality for various problems, yet the combination of the two remains in its infancy; the paper also outlines associated challenges and opportunities.

Significance. If the systematic review underlying the abstract is comprehensive and methodologically rigorous, the work could usefully map an emerging intersection between Semantic Web and machine translation research, highlighting directions for improving semantic handling in translation systems.

major comments (2)
  1. [Abstract] Abstract: The manuscript states it is an extended abstract of a systematic review but supplies no information on search strategy, databases queried, query strings, inclusion/exclusion criteria, screening process, or quality assessment. These details are load-bearing for the claim that the SW-MT combination 'is still in its infancy,' as they determine whether the reviewed sample is representative and whether maturity judgments are reproducible.
  2. [Abstract] Abstract: The phrase 'still in its infancy' is used without an operational definition (e.g., publication counts, citation patterns, or explicit maturity criteria relative to other MT paradigms). Without this or the full review's data, the central claim cannot be evaluated from the provided text.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive feedback on our extended abstract. We address each major comment below and commit to revisions that enhance the methodological transparency and rigor of the claims.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The manuscript states it is an extended abstract of a systematic review but supplies no information on search strategy, databases queried, query strings, inclusion/exclusion criteria, screening process, or quality assessment. These details are load-bearing for the claim that the SW-MT combination 'is still in its infancy,' as they determine whether the reviewed sample is representative and whether maturity judgments are reproducible.

    Authors: We agree that the extended abstract omits these methodological details, which limits evaluation of the review's scope and reproducibility. The underlying systematic review (of which this is an extended abstract) followed a standard protocol with explicit search strategy, databases (including Google Scholar, ACM Digital Library, IEEE Xplore), query strings, inclusion/exclusion criteria, screening stages, and quality assessment. Due to length constraints in the abstract format, these were not included. We will revise the abstract to add a concise methods summary (e.g., number of papers screened and included, key search terms) to support the representativeness of the sample. revision: yes

  2. Referee: [Abstract] Abstract: The phrase 'still in its infancy' is used without an operational definition (e.g., publication counts, citation patterns, or explicit maturity criteria relative to other MT paradigms). Without this or the full review's data, the central claim cannot be evaluated from the provided text.

    Authors: The characterization draws directly from the review's findings of a small number of integrated SW-MT approaches and persistent integration challenges. We acknowledge the need for an operational definition to make the claim evaluable. We will revise the abstract to qualify the statement explicitly, for example by referencing the low publication volume identified in the review and contrasting it with the more established status of neural MT paradigms. revision: yes

Circularity Check

0 steps flagged

Survey paper with no derivations or self-referential reductions

full rationale

This is a literature survey (extended abstract of a systematic review) that summarizes external machine translation papers using Semantic Web technologies. No equations, fitted parameters, ansatzes, or derivation chains exist. The central claim that the combination remains in its infancy is presented as an empirical observation drawn from reviewed external works rather than a result that reduces to the paper's own inputs by construction. No load-bearing self-citations or uniqueness theorems are invoked.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The review rests on standard assumptions that a systematic literature search can capture the state of an interdisciplinary field and that Semantic Web resources can in principle supply disambiguation information for translation; no free parameters, ad-hoc axioms, or invented entities are introduced by the paper itself.

pith-pipeline@v0.9.0 · 5647 in / 992 out tokens · 26363 ms · 2026-05-24T17:25:20.348619+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

22 extracted references · 22 canonical work pages · 2 internal anchors

  1. [1]

    CoRR, abs/1709.021 84 (2017)

    Arcan, M., Buitelaar, P.: Translating domain-specific ex pressions in knowledge bases with neural machine translation. CoRR, abs/1709.021 84 (2017)

    work page 2017

  2. [2]

    Arcan, M., Turchi, M., Buitelaar, P.: Knowledge Portabil ity with Semantic Expan- sion of Ontology Labels. In: ACL. pp. 708–718 (2015)

    work page 2015

  3. [3]

    In: Ad- vances in computers, vol

    Bar-Hillel, Y.: The present status of automatic translat ion of languages. In: Ad- vances in computers, vol. 1, pp. 91–163. Elsevier (1960)

    work page 1960

  4. [4]

    Computational linguistics 16(2), 79–85 (1990)

    Brown, P.F., Cocke, J., Della Pietra, S.A., Della Pietra, V.J., Jelinek, F., Lafferty, J.D., Mercer, R.L., Roossin, P.S.: A statistical approach t o machine translation. Computational linguistics 16(2), 79–85 (1990)

    work page 1990

  5. [5]

    In: EMNLP-CoNLL

    Carpuat, M., Wu, D.: Improving Statistical Machine Trans lation Using Word Sense Disambiguation. In: EMNLP-CoNLL. vol. 7, pp. 61–72 (2007)

    work page 2007

  6. [6]

