# On the Linguistic Representational Power of Neural Machine Translation Models

arXiv: https://arxiv.org/abs/1911.00317 · HTML: https://mlsanity.com/paper/1911.00317/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2019.

## Built on by (most cited first, 30 of 34)

- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [Neuron-level Interpretation of Deep NLP Models: A Survey](https://mlsanity.com/paper/2108.13138/) (2021)
- [Discovering Latent Concepts Learned in BERT](https://mlsanity.com/paper/2205.07237/) (2022)
- [Monitoring Latent World States in Language Models with Propositional Probes](https://mlsanity.com/paper/2406.19501/) (2024)
- [Analyzing Encoded Concepts in Transformer Language Models](https://mlsanity.com/paper/2206.13289/) (2022)
- [How transfer learning impacts linguistic knowledge in deep NLP models?](https://mlsanity.com/paper/2105.15179/) (2021)
- [Probing Pretrained Models of Source Code](https://mlsanity.com/paper/2202.08975/) (2022)
- [Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks](https://mlsanity.com/paper/2105.00573/) (2021)
- [Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation](https://mlsanity.com/paper/2203.09866/) (2022)
- [Discovering Salient Neurons in Deep NLP Models](https://mlsanity.com/paper/2206.13288/) (2022)
- [On the Transformation of Latent Space in Fine-Tuned NLP Models](https://mlsanity.com/paper/2210.12696/) (2022)
- [Can LLMs facilitate interpretation of pre-trained language models?](https://mlsanity.com/paper/2305.13386/) (2023)
- [Mediators in Determining what Processing BERT Performs First](https://mlsanity.com/paper/2104.06400/) (2021)
- [Probing for Constituency Structure in Neural Language Models](https://mlsanity.com/paper/2204.06201/) (2022)
- [Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5](https://mlsanity.com/paper/2410.11627/) (2024)
- [How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation](https://mlsanity.com/paper/2105.13782/) (2021)
- [Effect of Post-processing on Contextualized Word Representations](https://mlsanity.com/paper/2104.07456/) (2021)
- [How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?](https://mlsanity.com/paper/2109.01100/) (2021)
- [Explaining Language Models' Predictions with High-Impact Concepts](https://mlsanity.com/paper/2305.02160/) (2023)
- [What's the best place for an AI conference, Vancouver or ______: Why completing comparative questions is difficult](https://mlsanity.com/paper/2104.01940/) (2021)
- [Fine-grained Interpretation and Causation Analysis in Deep NLP Models](https://mlsanity.com/paper/2105.08039/) (2021)
- [The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation](https://mlsanity.com/paper/2305.09652/) (2023)
- [Interpretability in Activation Space Analysis of Transformers: A Focused Survey](https://mlsanity.com/paper/2302.09304/) (2023)
- [Signatures of human-like processing in Transformer forward passes](https://mlsanity.com/paper/2504.14107/) (2025)
- [Layer-wise Representation Fusion for Compositional Generalization](https://mlsanity.com/paper/2307.10799/) (2023)
- [Artificial intelligence contribution to translation industry: looking back and forward](https://mlsanity.com/paper/2411.19855/) (2024)
- [Screening Gender Transfer in Neural Machine Translation](https://mlsanity.com/paper/2202.12568/) (2022)
- [Post-hoc analysis of Arabic transformer models](https://mlsanity.com/paper/2210.09990/) (2022)
- [NxPlain: Web-based Tool for Discovery of Latent Concepts](https://mlsanity.com/paper/2303.03019/) (2023)

## Abstract (arXiv)

Despite the recent success of deep neural networks in natural language processing (NLP), their interpretability remains a challenge. We analyze the representations learned by neural machine translation models at various levels of granularity and evaluate their quality through relevant extrinsic properties. In particular, we seek answers to the following questions: (i) How accurately is word-structure captured within the learned representations, an important aspect in translating morphologically-rich languages? (ii) Do the representations capture long-range dependencies, and effectively handle syntactically divergent languages? (iii) Do the representations capture lexical semantics? We conduct a thorough investigation along several parameters: (i) Which layers in the architecture capture each of these linguistic phenomena; (ii) How does the choice of translation unit (word, character, or subword unit) impact the linguistic properties captured by the underlying representations? (iii) Do the encoder and decoder learn differently and independently? (iv) Do the representations learned by multilingual NMT models capture the same amount of linguistic information as their bilingual counterparts? Our data-driven, quantitative evaluation illuminates important aspects in NMT models and their ability to capture various linguistic phenomena. We show that deep NMT models learn a non-trivial amount of linguistic information. Notable findings include: i) Word morphology and part-of-speech information are captured at the lower layers of the model; (ii) In contrast, lexical semantics or non-local syntactic and semantic dependencies are better represented at the higher layers; (iii) Representations learned using characters are more informed about wordmorphology compared to those learned using subword units; and (iv) Representations learned by multilingual models are richer compared to bilingual models.