Related papers: SentenceMIM: A Latent Variable Language Model
This paper proposes the continuous semantic topic embedding model (CSTEM) which finds latent topic variables in documents using continuous semantic distance function between the topics and the words by means of the variational…
The prevalence of memes on social media has created the need to sentiment analyze their underlying meanings for censoring harmful content. Meme censoring systems by machine learning raise the need for a semi-supervised learning solution to…
Neural language models (LM) trained on diverse corpora are known to work well on previously seen entities, however, updating these models with dynamically changing entities such as place names, song titles and shopping items requires…
Probabilistic Latent Semantic Analysis is a novel statistical technique for the analysis of two-mode and co-occurrence data, which has applications in information retrieval and filtering, natural language processing, machine learning from…
Recent advances in large language models (LLMs) have revolutionized natural language processing, yet evaluating their intrinsic linguistic understanding remains challenging. Moving beyond specialized evaluation tasks, we propose an…
Recent work on generative modeling of text has found that variational auto-encoders (VAE) incorporating LSTM decoders perform worse than simpler LSTM language models (Bowman et al., 2015). This negative result is so far poorly understood,…
Learning semantically meaningful sentence embeddings is an open problem in natural language processing. In this work, we propose a sentence embedding learning approach that exploits both visual and textual information via a multimodal…
Machine learning and especially deep learning have garneredtremendous popularity in recent years due to their increased performanceover other methods. The availability of large amount of data has aidedin the progress of deep learning.…
Effective image and sentence matching depends on how to well measure their global visual-semantic similarity. Based on the observation that such a global similarity arises from a complex aggregation of multiple local similarities between…
Complex dialogue mappings (CDM), including one-to-many and many-to-one mappings, tend to make dialogue models generate incoherent or dull responses, and modeling these mappings remains a huge challenge for neural dialogue systems. To…
Language is typically modelled with discrete sequences. However, the most successful approaches to language modelling, namely neural networks, are continuous and smooth function approximators. In this work, we show that Transformer-based…
Long-term memory is increasingly important for personalized AI agents, yet existing benchmarks and methods remain largely text-centric. Even when images are included, the user-specific information needed for later questions is typically…
Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In this work, we extend the application of…
Masked Image Modeling (MIM) has emerged as a promising method for deriving visual representations from unlabeled image data by predicting missing pixels from masked portions of images. It excels in region-aware learning and provides strong…
The achievements of Large Language Models in Natural Language Processing, especially for high-resource languages, call for a better understanding of their characteristics from a cognitive perspective. Researchers have attempted to evaluate…
Although Transformers with fully connected self-attentions are powerful to model long-term dependencies, they are struggling to scale to long texts with thousands of words in language modeling. One of the solutions is to equip the model…
Understanding a long document requires tracking how entities are introduced and evolve over time. We present a new type of language model, EntityNLM, that can explicitly model entities, dynamically update their representations, and…
One of the principal objectives of Natural Language Processing (NLP) is to generate meaningful representations from text. Improving the informativeness of the representations has led to a tremendous rise in the dimensionality and the memory…
Attention mechanism has been proven effective on natural language processing. This paper proposes an attention boosted natural language inference model named aESIM by adding word attention and adaptive direction-oriented attention…
Conventional mechanical design follows an iterative process in which initial concepts are refined through cycles of expert assessment and resource-intensive Finite Element Method (FEM) analysis to meet performance goals. While machine…