相关论文: IDEA: Interactive DoublE Attentions from Label Emb…

While paragraph embedding models are remarkably effective for downstream classification tasks, what they learn and encode into a single vector remains opaque. In this paper, we investigate a state-of-the-art paragraph embedding method…

Achieving more powerful semantic representations and semantic understanding is one of the key problems in improving the performance of semantic communication systems. This work focuses on enhancing the semantic understanding of the text…

Creating meta-embeddings for better performance in language modelling has received attention lately, and methods based on concatenation or merely calculating the arithmetic mean of more than one separately trained embeddings to perform…

Instruction data is crucial for improving the capability of Large Language Models (LLMs) to align with human-level performance. Recent research LIMA demonstrates that alignment is essentially a process where the model adapts instructions'…

Language models that utilize extensive self-supervised pre-training from unlabeled text, have recently shown to significantly advance the state-of-the-art performance in a variety of language understanding tasks. However, it is yet unclear…

Multi-modal object Re-IDentification (ReID) aims to retrieve specific objects by utilizing complementary information from various modalities. However, existing methods focus on fusing heterogeneous visual features, neglecting the potential…

Embeddings, which compress information in raw text into semantics-preserving low-dimensional vectors, have been widely adopted for their efficacy. However, recent research has shown that embeddings can potentially leak private information…

Idiomatic expressions can be problematic for natural language processing applications as their meaning cannot be inferred from their constituting words. A lack of successful methodological approaches and sufficiently large datasets prevents…

This paper analyzes the impact of causal manner in the text encoder of text-to-image (T2I) diffusion models, which can lead to information bias and loss. Previous works have focused on addressing the issues through the denoising process.…

Entity Linking has two main open areas of research: 1) generate candidate entities without using alias tables and 2) generate more contextual representations for both mentions and entities. Recently, a solution has been proposed for the…

In real-world applications, as data availability increases, obtaining labeled data for machine learning (ML) projects remains challenging due to the high costs and intensive efforts required for data annotation. Many ML projects,…

CNNs, RNNs, GCNs, and CapsNets have shown significant insights in representation learning and are widely used in various text mining tasks such as large-scale multi-label text classification. However, most existing deep models for…

Traditional binary hard labels for sound event detection (SED) lack details about the complexity and variability of sound event distributions. Recently, a novel annotation workflow is proposed to generate fine-grained non-binary soft…

Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific…

Textual network embedding leverages rich text information associated with the network to learn low-dimensional vectorial representations of vertices. Rather than using typical natural language processing (NLP) approaches, recent research…

In addition to the unprecedented ability in imaginary creation, large text-to-image models are expected to take customized concepts in image generation. Existing works generally learn such concepts in an optimization-based manner, yet…

Neural network methods have achieved great success in reviews sentiment classification. Recently, some works achieved improvement by incorporating user and product information to generate a review representation. However, in reviews, we…

Research in emotion analysis is scattered across different label formats (e.g., polarity types, basic emotion categories, and affective dimensions), linguistic levels (word vs. sentence vs. discourse), and, of course, (few well-resourced…

Table entailment, the binary classification task of finding if a sentence is supported or refuted by the content of a table, requires parsing language and table structure as well as numerical and discrete reasoning. While there is extensive…

Can attention- or gradient-based visualization techniques be used to infer token-level labels for binary sequence tagging problems, using networks trained only on sentence-level labels? We construct a neural network architecture based on…