Related papers: Hyperbolic Representation Learning for Fast and Ef…

State of the art algorithms for many pattern recognition problems rely on deep network models. Training these models requires a large labeled dataset and considerable computational resources. Also, it is difficult to understand the working…

Finding a low dimensional representation of hierarchical, structured data described by a network remains a challenging problem in the machine learning community. An emerging approach is embedding these networks into hyperbolic space because…

Vector retrieval systems exhibit significant performance variance across queries due to heterogeneous embedding quality. We propose a lightweight framework for predicting retrieval performance at the query level by combining quantization…

A major challenge to the problem of community question answering is the lexical and semantic gap between the sentence representations. Some solutions to minimize this gap includes the introduction of extra parameters to deep models or…

State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking. To this end, models generally utilize an encoder-only (like BERT) paradigm or an encoder-decoder (like T5) approach. These paradigms,…

What does it take to design a machine that learns to answer natural questions about a video? A Video QA system must simultaneously understand language, represent visual content over space-time, and iteratively transform these…

In multimodal machine learning tasks, it is due to the complexity of the assignments that the network structure, in most cases, is assembled in a sophisticated way. The holistic architecture can be separated into several logical parts…

An effective paradigm for building Automated Question Answering systems is the re-use of previously answered questions, e.g., for FAQs or forum applications. Given a database (DB) of question/answer (q/a) pairs, it is possible to answer a…

Transformative innovations in model architectures have introduced hierarchical embedding augmentation as a means to redefine the representation of tokens through multi-level semantic structures, offering enhanced adaptability to complex…

Dual-encoder-based dense retrieval models have become the standard in IR. They employ large Transformer-based language models, which are notoriously inefficient in terms of resources and latency. We propose Fast-Forward indexes -- vector…

Transformer model architectures have become an indispensable staple in deep learning lately for their effectiveness across a range of tasks. Recently, a surge of "X-former" models have been proposed which improve upon the original…

We introduce adaptive input representations for neural language modeling which extend the adaptive softmax of Grave et al. (2017) to input representations of variable capacity. There are several choices on how to factorize the input and…

We present a framework for question answering that can efficiently scale to longer documents while maintaining or even improving performance of state-of-the-art models. While most successful approaches for reading comprehension rely on…

Deep learning has become the dominant approach for creating high capacity, scalable models across diverse data modalities. However, because these models rely on a large number of learned parameters, tightly couple feature extraction with…

In this paper we explore deep learning models with memory component or attention mechanism for question answering task. We combine and compare three models, Neural Machine Translation, Neural Turing Machine, and Memory Networks for a…

Complex Query Answering (CQA) is a fundamental knowledge representation and reasoning task over incomplete knowledge graphs (KGs). Answering existential first-order queries with $k$ free variables (i.e., $\text{EFO}_k$ queries) is a crucial…

Hardware-Software Co-Design is a highly successful strategy for improving performance of domain-specific computing systems. We argue for the application of the same methodology to deep learning; specifically, we propose to extend neural…

Various neuroimaging studies suffer from small sample size problem which often limit their reliability. Meta-analysis addresses this challenge by aggregating findings from different studies to identify consistent patterns of brain activity.…

Neural network based approaches for sentence relation modeling automatically generate hidden matching features from raw sentence pairs. However, the quality of matching feature representation may not be satisfied due to complex semantic…

Our work aimed at experimentally assessing the benefits of model ensembling within the context of neural methods for passage reranking. Starting from relatively standard neural models, we use a previous technique named Fast Geometric…