A neural interlingua for multilingual machine translation
Not on the map. Why?
Abstract (arXiv)
We incorporate an explicit neural interlingua into a multilingual encoder-decoder neural machine translation (NMT) architecture. We demonstrate that our model learns a language-independent representation by performing direct zero-shot translation (without using pivot translation), and by using the source sentence embeddings to create an English Yelp review classifier that, through the mediation of the neural interlingua, can also classify French and German reviews. Furthermore, we show that, despite using a smaller number of parameters than a pairwise collection of bilingual NMT models, our approach produces comparable BLEU scores for each language pair in WMT15.
Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Apr 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 11; 2022: 4; 2023: 6; 2024: 3; 2025: 3; 2026: 2.
29 papers.
Sort:
By area:
- 2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 109
- 2021Contrastive Learning for Many-to-many Multilingual Neural Machine Translationcited by 108
- 2021Learning Shared Semantic Space for Speech-to-Text Translationcited by 49
- 2021A Survey on Low-Resource Neural Machine Translationcited by 16
- 2022T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translationcited by 16
- 2022MMTAfrica: Multilingual Machine Translation for African Languagescited by 11
- 2023Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularizationcited by 10
- 2021Language Embeddings for Typology and Cross-lingual Transfer Learningcited by 8
- 2021Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translationcited by 8
- 2023Neural Machine Translation for the Indigenous Languages of the Americas: An Introductioncited by 7
- 2021Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?cited by 6
- 2022Adapting to Non-Centered Languages for Zero-shot Multilingual Translationcited by 6
17 more
- 2024Can Machine Translation Bridge Multilingual Pretraining and Cross-lingual Transfer Learning?cited by 6
- 2023The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translationcited by 4
- 2021Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoderscited by 3
- 2025The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlangcited by 3
- 2021Multilingual Neural Machine Translation:Can Linguistic Hierarchies Help?cited by 2
- 2022Unifying the Convergences in Multilingual Neural Machine Translationcited by 2
- 2025High-Dimensional Interlingual Representations of Large Language Modelscited by 2
- 2021Self-Learning for Zero Shot Neural Machine Translationcited by 1
- 2021Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddingscited by 1
- 2023TPDM: Selectively Removing Positional Information for Zero-shot Translation via Token-Level Position Disentangle Modulecited by 1
- 2024LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translationcited by 1
- 2023Variable-length Neural Interlingua Representations for Zero-shot Neural Machine Translationcited by 0
- 2023Direct Neural Machine Translation with Task-level Mixture of Experts modelscited by 0
- 2024I Have an Attention Bridge to Sell You: Generalization Capabilities of Modular Translation Architecturescited by 0
- 2025Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translationcited by 0
- 2026The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Spacecited by 0
- 2026ORCA: Evaluating LLMs on Data Science Code Translationcited by 0
- 2026ORCA: Evaluating LLMs on Data Science Code Translation25 Sep 2026
- 2026The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space1 Sep 2026
- 2025The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang30 Aug 2025
- 2025High-Dimensional Interlingual Representations of Large Language Models14 Mar 2025
- 2025Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translation6 Jan 2025
- 2024LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation5 Jun 2024
- 2024I Have an Attention Bridge to Sell You: Generalization Capabilities of Modular Translation Architectures27 Apr 2024
- 2024Can Machine Translation Bridge Multilingual Pretraining and Cross-lingual Transfer Learning?25 Mar 2024
- 2023Direct Neural Machine Translation with Task-level Mixture of Experts models18 Oct 2023
- 2023Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction11 Jun 2023
- 2023TPDM: Selectively Removing Positional Information for Zero-shot Translation via Token-Level Position Disentangle Module31 May 2023
- 2023Variable-length Neural Interlingua Representations for Zero-shot Neural Machine Translation17 May 2023
17 more
- 2023The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation16 May 2023
- 2023Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization12 May 2023
- 2022Adapting to Non-Centered Languages for Zero-shot Multilingual Translation9 Sep 2022
- 2022T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation24 May 2022
- 2022Unifying the Convergences in Multilingual Neural Machine Translation3 May 2022
- 2022MMTAfrica: Multilingual Machine Translation for African Languages8 Apr 2022
- 2021Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translation16 Oct 2021
- 2021Multilingual Neural Machine Translation:Can Linguistic Hierarchies Help?15 Oct 2021
- 2021A Survey on Low-Resource Neural Machine Translation9 Jul 2021
- 2021Neural Machine Translation for Low-Resource Languages: A Survey29 Jun 2021
- 2021Language Embeddings for Typology and Cross-lingual Transfer Learning3 Jun 2021
- 2021Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?31 May 2021
- 2021Contrastive Learning for Many-to-many Multilingual Neural Machine Translation20 May 2021
- 2021Learning Shared Semantic Space for Speech-to-Text Translation7 May 2021
- 2021Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddings11 Mar 2021
- 2021Self-Learning for Zero Shot Neural Machine Translation10 Mar 2021
- 2021Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders12 Feb 2021
- 2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 109
- 2021Contrastive Learning for Many-to-many Multilingual Neural Machine Translationcited by 108
- 2021Learning Shared Semantic Space for Speech-to-Text Translationcited by 49
- 2021A Survey on Low-Resource Neural Machine Translationcited by 16
- 2022T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translationcited by 16
- 2022MMTAfrica: Multilingual Machine Translation for African Languagescited by 11
- 2023Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularizationcited by 10
- 2021Language Embeddings for Typology and Cross-lingual Transfer Learningcited by 8
- 2021Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translationcited by 8
- 2023Neural Machine Translation for the Indigenous Languages of the Americas: An Introductioncited by 7
- 2021Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?cited by 6
- 2022Adapting to Non-Centered Languages for Zero-shot Multilingual Translationcited by 6
12 most cited of 26 All 26 (JSON)
- 2026ORCA: Evaluating LLMs on Data Science Code Translation25 Sep 2026
- 2026The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space1 Sep 2026
- 2025High-Dimensional Interlingual Representations of Large Language Models14 Mar 2025
- 2025Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translation6 Jan 2025
- 2024LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation5 Jun 2024
- 2024I Have an Attention Bridge to Sell You: Generalization Capabilities of Modular Translation Architectures27 Apr 2024
- 2024Can Machine Translation Bridge Multilingual Pretraining and Cross-lingual Transfer Learning?25 Mar 2024
- 2023Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction11 Jun 2023
- 2023TPDM: Selectively Removing Positional Information for Zero-shot Translation via Token-Level Position Disentangle Module31 May 2023
- 2023Variable-length Neural Interlingua Representations for Zero-shot Neural Machine Translation17 May 2023
- 2023The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation16 May 2023
- 2023Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization12 May 2023
12 newest of 26 All 26 (JSON)