Related papers: SemBridge: Language Transfer in Sparse Encoders vi…

This paper proposes a technique for adding a new source or target language to an existing multilingual NMT model without re-training it on the initial set of languages. It consists in replacing the shared vocabulary with a small…

Large pretrained multilingual language models (ML-LMs) have shown remarkable capabilities of zero-shot cross-lingual transfer, without direct cross-lingual supervision. While these results are promising, follow-up works found that, within…

Open-vocabulary semantic segmentation is a challenging task, which requires the model to output semantic masks of an image beyond a close-set vocabulary. Although many efforts have been made to utilize powerful CLIP models to accomplish…

Supervised Dictionary Learning has gained much interest in the recent decade and has shown significant performance improvements in image classification. However, in general, supervised learning needs a large number of labelled samples per…

Transformer-based large language models exhibit groundbreaking capabilities, but their storage and computational costs are prohibitively high, limiting their application in resource-constrained scenarios. An effective approach is to…

We introduce an architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in 28 different scripts. Our system uses a single BiLSTM encoder with a shared BPE…

Spoken language understanding is typically based on pipeline architectures including speech recognition and natural language understanding steps. These components are optimized independently to allow usage of available data, but the overall…

We frame the task of predicting a semantic labeling as a sparse reconstruction procedure that applies a target-specific learned transfer function to a generic deep sparse code representation of an image. This strategy partitions training…

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…

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…

Sentence-level embedding is essential for various tasks that require understanding natural language. Many studies have explored such embeddings for high-resource languages like English. However, low-resource languages like Bengali (a…

We provide the first exploration of sentence embeddings from text-to-text transformers (T5). Sentence embeddings are broadly useful for language processing tasks. While T5 achieves impressive performance on language tasks cast as…

As a new communication paradigm, semantic communication has received widespread attention in communication fields. However, since the decoding of semantic signals relies on contextual knowledge, misalignment between the starting position of…

We present LSeg, a novel model for language-driven semantic image segmentation. LSeg uses a text encoder to compute embeddings of descriptive input labels (e.g., "grass" or "building") together with a transformer-based image encoder that…

We introduce SemCSE, an unsupervised method for learning semantic embeddings of scientific texts. Building on recent advances in contrastive learning for text embeddings, our approach leverages LLM-generated summaries of scientific…

We consider a multi-user semantic communications system in which agents (transmitters and receivers) interact through the exchange of semantic messages to convey meanings. In this context, languages are instrumental in structuring the…

Encoder-decoder architectures are widely adopted for medical image segmentation tasks. With the lateral skip connection, the models can obtain and fuse both semantic and resolution information in deep layers to achieve more accurate…

Semantic communication has emerged as a new paradigm to facilitate the performance of integrated sensing and communication systems in 6G. However, most of the existing works mainly focus on sensing data compression to reduce the subsequent…

Machine comprehension(MC) style question answering is a representative problem in natural language processing. Previous methods rarely spend time on the improvement of encoding layer, especially the embedding of syntactic information and…

Visual transfer learning for unseen categories presents an active research topic yet a challenging task, due to the inherent conflict between preserving category-specific representations and acquiring transferable knowledge. Vision-Language…