YBYonatan Belinkov

Yonatan Belinkov

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yonatan Belinkov has a total of 32 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition

    by Yonatan Belinkov, Ahmed Ali, James Glass

    End-to-end neural network systems for automatic speech recognition (ASR) are trained from acoustic features to text transcriptions. In contrast to modular ASR systems, which contain separately-trained components for acoustic modeling, pronunciation lexicon, and language modeling, the end-to-end paradigm is both conceptually simpler and has the potential benefit of training the entire system on the end task. However, such neural network models are more opaque: it is not clear how to interpret the role of different parts of the network and what information it learns during training. In this paper, we analyze the learned internal representations in an end-to-end ASR model. We evaluate the representation quality in terms of several classification tasks, comparing phonemes and graphemes, as well as different articulatory features. We study two languages (English and Arabic) and three datasets, finding remarkable consistency in how different properties are represented in different layers of the deep neural network.

  • Studying the history of the Arabic language: language technology and a large-scale historical corpus

    by Yonatan Belinkov, Alexander Magidow, Alberto Barrón-Cedeño, Avi Shmidman, Maxim Romanov


  • Language processing and learning models for community question answering in Arabic

    by Salvatore Romeo, Giovanni Da San Martino, Yonatan Belinkov, Alberto Barrón-Cedeño, Mohamed Eldesouki, Kareem Darwish, Hamdy Mubarak, James Glass, Alessandro Moschitti


  • Open Access

    Analysis Methods in Neural Language Processing: A Survey

    by Yonatan Belinkov, James Glass

    The field of natural language processing has seen impressive progress in recent years, with neural network models replacing many of the traditional systems. A plethora of new models have been proposed, many of which are thought to be opaque compared to their feature-rich counterparts. This has led researchers to analyze, interpret, and evaluate neural networks in novel and more fine-grained ways. In this survey paper, we review analysis methods in neural language processing, categorize them according to prominent research trends, highlight existing limitations, and point to potential directions for future work.


  • Open Access

    Neural Machine Translation Training in a Multi-Domain Scenario

    by Hassan Sajjad, Nadir Durrani, Fahim Dalvi, Yonatan Belinkov, Stephan Vogel

    In this paper, we explore alternative ways to train a neural machine translation system in a multi-domain scenario. We investigate data concatenation (with fine tuning), model stacking (multi-level fine tuning), data selection and multi-model ensemble. Our findings show that the best translation quality can be achieved by building an initial system on a concatenation of available out-of-domain data and then fine-tuning it on in-domain data. Model stacking works best when training begins with the furthest out-of-domain data and the model is incrementally fine-tuned with the next furthest domain and so on. Data selection did not give the best results, but can be considered as a decent compromise between training time and translation quality. A weighted ensemble of different individual models performed better than data selection. It is beneficial in a scenario when there is no time for fine-tuning an already trained model.

  • Open Access

    Identifying and Controlling Important Neurons in Neural Machine Translation

    by Anthony Bau, Yonatan Belinkov, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, James Glass

    Neural machine translation (NMT) models learn representations containing substantial linguistic information. However, it is not clear if such information is fully distributed or if some of it can be attributed to individual neurons. We develop unsupervised methods for discovering important neurons in NMT models. Our methods rely on the intuition that different models learn similar properties, and do not require any costly external supervision. We show experimentally that translation quality depends on the discovered neurons, and find that many of them capture common linguistic phenomena. Finally, we show how to control NMT translations in predictable ways, by modifying activations of individual neurons.


  • Open Access

    What do Neural Machine Translation Models Learn about Morphology?

    by Yonatan Belinkov, Nadir Durrani, Fahim Dalvi, Hassan Sajjad, James Glass

    Neural machine translation (MT) models obtain state-of-the-art performance while maintaining a simple, end-to-end architecture. However, little is known about what these models learn about source and target languages during the training process. In this work, we analyze the representations learned by neural MT models at various levels of granularity and empirically evaluate the quality of the representations for learning morphology through extrinsic part-of-speech and morphological tagging tasks. We conduct a thorough investigation along several parameters: word-based vs. character-based representations, depth of the encoding layer, the identity of the target language, and encoder vs. decoder representations. Our data-driven, quantitative evaluation sheds light on important aspects in the neural MT system and its ability to capture word structure.


  • Open Access

    On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference

    by Adam Poliak, Yonatan Belinkov, James Glass, Benjamin Van Durme

    We propose a process for investigating the extent to which sentence representations arising from neural machine translation (NMT) systems encode distinct semantic phenomena. We use these representations as features to train a natural language inference (NLI) classifier based on datasets recast from existing semantic annotations. In applying this process to a representative NMT system, we find its encoder appears most suited to supporting inferences at the syntax-semantics interface, as compared to anaphora resolution requiring world-knowledge. We conclude with a discussion on the merits and potential deficiencies of the existing process, and how it may be improved and extended as a broader framework for evaluating semantic coverage.

  • Open Access

    Synthetic and Natural Noise Both Break Neural Machine Translation

    by Yonatan Belinkov, Yonatan Bisk

    Character-based neural machine translation (NMT) models alleviate out-of-vocabulary issues, learn morphology, and move us closer to completely end-to-end translation systems. Unfortunately, they are also very brittle and easily falter when presented with noisy data. In this paper, we confront NMT models with synthetic and natural sources of noise. We find that state-of-the-art models fail to translate even moderately noisy texts that humans have no trouble comprehending. We explore two approaches to increase model robustness: structure-invariant word representations and robust training on noisy texts. We find that a model based on a character convolutional neural network is able to simultaneously learn representations robust to multiple kinds of noise.


  • Open Access

    Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks

    by Yonatan Belinkov, Lluís Màrquez, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, James Glass

    While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector representations learned by NMT models on morphological and syntactic tasks. In this paper, we investigate the representations learned at different layers of NMT encoders. We train NMT systems on parallel data and use the trained models to extract features for training a classifier on two tasks: part-of-speech and semantic tagging. We then measure the performance of the classifier as a proxy to the quality of the original NMT model for the given task. Our quantitative analysis yields interesting insights regarding representation learning in NMT models. For instance, we find that higher layers are better at learning semantics while lower layers tend to be better for part-of-speech tagging. We also observe little effect of the target language on source-side representations, especially with higher quality NMT models.