Related papers: Reranking Machine Translation Hypotheses with Stru…
Transferability estimation has been attached to great attention in the computer vision fields. Researchers try to estimate with low computational cost the performance of a model when transferred from a source task to a given target task.…
In this paper we combine the advantages of a model using global source sentence contexts, the Discriminative Word Lexicon, and neural networks. By using deep neural networks instead of the linear maximum entropy model in the Discriminative…
Neural Machine Translation (NMT) typically leverages monolingual data in training through backtranslation. We investigate an alternative simple method to use monolingual data for NMT training: We combine the scores of a pre-trained and…
Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at the cost of inferior accuracy compared to autoregressive…
Discourse coherence plays an important role in the translation of one text. However, the previous reported models most focus on improving performance over individual sentence while ignoring cross-sentence links and dependencies, which…
The end-to-end nature of neural machine translation (NMT) removes many ways of manually guiding the translation process that were available in older paradigms. Recent work, however, has introduced a new capability: lexically constrained or…
Evaluation is a bottleneck in the development of natural language generation (NLG) models. Automatic metrics such as BLEU rely on references, but for tasks such as open-ended generation, there are no references to draw upon. Although…
Pre-trained language model representations have been successful in a wide range of language understanding tasks. In this paper, we examine different strategies to integrate pre-trained representations into sequence to sequence models and…
A challenge in spoken language translation is that plenty of spoken content is long-form, but short units are necessary for obtaining high-quality translations. To address this mismatch, we fine-tune a general-purpose, large language model…
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…
High-resource languages such as English, enables the pretraining of high-quality large language models (LLMs). The same can not be said for most other languages as LLMs still underperform for non-English languages, likely due to a gap in…
The non-autoregressive models have boosted the efficiency of neural machine translation through parallelized decoding at the cost of effectiveness when comparing with the autoregressive counterparts. In this paper, we claim that the…
We study the utility of the lexical translation model (IBM Model 1) for English text retrieval, in particular, its neural variants that are trained end-to-end. We use the neural Model1 as an aggregator layer applied to context-free or…
In this work, we address the problem to model all the nodes (words or phrases) in a dependency tree with the dense representations. We propose a recursive convolutional neural network (RCNN) architecture to capture syntactic and…
Machine Translation is one of the essential tasks in Natural Language Processing (NLP), which has massive applications in real life as well as contributing to other tasks in the NLP research community. Recently, Transformer -based methods…
We investigate the effective memory depth of RNN models by using them for $n$-gram language model (LM) smoothing. Experiments on a small corpus (UPenn Treebank, one million words of training data and 10k vocabulary) have found the LSTM cell…
We present a probabilistic framework for multilingual neural machine translation that encompasses supervised and unsupervised setups, focusing on unsupervised translation. In addition to studying the vanilla case where there is only…
Reference-free evaluation has the potential to make machine translation evaluation substantially more scalable, allowing us to pivot easily to new languages or domains. It has been recently shown that the probabilities given by a large,…
We report our ongoing work about a new deep architecture working in tandem with a statistical test procedure for jointly training texts and their label descriptions for multi-label and multi-class classification tasks. A statistical…
This paper describes our submission to the First Workshop on Reordering for Statistical Machine Translation. We have decided to build a reordering system based on tree-to-string model, using only publicly available tools to accomplish this…