Rico Sennrich

A parallel corpus of Python functions and documentation strings for automated code documentation and code generation

2017 · arXiv (Cornell University)

Automated documentation of programming source code and automated code generation from natural language are challenging tasks of both practical and scientific interest. Progress in these areas has been limited by the low availability of parallel …

On Sparsifying Encoder Outputs in Sequence-to-Sequence Models

2021

Sequence-to-sequence models usually transfer all encoder outputs to the decoder for generation. In this work, by contrast, we hypothesize that these encoder outputs can be compressed to shorten the sequence delivered for decoding. We take …

Sparse Attention with Linear Units

2021 · Zurich Open Repository and Archive (University of Zurich)

Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for …

BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation

2022 · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Yuchen Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Jian Yang, Haoyang Huang, Rico Sennrich, Ryan Cotterell, Mrinmaya Sachan, Ming Zhou. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational …

How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?

2021 · arXiv (Cornell University)

Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite to evaluate …

Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents

2023 · Zurich Open Repository and Archive (University of Zurich)

Automatically highlighting words that cause semantic differences between two documents could be useful for a wide range of applications. We formulate recognizing semantic differences (RSD) as a token-level regression task and study three unsupervised approaches …

Robust Native Language Identification through Agentic Decomposition

2025 · arXiv (Cornell University)

Large language models (LLMs) often achieve high performance in native language identification (NLI) benchmarks by leveraging superficial contextual clues such as names, locations, and cultural stereotypes, rather than the underlying linguistic patterns indicative of native …

Neural Machine Translation of Rare Words with Subword Units

2016

Neural machine translation (NMT) models typically operate with a fixed vocabulary, but translation is an open-vocabulary problem. Previous work addresses the translation of out-of-vocabulary words by backing off to a dictionary. In this paper, we …

Controlling Politeness in Neural Machine Translation via Side Constraints

2016

Many languages use honorifics to express politeness, social distance, or the relative social status between the speaker and their addressee(s). In machine translation from a language without honorifics such as English, it is difficult to …

Nematus: a Toolkit for Neural Machine Translation

2017

Rico Sennrich, Orhan Firat, Kyunghyun Cho, Alexandra Birch, Barry Haddow, Julian Hitschler, Marcin Junczys-Dowmunt, Samuel Läubli, Antonio Valerio Miceli Barone, Jozef Mokry, Maria Nădejde. Proceedings of the Software Demonstrations of the 15th Conference of the …

Predicting Target Language CCG Supertags Improves Neural Machine Translation

2017

Neural machine translation (NMT) models are able to partially learn syntactic information from sequential lexical information. Still, some complex syntactic phenomena such as prepositional phrase attachment are poorly modeled. This work aims to answer two …

The University of Edinburgh's Neural MT Systems for WMT17

2017

Rico Sennrich, Alexandra Birch, Anna Currey, Ulrich Germann, Barry Haddow, Kenneth Heafield, Antonio Valerio Miceli Barone, Philip Williams. Proceedings of the Second Conference on Machine Translation. 2017.

Paraphrasing Revisited with Neural Machine Translation

2017

Recognizing and generating paraphrases is an important component in many natural language processing applications. A wellestablished technique for automatically extracting paraphrases leverages bilingual corpora to find meaning-equivalent phrases in a single language by "pivoting" over …

Improving Word Sense Disambiguation in Neural Machine Translation with Sense Embeddings

2017

Word sense disambiguation is necessary in translation because different word senses often have different translations. Neural machine translation models learn different senses of words as part of an endto-end translation task, and their capability to …

Evaluating Discourse Phenomena in Neural Machine Translation

2018

Rachel Bawden, Rico Sennrich, Alexandra Birch, Barry Haddow. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

Context-Aware Neural Machine Translation Learns Anaphora Resolution

2018

Standard machine translation systems process sentences in isolation and hence ignore extra-sentential information, even though extended context can both prevent mistakes in ambiguous cases and improve translation coherence. We introduce a context-aware neural machine translation …

Has Machine Translation Achieved Human Parity? A Case for Document-level Evaluation

2018

Recent research suggests that neural machine translation achieves parity with professional human translation on the WMT Chinese-English news translation task. We empirically test this claim with alternative evaluation protocols, contrasting the evaluation of single sentences …

Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned

2019

Multi-head self-attention is a key component of the Transformer, a state-of-the-art architecture for neural machine translation. In this work we evaluate the contribution made by individual attention heads in the encoder to the overall performance …

Revisiting Low-Resource Neural Machine Translation: A Case Study

2019

It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data to achieve competitive results. In …

Evaluating Discourse Phenomena in Neural Machine Translation

2017 · Zurich Open Repository and Archive (University of Zurich)

For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally evaluated with …