WMT14

This paper presents the use of consensus among Machine Translation (MT) systems for the WMT14 Quality Estimation shared task. Consensus is explored here by com- paring the MT system output …...

This paper describes the UPC submissions to the WMT14 Metrics Shared Task: UPC- IPA and UPC-STOUT. These metrics use a collection of evaluation measures in- tegrated in ASIYA, a toolkit …...

This paper describes Meteor-WSD and RATATOUILLE, the LIMSI submissions to the WMT15 metrics shared task. Meteor- WSD extends synonym mapping to lan- guages other than English based on align- ments …...

We propose the use of character n-gram F-score for automatic evaluation of ma- chine translation output. Character n- grams have already been used as a part of more complex metrics, …...

Quality estimation evaluation commonly takes the form of measurement of the error that exists between predictions and gold standard labels for a particular test set of translations. Issues can arise …...

Many state-of-the-art Machine Translation (MT) evaluation metrics are complex, in- volve extensive external resources (e.g. for paraphrasing) and require tuning to achieve best results. We present a simple alternative approach …...

This paper describes VERTa’s submis- sion to the 2015 EMNLP Workshop on Statistical Machine Translation. VERTa is a linguistically-motivated metric that combines linguistic features at different levels. In this paper, …...

AbstractThere has been much recent work on training neural attention models at the sequence-level using either reinforcement learning-style methods or by optimizing the beam. In this paper, we survey a …...

AbstractNeural encoder-decoder models of machine translation have achieved impressive results, while learning linguistic knowledge of both the source and target languages in an implicit end-to-end manner. We propose a framework …...

AbstractNon-autoregressive translation models (NAT) have achieved impressive inference speedup. A potential issue of the existing NAT algorithms, however, is that the decoding is conducted in parallel, without directly considering previous …...

AbstractA typical architecture for end-to-end entity linking systems consists of three steps: mention detection, candidate generation and entity disambiguation. In this study we investigate the following questions: (a) Can all …...

AbstractRecently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence modeling …...

AbstractThe reordering model plays an important role in phrase-based statistical machine translation. However, there are few works that exploit the reordering information in neural machine translation. In this paper, we …...

AbstractIn this paper, we alleviate the local optimality of back-translation by learning a policy (takes the form of an encoder-decoder and is defined by its parameters) with future rewarding under …...

AbstractMulti-head attentive neural architectures have achieved state-of-the-art results on a variety of natural language processing tasks. Evidence has shown that they are overparameterized; attention heads can be pruned without significant …...

AbstractThis paper proposed a new subword segmentation method for neural machine translation, “Bilingual Subword Segmentation,” which tokenizes sentences to minimize the difference between the number of subword units in a …...

AbstractThe choice of hyper-parameters affects the performance of neural models. While much previous research (Sutskever et al., 2013; Duchi et al., 2011; Kingma and Ba, 2015) focuses on accelerating convergence …...

AbstractWe propose an efficient inference procedure for non-autoregressive machine translation that iteratively refines translation purely in the continuous space. Given a continuous latent variable model for machine translation (Shu et …...

AbstractThe masked language model has received remarkable attention due to its effectiveness on various natural language processing tasks. However, few works have adopted this technique in the sequence-to-sequence models. In …...

AbstractThe Transformer translation model (Vaswani et al., 2017) based on a multi-head attention mechanism can be computed effectively in parallel and has significantly pushed forward the performance of Neural Machine …...

AbstractRecent evidence reveals that Neural Machine Translation (NMT) models with deeper neural networks can be more effective but are difficult to train. In this paper, we present a MultiScale Collaborative …...

AbstractThis paper presents two strong methods, CTC and Imputer, for non-autoregressive machine translation that model latent alignments with dynamic programming. We revisit CTC for machine translation and demonstrate that a …...

AbstractPopular Neural Machine Translation model training uses strategies like backtranslation to improve BLEU scores, requiring large amounts of additional data and training. We introduce a class of conditional generative-discriminative hybrid …...

AbstractWe introduce DropHead, a structured dropout method specifically designed for regularizing the multi-head attention mechanism which is a key component of transformer. In contrast to the conventional dropout mechanism which …...

AbstractPosition encoding (PE), an essential part of self-attention networks (SANs), is used to preserve the word order information for natural language processing tasks, generating fixed position indices for input sequences. …...

AbstractWe describe an unsupervised method to create pseudo-parallel corpora for machine translation (MT) from unaligned text. We use multilingual BERT to create source and target sentence embeddings for nearest-neighbor search …...

AbstractNon-autoregressive neural machine translation, which decomposes the dependence on previous target tokens from the inputs of the decoder, has achieved impressive inference speedup but at the cost of inferior accuracy. …...

AbstractIn supervised learning, a well-trained model should be able to recover ground truth accurately, i.e. the predicted labels are expected to resemble the ground truth labels as much as possible. …...

AbstractWe demonstrate that, hidden within one-layer randomly weighted neural networks, there exist subnetworks that can achieve impressive performance, without ever modifying the weight initializations, on machine translation tasks. To find …...

AbstractWe introduce Bi-SimCut: a simple but effective training strategy to boost neural machine translation (NMT) performance. It consists of two procedures: bidirectional pretraining and unidirectional finetuning. Both procedures utilize SimCut, …...

AbstractStructured State Spaces for Sequences (S4) is a recently proposed sequence model with successful applications in various tasks, e.g. vision, language modelling, and audio. Thanks to its mathematical formulation, it …...