Neural machine translation (NMT) has achieved great success due to the ability to generate high-quality sentences.
We study the problem of online learning with human feedback in the human-in-the-loop machine translation, in which the human translators revise the machine-generated translations and then the corrected translations are used to improve the neural machine translation (NMT) system.
Recently, $k$NN-MT has shown the promising capability of directly incorporating the pre-trained neural machine translation (NMT) model with domain-specific token-level $k$-nearest-neighbor ($k$NN) retrieval to achieve domain adaptation without retraining.
However, it usually suffers from capturing spurious correlations between the output language and language invariant semantics due to the maximum likelihood training objective, leading to poor transfer performance on zero-shot translation.
In this paper, we propose to formulate the task-oriented dialogue system as the purely natural language generation task, so as to fully leverage the large-scale pre-trained models like GPT-2 and simplify complicated delexicalization prepossessing.
To this end, we propose two pre-training tasks.
A well-known limitation in pretrain-finetune paradigm lies in its inflexibility caused by the one-size-fits-all vocabulary.
Furthermore, we contribute the first Chinese-English parallel corpus annotated with user behavior called UDT-Corpus.
Bilingual Lexicon Induction (BLI) aims to map words in one language to their translations in another, and is typically through learning linear projections to align monolingual word representation spaces.
Document machine translation aims to translate the source sentence into the target language in the presence of additional contextual information.
However, study shows that when we further enlarge the translation unit to a whole document, supervised training of Transformer can fail.
On four benchmark machine translation datasets, we demonstrate that the proposed method is able to effectively filter out the noises in retrieval results and significantly outperforms the vanilla kNN-MT model.
In this way, our approach is able to more comprehensively find adversarial examples around the decision boundary and effectively conduct adversarial attacks.
Bilingual terminologies are important resources for natural language processing (NLP) applications.
Moreover, compared with autoregressive models, HRT can be steadily accelerated 1. 5 times regardless of batch size and device.
Existing ways either employ extra encoder to encode information from TM or concatenate source sentence and TM sentences as encoder's input.
Query translation (QT) serves as a critical factor in successful cross-lingual information retrieval (CLIR).
Multi-Domain Neural Machine Translation (NMT) aims at building a single system that performs well on a range of target domains.
Query translation (QT) is a key component in cross-lingual information retrieval system (CLIR).
As a crucial role in cross-language information retrieval (CLIR), query translation has three main challenges: 1) the adequacy of translation; 2) the lack of in-domain parallel training data; and 3) the requisite of low latency.
As a sequence-to-sequence generation task, neural machine translation (NMT) naturally contains intrinsic uncertainty, where a single sentence in one language has multiple valid counterparts in the other.
In this paper, we focus on the domain-specific translation with low resources, where in-domain parallel corpora are scarce or nonexistent.
Recent studies have demonstrated the overwhelming advantage of cross-lingual pre-trained models (PTMs), such as multilingual BERT and XLM, on cross-lingual NLP tasks.
In this paper, we propose a new task of machine translation (MT), which is based on no parallel sentences but can refer to a ground-truth bilingual dictionary.
However, the traditional multilingual model fails to capture the diversity and specificity of different languages, resulting in inferior performance compared with individual models that are sufficiently trained.
Recent evidence reveals that Neural Machine Translation (NMT) models with deeper neural networks can be more effective but are difficult to train.
Compared with only using limited authentic parallel data as training corpus, many studies have proved that incorporating synthetic parallel data, which generated by back translation (BT) or forward translation (FT, or selftraining), into the NMT training process can significantly improve translation quality.
The encoder maps the words in the input sentence into a sequence of hidden states, which are then fed into the decoder to generate the output sentence.
The standard paradigm of exploiting them includes two steps: first, pre-training a model, e. g. BERT, with a large scale unlabeled monolingual data.
However, existing transfer methods involving a common target language are far from success in the extreme scenario of zero-shot translation, due to the language space mismatch problem between transferor (the parent model) and transferee (the child model) on the source side.
We propose a contrastive attention mechanism to extend the sequence-to-sequence framework for abstractive sentence summarization task, which aims to generate a brief summary of a given source sentence.
Then, we design a framework for integrating both source and target sentence-level representations into NMT model to improve the translation quality.
But there is no cross-lingual parallel corpus, whose source sentence language is different to the summary language, to directly train a cross-lingual ASSUM system.
Neural machine translation (NMT) suffers a performance deficiency when a limited vocabulary fails to cover the source or target side adequately, which happens frequently when dealing with morphologically rich languages.
Sentences in a well-formed text are connected to each other via various links to form the cohesive structure of the text.
In neural machine translation, a source sequence of words is encoded into a vector from which a target sequence is generated in the decoding phase.