Информация о Подсловах
Related Papers
A Systematic Study of Leveraging Subword Information for Learning Word Representations
AbstractThe use of subword-level information (e.g., characters, character n-grams, morphemes) has become ubiquitous in modern word representation learning. Its importance is attested especially for morphologically rich languages which generate a …...
An Effective Approach to Unsupervised Machine Translation
AbstractWhile machine translation has traditionally relied on large amounts of parallel corpora, a recent research line has managed to train both Neural Machine Translation (NMT) and Statistical Machine Translation (SMT) …...
On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages
AbstractRecent work has validated the importance of subword information for word representation learning. Since subwords increase parameter sharing ability in neural models, their value should be even more pronounced in …...
Low-Resource Unsupervised NMT: Diagnosing the Problem and Providing a Linguistically Motivated Solution
AbstractUnsupervised Machine Translation has been advancing our ability to translate without parallel data, but state-of-the-art methods assume an abundance of monolingual data. This paper investigates the scenario where monolingual data …...
Evaluating a Joint Training Approach for Learning Cross-lingual Embeddings with Sub-word Information without Parallel Corpora on Lower-resource Languages
AbstractCross-lingual word embeddings provide a way for information to be transferred between languages. In this paper we evaluate an extension of a joint training approach to learning cross-lingual embeddings that …...
One Size Does Not Fit All: Finding the Optimal Subword Sizes for FastText Models across Languages
AbstractUnsupervised representation learning of words from large multilingual corpora is useful for downstream tasks such as word sense disambiguation, semantic text similarity, and information retrieval. The representation precision of log-bilinear …...
Limitations and Challenges of Unsupervised Cross-lingual Pre-training
AbstractCross-lingual alignment methods for monolingual language representations have received notable attention in recent years. However, their use in machine translation pre-training remains scarce. This work tries to shed light on …...