Related papers: Finding Better Subword Segmentation for Neural Mac…
Many-to-one neural machine translation systems improve over one-to-one systems when training data is scarce. In this paper, we design and test a novel algorithm for selecting the language of minibatches when training such systems. The…
In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training. The proposed approach consists of two stages. In the first…
Byte-level fallbacks for subword tokenization have become a common practice in large language models. In particular, it has been demonstrated to be incredibly effective as a pragmatic solution for preventing OOV, especially in the context…
With the increasing attention to molecular machine learning, various innovations have been made in designing better models or proposing more comprehensive benchmarks. However, less is studied on the data preprocessing schedule for molecular…
In spoken Keyword Search, the query may contain out-of-vocabulary (OOV) words not observed when training the speech recognition system. Using subword language models (LMs) in the first-pass recognition makes it possible to recognize the OOV…
This work presents a novel approach to Automatic Post-Editing (APE) and Word-Level Quality Estimation (QE) using ensembles of specialized Neural Machine Translation (NMT) systems. Word-level features that have proven effective for QE are…
Machine translation has gained much attention in recent years. It is a sub-field of computational linguistic which focus on translating text from one language to other language. Among different translation techniques, neural network…
Despite advances in neural machine translation (NMT) quality, rare words continue to be problematic. For humans, the solution to the rare-word problem has long been dictionaries, but dictionaries cannot be straightforwardly incorporated…
The quality of a Neural Machine Translation system depends substantially on the availability of sizable parallel corpora. For low-resource language pairs this is not the case, resulting in poor translation quality. Inspired by work in…
Multilingual automatic speech recognition (ASR) requires tokenization that efficiently covers many writing systems. Byte-level BPE (BBPE) using UTF-8 is widely adopted for its language-agnostic design and full Unicode coverage, but its…
The choice of token vocabulary affects the performance of machine translation. This paper aims to figure out what is a good vocabulary and whether one can find the optimal vocabulary without trial training. To answer these questions, we…
Word segmentation is the task of inserting or deleting word boundary characters in order to separate character sequences that correspond to words in some language. In this article we propose an approach based on a beam search algorithm and…
Neural machine translation (NMT) is sensitive to domain shift. In this paper, we address this problem in an active learning setting where we can spend a given budget on translating in-domain data, and gradually fine-tune a pre-trained…
In simultaneous machine translation, the objective is to determine when to produce a partial translation given a continuous stream of source words, with a trade-off between latency and quality. We propose a neural machine translation (NMT)…
We investigate adaptive ensemble weighting for Neural Machine Translation, addressing the case of improving performance on a new and potentially unknown domain without sacrificing performance on the original domain. We adapt sequentially…
Resolving semantic ambiguity has long been recognised as a central challenge in the field of Machine Translation. Recent work on benchmarking translation performance on ambiguous sentences has exposed the limitations of conventional Neural…
Homographs, words with different meanings but the same surface form, have long caused difficulty for machine translation systems, as it is difficult to select the correct translation based on the context. However, with the advent of neural…
Both research and commercial machine translation have so far neglected the importance of properly handling the spelling, lexical and grammar divergences occurring among language varieties. Notable cases are standard national varieties such…
Most studies on word-level Quality Estimation (QE) of machine translation focus on language-specific models. The obvious disadvantages of these approaches are the need for labelled data for each language pair and the high cost required to…
Quality Estimation (QE), the evaluation of machine translation output without the need of explicit references, has seen big improvements in the last years with the use of neural metrics. In this paper we analyze the viability of using QE…