相关论文: Cross-Lingual Transfer Learning for Statistical Ty…

While unsupervised domain adaptation methods based on deep architectures have achieved remarkable success in many computer vision tasks, they rely on a strong assumption, i.e. labeled source data must be available. In this work we overcome…

With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…

We develop here a novel transfer learning methodology called Profiled Transfer Learning (PTL). The method is based on the \textit{approximate-linear} assumption between the source and target parameters. Compared with the commonly assumed…

Cross-lingual consistency should be considered to assess cross-lingual transferability, maintain the factuality of the model knowledge across languages, and preserve the parity of language model performance. We are thus interested in…

Multi-task learning shares information between related tasks, sometimes reducing the number of parameters required. State-of-the-art results across multiple natural language understanding tasks in the GLUE benchmark have previously used…

Code-switching is a data augmentation scheme mixing words from multiple languages into source lingual text. It has achieved considerable generalization performance of cross-lingual transfer tasks by aligning cross-lingual contextual word…

Pretrained contextualized representations offer great success for many downstream tasks, including document ranking. The multilingual versions of such pretrained representations provide a possibility of jointly learning many languages with…

Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success…

We propose transfer learning as a method for analyzing the encoding of grammatical structure in neural language models. We train LSTMs on non-linguistic data and evaluate their performance on natural language to assess which kinds of data…

Transfer learning, also referred as knowledge transfer, aims at reusing knowledge from a source dataset to a similar target one. While many empirical studies illustrate the benefits of transfer learning, few theoretical results are…

This paper addresses the problem of transferring useful knowledge from a source network to predict node labels in a newly formed target network. While existing transfer learning research has primarily focused on vector-based data, in which…

End-to-end spoken language understanding (SLU) systems benefit from pretraining on large corpora, followed by fine-tuning on application-specific data. The resulting models are too large for on-edge applications. For instance, BERT-based…

Pretraining has become a standard technique in computer vision and natural language processing, which usually helps to improve performance substantially. Previously, the most dominant pretraining method is transfer learning (TL), which uses…

Cybersecurity has become a primary global concern with the rapid increase in security attacks and data breaches. Artificial intelligence is promising to help humans analyzing and identifying attacks. However, labeling millions of packets…

Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We…

Different languages have distinct phonetic systems and vary in their prosodic features making it challenging to develop a Text-to-Speech (TTS) model that can effectively synthesise speech in multilingual settings. Furthermore, TTS…

Morphological analysis involves predicting the syntactic traits of a word (e.g. {POS: Noun, Case: Acc, Gender: Fem}). Previous work in morphological tagging improves performance for low-resource languages (LRLs) through cross-lingual…

Zero-shot cross-lingual knowledge transfer enables the multilingual pretrained language model (mPLM), finetuned on a task in one language, make predictions for this task in other languages. While being broadly studied for natural language…

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

Cross-modal data matching refers to retrieval of data from one modality, when given a query from another modality. In general, supervised algorithms achieve better retrieval performance compared to their unsupervised counterpart, as they…