Models and Inference for Prefix-Constrained Machine Translation

By Joern Wuebker, Spence Green, John DeNero, Sasa Hasan, Minh-Thang Luong. 2016

58 citations recorded by the source corpus.

We apply phrase-based and neural models to a core task in interactive machine translation: suggesting how to complete a partial translation. For the phrase-based sys-tem, we demonstrate improvements in suggestion quality using novel objective functions, learning techniques, and inference algorithms tailored to this task. Our contributions include new tunable metrics, an improved beam search strategy, an n -best extraction method that increases suggestion diversity, and a tuning procedure for a hierarchical joint model of alignment and translation. The combination of these techniques improves next-word suggestion accuracy dramatically from 28.5% to 41.2% in a large-scale English-German experiment. Our recurrent neural translation system increases accuracy yet further to 53.0%, but inference is two orders of magnitude slower. Manual error analysis shows the strengths and weaknesses of both approaches.

Subfields: Artificial Intelligence, Natural Language Processing

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 Natural Language Processing

Citations in the corpus

Few-Shot Text Generation with Natural Language Instructions (2020, background): “Our work is also related to prefix-constrained decoding in interactive machine translation for making suggestions on how to complete a partial translation (Knowles and Koehn, 2016; Wuebker et al., 2016).”
Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP (2021, methodology): “Our proposed self-debiasing algorithm bears some resemblance with preﬁx-constrained decoding used in interactive machine translation for completing partial translations (Knowles and Koehn, 2016; Wuebker et al., 2016).”
How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairs (2016, methodology): “While one could consider this instance a false positive, it can be important for an NMT model to properly score translations other than the 1-best, for instance for applications such as preﬁx-constrained MT (Wuebker et al., 2016).”
Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search (2017, methodology): “Wuebker et al. (2016) and Knowles and Koehn (2016) also present a simple modification of NMT models for IMT, enabling models to predict suffixes for user-supplied prefixes.”
Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation (2018, background): “Lexically-constrained decoding also generalizes prefix decoding (Knowles and Koehn, 2016; Wuebker et al., 2016), since the 〈s〉 symbol can easily be included as the first word of a constraint.”
CTRLsum: Towards Generic Controllable Text Summarization (2020, methodology): “We detail g control next, but describe the automatic keyword extraction later in §2.3.”
Few-Shot Text Generation with Pattern-Exploiting Training (2020, background): “…our proposed variant of P ET is closely related to concurrent work by He et al. (2020) who use prompts and keywords for controllable text generation (but do so only in high-resource settings) and to preﬁx-constrained decoding (Knowles and Koehn, 2016; Wuebker et al., 2016; Keskar et al., 2019).”
Neural Interactive Translation Prediction (2016, methodology): “Parallel to this work, Wuebker et al. (2016) also explore a similar approach to using neural MT for interactive translation prediction.”
A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation (2018, methodology): “This interaction protocol can easily be ﬁt to neural machine translation (NMT) (Bahdanau et al., 2015) by conditioning the model’s word predictions on the user-validated preﬁx (Knowles and Koehn, 2016; Wuebker et al., 2016).”