Related papers: CTCBERT: Advancing Hidden-unit BERT with CTC Objec…

Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from…

Continual learning (CL) learns a sequence of tasks incrementally with the goal of achieving two main objectives: overcoming catastrophic forgetting (CF) and encouraging knowledge transfer (KT) across tasks. However, most existing techniques…

Named entity recognition (NER) is frequently addressed as a sequence classification task where each input consists of one sentence of text. It is nevertheless clear that useful information for the task can often be found outside of the…

State-of-the-art federated learning methods can perform far worse than their centralized counterparts when clients have dissimilar data distributions. For neural networks, even when centralized SGD easily finds a solution that is…

This study (The work was accomplished during the internship in Tencent AI lab) addresses semi-supervised acoustic modeling, i.e. attaining high-level representations from unsupervised audio data and fine-tuning the parameters of pre-trained…

BERT, which stands for Bidirectional Encoder Representations from Transformers, is a recently introduced language representation model based upon the transfer learning paradigm. We extend its fine-tuning procedure to address one of its…

Bidirectional Encoder Representations from Transformers or BERT~\cite{devlin-etal-2019-bert} has been one of the base models for various NLP tasks due to its remarkable performance. Variants customized for different languages and tasks are…

Multilingual BERT (mBERT), XLM-RoBERTa (XLMR) and other unsupervised multilingual encoders can effectively learn cross-lingual representation. Explicit alignment objectives based on bitexts like Europarl or MultiUN have been shown to…

In this study, we propose advancing all-neural speech recognition by directly incorporating attention modeling within the Connectionist Temporal Classification (CTC) framework. In particular, we derive new context vectors using time…

We present a novel approach to end-to-end automatic speech recognition (ASR) that utilizes pre-trained masked language models (LMs) to facilitate the extraction of linguistic information. The proposed models, BERT-CTC and BECTRA, are…

This paper achieves state of the art results for the ICD code prediction task using the MIMIC-III dataset. This was achieved through the use of Clinical BERT (Alsentzer et al., 2019). embeddings and text augmentation and label balancing to…

In this work, we are dedicated to leveraging the BERT pre-training success and modeling the domain-specific statistics to fertilize the sign language recognition~(SLR) model. Considering the dominance of hand and body in sign language…

The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters. To improve the decoding…

Speech emotion recognition (SER) systems aim to recognize human emotional state during human-computer interaction. Most existing SER systems are trained based on utterance-level labels. However, not all frames in an audio have affective…

Recent state-of-the-art language models utilize a two-phase training procedure comprised of (i) unsupervised pre-training on unlabeled text, and (ii) fine-tuning for a specific supervised task. More recently, many studies have been focused…

Though the community has made great progress on Machine Reading Comprehension (MRC) task, most of the previous works are solving English-based MRC problems, and there are few efforts on other languages mainly due to the lack of large-scale…

Pre-training large-scale neural language models on raw texts has made a significant contribution to improving transfer learning in natural language processing (NLP). With the introduction of transformer-based language models, such as…

Face recognition models trained under the assumption of identical training and test distributions often suffer from poor generalization when faced with unknown variations, such as a novel ethnicity or unpredictable individual make-ups…

Ensembling BERT models often significantly improves accuracy, but at the cost of significantly more computation and memory footprint. In this work, we propose Multi-CLS BERT, a novel ensembling method for CLS-based prediction tasks that is…

Transformers have shown remarkable performance in 3D medical image segmentation, but their high computational requirements and need for large amounts of labeled data limit their applicability. To address these challenges, we consider two…