Related papers: Automatic Translating between Ancient Chinese and …
Developing parallel corpora is an important and a difficult activity for Machine Translation. This requires manual annotation by Human Translators. Translating same text again is a useless activity. There are tools available to implement…
To understand the algorithm that supports the human brain's language representation, previous research has attempted to predict neural responses to linguistic stimuli using embeddings generated by artificial neural networks (ANNs), a…
Chinese short text matching is a fundamental task in natural language processing. Existing approaches usually take Chinese characters or words as input tokens. They have two limitations: 1) Some Chinese words are polysemous, and semantic…
Chinese text segmentation is a well-known and difficult problem. On one side, there is not a simple notion of "word" in Chinese language making really hard to implement rule-based systems to segment written texts, thus lexicons and…
Unsupervised neural machine translation (NMT) is a recently proposed approach for machine translation which aims to train the model without using any labeled data. The models proposed for unsupervised NMT often use only one shared encoder…
Sentence embeddings are commonly used in text clustering and semantic retrieval tasks. State-of-the-art sentence representation methods are based on artificial neural networks fine-tuned on large collections of manually labeled sentence…
Large language models are typically trained densely: all parameters are updated with respect to all inputs. This requires synchronization of billions of parameters across thousands of GPUs. We introduce a simple but effective method to…
Word alignment, which aims to align translationally equivalent words between source and target sentences, plays an important role in many natural language processing tasks. Current unsupervised neural alignment methods focus on inducing…
In this paper, we present an approach to improve the accuracy of a strong transition-based dependency parser by exploiting dependency language models that are extracted from a large parsed corpus. We integrated a small number of features…
Recent progress in task-oriented neural dialogue systems is largely focused on a handful of languages, as annotation of training data is tedious and expensive. Machine translation has been used to make systems multilingual, but this can…
Deep Neural Networks (DNNs) have provably enhanced the state-of-the-art Neural Machine Translation (NMT) with their capability in modeling complex functions and capturing complex linguistic structures. However NMT systems with deep…
Cross-lingual entity alignment is the task of finding the same semantic entities from different language knowledge graphs. In this paper, we propose a simple and novel unsupervised method for cross-language entity alignment. We utilize the…
Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a…
Unsupervised on-the-fly back-translation, in conjunction with multilingual pretraining, is the dominant method for unsupervised neural machine translation. Theoretically, however, the method should not work in general. We therefore conduct…
Multilingual sentence representations pose a great advantage for low-resource languages that do not have enough data to build monolingual models on their own. These multilingual sentence representations have been separately exploited by few…
Neural models with minimal feature engineering have achieved competitive performance against traditional methods for the task of Chinese word segmentation. However, both training and working procedures of the current neural models are…
Unsupervised neural machine translation (UNMT) requires only monolingual data of similar language pairs during training and can produce bi-directional translation models with relatively good performance on alphabetic languages (Lample et…
Resources for the non-English languages are scarce and this paper addresses this problem in the context of machine translation, by automatically extracting parallel sentence pairs from the multilingual articles available on the Internet. In…
Word alignments identify translational correspondences between words in a parallel sentence pair and is used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems , or to perform quality…
Despite the growing variety of languages supported by existing multilingual neural machine translation (MNMT) models, most of the world's languages are still being left behind. We aim to extend large-scale MNMT models to incorporate a new…