The University of Cambridge’s Machine Translation Systems for WMT18

By Felix Stahlberg, Adrià de Gispert, Bill Byrne. 2018

20 citations recorded by the source corpus.

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-attention-based neural models on German-English, English-German, and Chinese-English. Our final system combines all neural models together with a phrase-based SMT system in an MBR-based scheme. We report small but consistent gains on top of strong Transformer ensembles.

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

The NiuTrans Machine Translation Systems for WMT19 (2019, methodology): “…features would be described on five aspects as following: Right-to-Left Models: NMT models generate target translations in a left to right fashion, so it’s obviously that incorporating models which generate the target sentences in reverse order can be complementary (Stahlberg et al., 2018).”
Findings of the 2018 Conference on Machine Translation (WMT18) (2018, background): “The results highlight the overall performance of UCAM, followed by NTT and MLLP-UPV.”
Text Repair Model for Neural Machine Translation (2019, background): “Table 4 shows the results for the 2 top submissions of Microsoft (Junczys-Dowmunt, 2018) and Cambridge (Stahlberg et al., 2018).”
On NMT Search Errors and Model Errors: Cat Got Your Tongue? (2019, methodology): “Even a highly optimized Transformer Big model from our WMT18 shared task submission (Stahlberg et al., 2018a) has 25.8% empty translations.”
Exploiting Monolingual Data at Scale for Neural Machine Translation (2019, methodology): “We also list the WMT18 top-2 systems for De → En translation in Table 4: RWTH (Grac¸a et al., 2018) and UCAM (Stahlberg et al., 2018) systems, which are both ensemble models.”
APE at Scale and Its Implications on MT Evaluation Biases (2019, background): “Table 4 shows the results for the 2 top submissions of Microsoft (Junczys-Dowmunt, 2018) and Cambridge (Stahlberg et al., 2018 Finally, we train our APE model on different random subsets of the available 216.5M monolingual data (see Figure 3).”
Depth Growing for Neural Machine Translation (2019, methodology): “For example, the LSTM-based models are usually stacked for 4 (Stahlberg et al., 2018) or 6 (Chen et al., 2018) blocks, and the state-of-the-art Trans-former models are equipped with a 6 -block encoder and decoder (Vaswani et al., 2017; Junczys-Dowmunt, 2018; Edunov et al., 2018).”
The University of Helsinki Submissions to the WMT19 News Translation Task (2019, methodology): “Heuristic filters: The first step in cleaning the data refers to a number of heuristics (largely inspired by (Stahlberg et al., 2018)) including: • removing all sentence pairs with a length difference ratio above a certain threshold: for CommonCrawl, ParaCrawl and Rapid we used a threshold of 3,…”