On the Linguistic Representational Power of Neural Machine Translation Models

By Yonatan Belinkov, Nadir Durrani, Fahim Dalvi, Hassan Sajjad, James R. Glass. 2019

77 citations recorded by the source corpus.

Despite the recent success of deep neural networks in natural language processing and other spheres of artificial intelligence, their interpretability remains a challenge. We analyze the representations learned by neural machine translation (NMT) 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, which is 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 trained in an end-to-end fashion, without being provided any direct supervision during the training process, learn a non-trivial amount of linguistic information. Notable findings include the following observations: (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 of the model; (iii) Representations learned using characters are more informed about word-morphology compared to those learned using subword units; and (iv) Representations learned by multilingual models are richer compared to bilingual models.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Computational Linguistics & Semantics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Computational Linguistics & Semantics

Citations in the corpus

Probing Classifiers: Promises, Shortcomings, and Advances (2021, background): “Belinkov et al. (2020) discuss how their probing experiments can guide the selection of which machine translation models to use when translating speciﬁc languages.”
Analyzing Redundancy in Pretrained Transformer Models (2020, background): “Linear classifiers are a popular choice in analyzing deep NLP models due to their better interpretability (Qian et al., 2016; Belinkov et al., 2020).”
Probing Classifiers: Promises, Shortcomings, and Alternatives (2021, background): “Belinkov et al. (2020) discuss how their probing experiments can guide the selection of which machine translation models to use when translating speciﬁc languages.”
Gender Bias in Machine Translation (2021, methodology): “We think that explainability techniques (Belinkov et al., 2020) represent a useful tool to identify spurious cues (features) exploited by the model during inference.”
Analyzing Individual Neurons in Pre-trained Language Models (2020, unknown): “Linear classifiers are a popular choice in analyzing deep NLP models due to their better interpretability (Qian et al., 2016; Belinkov et al., 2020).”