Related papers: BELT:Bootstrapping Electroencephalography-to-Langu…
Brain extraction is a critical preprocessing step in various neuroimaging studies, particularly enabling accurate separation of brain from non-brain tissue and segmentation of relevant within-brain tissue compartments and structures using…
Recent works have demonstrated that multilingual BERT (mBERT) learns rich cross-lingual representations, that allow for transfer across languages. We study the word-level translation information embedded in mBERT and present two simple…
Speech brain-computer interfaces (BCIs) aim to restore communication for people with paralysis by translating neural activity into text. Most systems use cascaded frameworks that decode phonemes before assembling sentences with an n-gram…
Pretrained generative models have opened new frontiers in brain decoding by enabling the synthesis of realistic texts and images from non-invasive brain recordings. However, the reliability of such outputs remains questionable--whether they…
Cross-lingual entity linking maps an entity mention in a source language to its corresponding entry in a structured knowledge base that is in a different (target) language. While previous work relies heavily on bilingual lexical resources…
Recent major milestones have successfully reconstructed natural language from non-invasive brain signals (e.g. functional Magnetic Resonance Imaging (fMRI) and Electroencephalogram (EEG)) across subjects. However, we find current dataset…
Decoding visual representations from human brain activity has emerged as a thriving research domain, particularly in the context of brain-computer interfaces. Our study presents an innovative method that employs to classify and reconstruct…
Progress in natural language processing (NLP) models that estimate representations of word sequences has recently been leveraged to improve the understanding of language processing in the brain. However, these models have not been…
Zero-shot neural machine translation is an attractive goal because of the high cost of obtaining data and building translation systems for new translation directions. However, previous papers have reported mixed success in zero-shot…
Pretrained language models are long known to be subpar in capturing sentence and document-level semantics. Though heavily investigated, transferring perturbation-based methods from unsupervised visual representation learning to NLP remains…
An important concern in training multilingual neural machine translation (NMT) is to translate between language pairs unseen during training, i.e zero-shot translation. Improving this ability kills two birds with one stone by providing an…
End-to-end Spoken Language Understanding (SLU) is proposed to infer the semantic meaning directly from audio features without intermediate text representation. Although the acoustic model component of an end-to-end SLU system can be…
Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usually suffers from capturing spurious correlations between the…
The brain-computer interface (BCI) establishes a non-muscle channel that enables direct communication between the human body and an external device. Electroencephalography (EEG) is a popular non-invasive technique for recording brain…
We propose procedures for evaluating and strengthening contextual embedding alignment and show that they are useful in analyzing and improving multilingual BERT. In particular, after our proposed alignment procedure, BERT exhibits…
Decoding natural language from non-invasive EEG signals is a promising yet challenging task. However, current state-of-the-art models remain constrained by three fundamental limitations: Semantic Bias (mode collapse into generic templates),…
The field of natural language processing (NLP) has made significant progress with the rapid development of deep learning technologies. One of the research directions in text sentiment analysis is sentiment analysis of medical texts, which…
The recently proposed BERT has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks…
Multi-lingual contextualized embeddings, such as multilingual-BERT (mBERT), have shown success in a variety of zero-shot cross-lingual tasks. However, these models are limited by having inconsistent contextualized representations of…
Pretrained Language Models (PLMs) learn rich cross-lingual knowledge and can be finetuned to perform well on diverse tasks such as translation and multilingual word sense disambiguation (WSD). However, they often struggle at disambiguating…