Neural Fuzzy Repair: Integrating Fuzzy Matches into Neural Machine Translation

By Bram Bulté, Arda Tezcan. 2019

95 citations recorded by the source corpus.

We present a simple yet powerful data augmentation method for boosting Neural Machine Translation (NMT) performance by leveraging information retrieved from a Translation Memory (TM). We propose and test two methods for augmenting NMT training data with fuzzy TM matches. Tests on the DGT-TM data set for two language pairs show consistent and substantial improvements over a range of baseline systems. The results suggest that this method is promising for any translation environment in which a sizeable TM is available and a certain amount of repetition across translations is to be expected, especially considering its ease of implementation.

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

Simple and Effective Retrieve-Edit-Rerank Text Generation (2020, methodology): “We evaluate performance on the Gigaword summarization dataset (Rush et al., 2015) and on the English to Dutch (EN-NL) and the English to Hungarian (EN-HU) machine translation (MT) tasks, following Bulte and Tezcan (2019).”
A Survey of Data Augmentation Approaches for NLP (2021, background): “Bulte and Tezcan (2019) Propose DA approaches for NMT that leverage information retrieved from a Translation Memory (TM) and using fuzzy TM matches.”
Nearest Neighbor Machine Translation (2020, background): “Bulte & Tezcan (2019) and Xu et al. (2020) use fuzzy-matching with translation memories and augment source sequences with retrieved source-target pairs.”
Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back-Translation (2019, methodology): “We also adapt the idea of fuzzy matches from Bulte and Tezcan (2019) to the MTNT case by ﬁnding similar sentences in a parallel corpus to augment the limited noisy data.”
Retrieval-based Neural Source Code Summarization (2020, methodology): “…with additional retrieval information, a Translation Memory (TM) which consists of source and target sentence pairs is leveraged by graph representation and self-attention mechanism over the graph [62], or augmenting the source data with retrieved fuzzy TM targets by means of concatenation [10].”
A Survey of Knowledge-enhanced Text Generation (2020, background): “[75, 149] Summarization Document [105, 146] [80, 84] [2, 104] [166] [65, 183] [72, 87] [84] [18, 47, 145] (e.g., an article) [43, 149] [81] Machine Sentence [152, 174] - [31, 124] - [103, 177] [1, 6] [15, 165] translation [131] Content Document [83] - - [41, 67, 150] - - - manipulation Content Docum”