    In: Proceedings of the Tenth International Conference on La nguage Resources and Evaluation 2016

    Du, J., Way, A., Zydron, A.: Using babelnet to improve OOV c overage in SMT. In: Proceedings of the Tenth International Conference on La nguage Resources and Evaluation 2016. pp. 9–15 (2016)

    work page 2016

  7. [7]

    Hutchins, W.J., Somers, H.L.: An introduction to machine translation, vol. 362. Academic Press London (1992)

    work page 1992

  8. [8]

    In: AAAI

    Knight, K., Luk, S.K.: Building a large-scale knowledge b ase for machine transla- tion. In: AAAI. vol. 94, pp. 773–778 (1994)

    work page 1994

  9. [9]

    Cambridge U niversity Press (2010)

    Koehn, P.: Statistical Machine Translation. Cambridge U niversity Press (2010)

    work page 2010

  10. [10]

    Six Challenges for Neural Machine Translation

    Koehn, P., Knowles, R.: Six Challenges for Neural Machin e Translation. arXiv preprint arXiv:1706.03872 (2017)

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  11. [11]

    In: Proceedings of the EMNLP Workshop on Twenty Years of Bitext

    Lopez, A., Post, M.: Beyond bitext: Five open problems in machine translation. In: Proceedings of the EMNLP Workshop on Twenty Years of Bitext. pp. 1–3 (2013)

    work page 2013

  12. [12]

    Web Semantics: Scie nce, Services and Agents on the WWW pp

    McCrae, J.P., Arcan, M., Asooja, K., Gracia, J., Buitela ar, P., Cimiano, P.: Domain adaptation for ontology localization. Web Semantics: Scie nce, Services and Agents on the WWW pp. 23–31 (2016)

    work page 2016

  13. [13]

    Augmenting Neural Machine Translation with Knowledge Graphs

    Moussallem, D., Arˇ can, M., Ngomo, A.C.N., Buitelaar, P .: Augmenting neural ma- chine translation with knowledge graphs. arXiv preprint ar Xiv:1902.08816 (2019)

    work page internal anchor Pith review Pith/arXiv arXiv 1902

  14. [14]

    , Ngomo, A.C.N.: LIdioms: A Multilingual Linked Idioms Data Set

    Moussallem, D., Sherif, M.A., Esteves, D., Zampieri, M. , Ngomo, A.C.N.: LIdioms: A Multilingual Linked Idioms Data Set. In: LREC 2018. p. 7 (20 18)

    work page 2018

  15. [15]

    In: Pro- ceedings of the Knowledge Capture Conference

    Moussallem, D., Usbeck, R., R¨ oeder, M., Ngomo, A.C.N.: MAG: A Multilingual, Knowledge-base Agnostic and Deterministic Entity Linking Approach. In: Pro- ceedings of the Knowledge Capture Conference. p. 9. ACM (201 7)

    work page

  16. [16]

    Journal of Web Semantics 51, 1–19 (2018)

    Moussallem, D., Wauer, M., Ngomo, A.C.N.: Machine trans lation using semantic web technologies: A survey. Journal of Web Semantics 51, 1–19 (2018)

    work page 2018

  17. [17]

    In: The Semantic Web ISWC 2019, pp

    Moussallem, D., et al.: THOTH: Neural Translation and En richment of Knowledge Graphs. In: The Semantic Web ISWC 2019, pp. 1–17. Springer (2 019)

    work page 2019

  18. [18]

    Artificial Intelligence 193, 217–250 (2012)

    Navigli, R., Ponzetto, S.P.: BabelNet: The automatic co nstruction, evaluation and application of a wide-coverage multilingual semantic netw ork. Artificial Intelligence 193, 217–250 (2012)

    work page 2012

  19. [19]

    In: Proceedings of the Seventh Workshop on Statistical Machine Translation

    Popovi´ c, M.: Class error rates for evaluation of machin e translation output. In: Proceedings of the Seventh Workshop on Statistical Machine Translation. pp. 71–

    work page

  20. [20]

    Association for Computational Linguistics (2012)

    work page 2012

  21. [21]

    In: International Semantic Web Conference

    Ristoski, P., Paulheim, H.: Rdf2vec: Rdf graph embeddin gs for data mining. In: International Semantic Web Conference. pp. 498–514. Sprin ger (2016)

    work page 2016

  22. [22]

    In: Proceedings of the 54th Annual Meeting of the Associatio n for Computational Linguistics)

    Shi, C., et al.: Knowledge-Based Semantic Embedding for Machine Translation. In: Proceedings of the 54th Annual Meeting of the Associatio n for Computational Linguistics). vol. 1, pp. 2245–2254 (2016)

    work page 2016