Related papers: Revisiting Checkpoint Averaging for Neural Machine…

Machine Translation (MT) has been widely used for cross-lingual classification, either by translating the test set into English and running inference with a monolingual model (translate-test), or translating the training set into the target…

Conventional retrieval-augmented neural machine translation (RANMT) systems leverage bilingual corpora, e.g., translation memories (TMs). Yet, in many settings, monolingual corpora in the target language are often available. This work…

Existing machine translation decoding algorithms generate translations in a strictly monotonic fashion and never revisit previous decisions. As a result, earlier mistakes cannot be corrected at a later stage. In this paper, we present a…

Although neural machine translation has achieved promising results, it suffers from slow translation speed. The direct consequence is that a trade-off has to be made between translation quality and speed, thus its performance can not come…

Automatic machine translation (MT) metrics are widely used to distinguish the translation qualities of machine translation systems across relatively large test sets (system-level evaluation). However, it is unclear if automatic metrics are…

We present a new approach to the calculation of measures in weighted networks, based on the translation of a weighted network into an ensemble of edges. This leads to a straightforward generalization of any measure defined on unweighted…

Analysing translation quality in regards to specific linguistic phenomena has historically been difficult and time-consuming. Neural machine translation has the attractive property that it can produce scores for arbitrary translations, and…

Automatic evaluation comparing candidate translations to human-generated paraphrases of reference translations has recently been proposed by Freitag et al. When used in place of original references, the paraphrased versions produce metric…

Tying the weights of the target word embeddings with the target word classifiers of neural machine translation models leads to faster training and often to better translation quality. Given the success of this parameter sharing, we…

Prior work has proved that Translation memory (TM) can boost the performance of Neural Machine Translation (NMT). In contrast to existing work that uses bilingual corpus as TM and employs source-side similarity search for memory retrieval,…

Multilingual neural machine translation models are trained to maximize the likelihood of a mix of examples drawn from multiple language pairs. The dominant inductive bias applied to these models is a shared vocabulary and a shared set of…

Simultaneous machine translation is a variant of machine translation that starts the translation process before the end of an input. This task faces a trade-off between translation accuracy and latency. We have to determine when we start…

The majority of machine learning methods can be regarded as the minimization of an unavailable risk function. To optimize the latter, given samples provided in a streaming fashion, we define a general stochastic Newton algorithm and its…

Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In this work, we provide a theoretical motivation for task vectors…

Neural network checkpoints have quietly become a large-scale data resource: millions of trained weight vectors now exist, each encoding task-, domain-, and architecture-specific knowledge. This position paper argues that model checkpoints…

Generative models have recently been explored for synthesizing neural network weights. These approaches take neural network checkpoints as training data and aim to generate high-performing weights during inference. In this work, we examine…

Regularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in a system that is…

Low-frequency word prediction remains a challenge in modern neural machine translation (NMT) systems. Recent adaptive training methods promote the output of infrequent words by emphasizing their weights in the overall training objectives.…

In a world of proliferating data, the ability to rapidly summarize text is growing in importance. Automatic summarization of text can be thought of as a sequence to sequence problem. Another area of natural language processing that solves a…

Being able to rank the similarity of short text segments is an interesting bonus feature of neural machine translation. Translation-based similarity measures include direct and pivot translation probability, as well as translation…