Related papers: Better Document-Level Machine Translation with Bay…
The scarcity of large parallel corpora is an important obstacle for neural machine translation. A common solution is to exploit the knowledge of language models (LM) trained on abundant monolingual data. In this work, we propose a novel…
Our ability to efficiently and accurately evaluate the quality of machine translation systems has been outrun by the effectiveness of current language models--which limits the potential for further improving these models on more challenging…
Search has been proposed as an effective method for self-improving language models and agentic systems, both for post-training sample generation and for inference. However, widely used methods such as best-of-N sampling and tree search face…
A sentence can be translated into more than one correct sentences. However, most of the existing neural machine translation models only use one of the correct translations as the targets, and the other correct sentences are punished as the…
Knowing which words have been attended to in previous time steps while generating a translation is a rich source of information for predicting what words will be attended to in the future. We improve upon the attention model of Bahdanau et…
This work compares concept models for cross-language retrieval: First, we adapt probabilistic Latent Semantic Analysis (pLSA) for multilingual documents. Experiments with different weighting schemes show that a weighting method favoring…
Unsupervised word translation from non-parallel inter-lingual corpora has attracted much research interest. Very recently, neural network methods trained with adversarial loss functions achieved high accuracy on this task. Despite the…
Although the parallel corpus has an irreplaceable role in machine translation, its scale and coverage is still beyond the actual needs. Non-parallel corpus resources on the web have an inestimable potential value in machine translation and…
Word2vec (Mikolov et al., 2013) has proven to be successful in natural language processing by capturing the semantic relationships between different words. Built on top of single-word embeddings, paragraph vectors (Le and Mikolov, 2014)…
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…
Many multilingual NLP applications need to translate words between different languages, but cannot afford the computational expense of inducing or applying a full translation model. For these applications, we have designed a fast algorithm…
When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic…
Texts and their translations are a rich linguistic resource that can be used to train and test statistics-based Machine Translation systems and many other applications. In this paper, we present a working system that can identify…
The basic concept in Neural Machine Translation (NMT) is to train a large Neural Network that maximizes the translation performance on a given parallel corpus. NMT is then using a simple left-to-right beam-search decoder to generate new…
Back-translation (BT) has become one of the de facto components in unsupervised neural machine translation (UNMT), and it explicitly makes UNMT have translation ability. However, all the pseudo bi-texts generated by BT are treated equally…
Beam search is universally used in full-sentence translation but its application to simultaneous translation remains non-trivial, where output words are committed on the fly. In particular, the recently proposed wait-k policy (Ma et al.,…
One of the things that need to change when it comes to machine translation is the models' ability to translate code-switching content, especially with the rise of social media and user-generated content. In this paper, we are proposing a…
Non-autoregressive translation (NAT) models achieve comparable performance and superior speed compared to auto-regressive translation (AT) models in the context of sentence-level machine translation (MT). However, their abilities are…
We present the task of PreQuEL, Pre-(Quality-Estimation) Learning. A PreQuEL system predicts how well a given sentence will be translated, without recourse to the actual translation, thus eschewing unnecessary resource allocation when…
Sequence-to-sequence neural translation models learn semantic and syntactic relations between sentence pairs by optimizing the likelihood of the target given the source, i.e., $p(y|x)$, an objective that ignores other potentially useful…