Related papers: Semi Supervised Preposition-Sense Disambiguation u…
Unsupervised learning of cross-lingual word embedding offers elegant matching of words across languages, but has fundamental limitations in translating sentences. In this paper, we propose simple yet effective methods to improve…
We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. As opposed to unsupervised initialisation followed by…
Unsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through semi-supervised learning. To obtain additional data for a…
Semi-supervised learning deals with the problem of how, if possible, to take advantage of a huge amount of unclassified data, to perform a classification in situations when, typically, there is little labeled data. Even though this is not…
Lexical ambiguity is a significant and pervasive challenge in Neural Machine Translation (NMT), with many state-of-the-art (SOTA) NMT systems struggling to handle polysemous words (Campolungo et al., 2022). The same holds for the NMT…
Large sense-annotated datasets are increasingly necessary for training deep supervised systems in Word Sense Disambiguation. However, gathering high-quality sense-annotated data for as many instances as possible is a laborious and expensive…
In this paper, we present a novel cross-consistency based semi-supervised approach for semantic segmentation. Consistency training has proven to be a powerful semi-supervised learning framework for leveraging unlabeled data under the…
A significant roadblock in multilingual neural language modeling is the lack of labeled non-English data. One potential method for overcoming this issue is learning cross-lingual text representations that can be used to transfer the…
Labeled sequence transduction is a task of transforming one sequence into another sequence that satisfies desiderata specified by a set of labels. In this paper we propose multi-space variational encoder-decoders, a new model for labeled…
Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however not been so…
Word sense disambiguation (WSD) methods identify the most suitable meaning of a word with respect to the usage of that word in a specific context. Neural network-based WSD approaches rely on a sense-annotated corpus since they do not…
The lack of labeled data is a common challenge in speech classification tasks, particularly those requiring extensive subjective assessment, such as cognitive state classification. In this work, we propose a Semi-Supervised Learning (SSL)…
Sentence embeddings are an important component of many natural language processing (NLP) systems. Like word embeddings, sentence embeddings are typically learned on large text corpora and then transferred to various downstream tasks, such…
Cross-lingual word embeddings aim to bridge the gap between high-resource and low-resource languages by allowing to learn multilingual word representations even without using any direct bilingual signal. The lion's share of the methods are…
Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…
Pretrained multilingual language models (LMs) can be successfully transformed into multilingual sentence encoders (SEs; e.g., LaBSE, xMPNet) via additional fine-tuning or model distillation with parallel data. However, it remains unclear…
Recent work in cross-lingual contextual word embedding learning cannot handle multi-sense words well. In this work, we explore the characteristics of contextual word embeddings and show the link between contextual word embeddings and word…
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…
In this paper, we present our overall efforts to improve the performance of a code-switching speech recognition system using semi-supervised training methods from lexicon learning to acoustic modeling, on the South East Asian…
The ability to learn from large unlabeled corpora has allowed neural language models to advance the frontier in natural language understanding. However, existing self-supervision techniques operate at the word form level, which serves as a…