72 citations · 102 across the 18 of their papers we have counts for
28 papers
Towards an On-device Agent for Text Rewriting
Yun Zhu, Yinxiao Liu, Felix Stahlberg +7
Large Language Models (LLMs) have demonstrated impressive capabilities for text rewriting. Nonetheless, the large sizes of these models make them impractical for on-device inferenc…
Improved Long-Form Spoken Language Translation with Large Language Models
Arya D. McCarthy, Hao Zhang, Shankar Kumar +2
A challenge in spoken language translation is that plenty of spoken content is long-form, but short units are necessary for obtaining high-quality translations. To address this mis…
Conciseness: An Overlooked Language Task
Felix Stahlberg, Aashish Kumar, Chris Alberti +1
We report on novel investigations into training models that make sentences concise. We define the task and show that it is different from related tasks such as summarization and si…
Text Generation with Text-Editing Models
Eric Malmi, Yue Dong, Jonathan Mallinson +7
Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and s…
Jam or Cream First? Modeling Ambiguity in Neural Machine Translation with SCONES
Felix Stahlberg, Shankar Kumar
The softmax layer in neural machine translation is designed to model the distribution over mutually exclusive tokens. Machine translation, however, is intrinsically uncertain: the…
Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models
Felix Stahlberg, Ilia Kulikov, Shankar Kumar
In many natural language processing (NLP) tasks the same input (e.g. source sentence) can have multiple possible outputs (e.g. translations). To analyze how this ambiguity (also kn…
Transformer-based Models of Text Normalization for Speech Applications
Jae Hun Ro, Felix Stahlberg, Ke Wu +1
Text normalization, or the process of transforming text into a consistent, canonical form, is crucial for speech applications such as text-to-speech synthesis (TTS). In TTS, the sy…
Synthetic Data Generation for Grammatical Error Correction with Tagged Corruption Models
Felix Stahlberg, Shankar Kumar
Synthetic data generation is widely known to boost the accuracy of neural grammatical error correction (GEC) systems, but existing methods often lack diversity or are too simplisti…
Seq2Edits: Sequence Transduction Using Span-level Edit Operations
Felix Stahlberg, Shankar Kumar
We propose Seq2Edits, an open-vocabulary approach to sequence editing for natural language processing (NLP) tasks with a high degree of overlap between input and output texts. In t…
Using Context in Neural Machine Translation Training Objectives
Danielle Saunders, Felix Stahlberg, Bill Byrne
We present Neural Machine Translation (NMT) training using document-level metrics with batch-level documents. Previous sequence-objective approaches to NMT training focus exclusive…
Neural Machine Translation: A Review and Survey
Felix Stahlberg
The field of machine translation (MT), the automatic translation of written text from one natural language into another, has experienced a major paradigm shift in recent years. Sta…
On NMT Search Errors and Model Errors: Cat Got Your Tongue?
Felix Stahlberg, Bill Byrne
We report on search errors and model errors in neural machine translation (NMT). We present an exact inference procedure for neural sequence models based on a combination of beam s…
The CUED's Grammatical Error Correction Systems for BEA-2019
Felix Stahlberg, Bill Byrne
We describe two entries from the Cambridge University Engineering Department to the BEA 2019 Shared Task on grammatical error correction. Our submission to the low-resource track i…
UCAM Biomedical translation at WMT19: Transfer learning multi-domain ensembles
Danielle Saunders, Felix Stahlberg, Bill Byrne
The 2019 WMT Biomedical translation task involved translating Medline abstracts. We approached this using transfer learning to obtain a series of strong neural models on distinct d…
Cued@wmt19:ewc&lms
Felix Stahlberg, Danielle Saunders, Adria de Gispert +1
Two techniques provide the fabric of the Cambridge University Engineering Department's (CUED) entry to the WMT19 evaluation campaign: elastic weight consolidation (EWC) and differe…
Domain Adaptive Inference for Neural Machine Translation
Danielle Saunders, Felix Stahlberg, Adria de Gispert +1
We investigate adaptive ensemble weighting for Neural Machine Translation, addressing the case of improving performance on a new and potentially unknown domain without sacrificing…
Neural Grammatical Error Correction with Finite State Transducers
Felix Stahlberg, Christopher Bryant, Bill Byrne
Grammatical error correction (GEC) is one of the areas in natural language processing in which purely neural models have not yet superseded more traditional symbolic models. Hybrid…
Simple Fusion: Return of the Language Model
Felix Stahlberg, James Cross, Veselin Stoyanov
Neural Machine Translation (NMT) typically leverages monolingual data in training through backtranslation. We investigate an alternative simple method to use monolingual data for N…
An Operation Sequence Model for Explainable Neural Machine Translation
Felix Stahlberg, Danielle Saunders, Bill Byrne
We propose to achieve explainable neural machine translation (NMT) by changing the output representation to explain itself. We present a novel approach to NMT which generates the t…
The University of Cambridge's Machine Translation Systems for WMT18
Felix Stahlberg, Adria de Gispert, Bill Byrne
The University of Cambridge submission to the WMT18 news translation task focuses on the combination of diverse models of translation. We compare recurrent, convolutional, and self…
Multi-representation Ensembles and Delayed SGD Updates Improve Syntax-based NMT
Danielle Saunders, Felix Stahlberg, Adria de Gispert +1
We explore strategies for incorporating target syntax into Neural Machine Translation. We specifically focus on syntax in ensembles containing multiple sentence representations. We…
Why not be Versatile? Applications of the SGNMT Decoder for Machine Translation
Felix Stahlberg, Danielle Saunders, Gonzalo Iglesias +1
SGNMT is a decoding platform for machine translation which allows paring various modern neural models of translation with different kinds of constraints and symbolic models. In thi…
A Comparison of Neural Models for Word Ordering
Eva Hasler, Felix Stahlberg, Marcus Tomalin +2
We compare several language models for the word-ordering task and propose a new bag-to-sequence neural model based on attention-based sequence-to-sequence models. We evaluate the m…
SGNMT -- A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies
Felix Stahlberg, Eva Hasler, Danielle Saunders +1
This paper introduces SGNMT, our experimental platform for machine translation research. SGNMT provides a generic interface to neural and symbolic scoring modules (predictors) with…