Related papers: Compass-Embedding v4: Robust Contrastive Learning …

Self-supervised learning (SSL) has revolutionized representation learning, with Joint-Embedding Architectures (JEAs) emerging as an effective approach for capturing semantic features. Existing JEAs rely on implicit or explicit batch…

Large language models (LLMs) have recently demonstrated excellent performance in text embedding tasks. Previous work usually use LoRA to fine-tune existing LLMs, which are limited by the data and training gap between LLMs and embedding…

Multimodal aspect-based sentiment analysis(MABSA) seeks to identify aspect terms within paired image-text data and determine their fine grained sentiment polarities, representing a fundamental task for improving the effectiveness of…

Cross-lingual embeddings aim to represent words in multiple languages in a shared vector space by capturing semantic similarities across languages. They are a crucial component for scaling tasks to multiple languages by transferring…

This paper describes one objective function for learning semantically coherent feature embeddings in multi-output classification problems, i.e., when the response variables have dimension higher than one. In particular, we consider the…

Learning multi-label image recognition with incomplete annotation is gaining popularity due to its superior performance and significant labor savings when compared to training with fully labeled datasets. Existing literature mainly focuses…

Aligning multilingual assistants with culturally grounded user preferences is essential for serving India's linguistically diverse population of over one billion speakers across multiple scripts. However, existing benchmarks either focus on…

Visual-Semantic Embedding (VSE) aims to learn an embedding space where related visual and semantic instances are close to each other. Recent VSE models tend to design complex structures to pool visual and semantic features into fixed-length…

Cross-lingual word embeddings are vector representations of words in different languages where words with similar meaning are represented by similar vectors, regardless of the language. Recent developments which construct these embeddings…

While speech emotion recognition (SER) research has made significant progress, achieving generalization across various corpora continues to pose a problem. We propose a novel domain adaptation technique that embodies a multitask framework…

Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative image-text pairs, the capability of constrastive learning…

The increasing level of sound pollution in marine environments poses an increased threat to ocean health, making it crucial to monitor underwater noise. By monitoring this noise, the sources responsible for this pollution can be mapped.…

Existing multilingual machine translation approaches mainly focus on English-centric directions, while the non-English directions still lag behind. In this work, we aim to build a many-to-many translation system with an emphasis on the…

Multilingual pretraining typically lacks explicit alignment signals, leading to suboptimal cross-lingual alignment in the representation space. In this work, we show that training standard pretrained models for cross-lingual alignment with…

Deep learning models tend to memorize training data, which hurts their ability to generalize to under-represented classes. We empirically study a convolutional neural network's internal representation of imbalanced image data and measure…

We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. The advantage of using entity supervision is twofold: (1) entities have been shown to be a strong…

Representation learning is a fundamental building block for analyzing entities in a database. While the existing embedding learning methods are effective in various data mining problems, their applicability is often limited because these…

Achieving artificially intelligent-native wireless networks is necessary for the operation of future 6G applications such as the metaverse. Nonetheless, current communication schemes are, at heart, a mere reconstruction process that lacks…

State-of-the-art model for zero-shot cross-lingual spoken language understanding performs cross-lingual unsupervised contrastive learning to achieve the label-agnostic semantic alignment between each utterance and its code-switched data.…

As global e-commerce platforms continue to expand, companies are entering new markets where they encounter cold-start challenges due to limited human labels and user behaviors. In this paper, we share our experiences in Coupang to provide a…