Related papers: Cell-aware Stacked LSTMs for Modeling Sentences

Unlike human reasoning in abstract conceptual spaces, large language models (LLMs) typically reason by generating discrete tokens, which potentially limit their expressive power. The recent work Soft Thinking has shown that LLMs' latent…

Lipreading, i.e. speech recognition from visual-only recordings of a speaker's face, can be achieved with a processing pipeline based solely on neural networks, yielding significantly better accuracy than conventional methods. Feed-forward…

As deep neural networks continue to revolutionize various application domains, there is increasing interest in making these powerful models more understandable and interpretable, and narrowing down the causes of good and bad predictions. We…

The Extended Long Short-Term Memory (xLSTM) network has demonstrated strong capability in modeling complex long-term dependencies in time series data. Despite its success, the deterministic architecture of xLSTM limits its representational…

Speech intelligibility can be degraded due to multiple factors, such as noisy environments, technical difficulties or biological conditions. This work is focused on the development of an automatic non-intrusive system for predicting the…

Gating is a key technique used for integrating information from multiple sources by long short-term memory (LSTM) models and has recently also been applied to other models such as the highway network. Although gating is powerful, it is…

Language models based on deep neural networks and traditional stochastic modelling have become both highly functional and effective in recent times. In this work, a general survey into the two types of language modelling is conducted. We…

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion,…

We propose an end-to-end approach for phrase grounding in images. Unlike prior methods that typically attempt to ground each phrase independently by building an image-text embedding, our architecture formulates grounding of multiple phrases…

Long short-term memory (LSTM) is a robust recurrent neural network architecture for learning spatiotemporal sequential data. However, it requires significant computational power for learning and implementing from both software and hardware…

A cache-inspired approach is proposed for neural language models (LMs) to improve long-range dependency and better predict rare words from long contexts. This approach is a simpler alternative to attention-based pointer mechanism that…

Latent reasoning offers a computation-efficient alternative to Chain-of-Thought but often suffers from performance degradation due to distributional misalignment and ambiguous chain definitions. Ideally, latent reasoning should function as…

The standard LSTM, although it succeeds in the modeling long-range dependences, suffers from a highly complex structure that can be simplified through modifications to its gate units. This paper was to perform an empirical comparison…

The Sentence-State LSTM (S-LSTM) is a powerful and high efficient graph recurrent network, which views words as nodes and performs layer-wise recurrent steps between them simultaneously. Despite its successes on text representations, the…

We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentences into blocks of increasing complexity. Our Structure…

As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and…

Neural word segmentation has attracted more and more research interests for its ability to alleviate the effort of feature engineering and utilize the external resource by the pre-trained character or word embeddings. In this paper, we…

This work presents an end-to-end trainable deep bidirectional LSTM (Long-Short Term Memory) model for image captioning. Our model builds on a deep convolutional neural network (CNN) and two separate LSTM networks. It is capable of learning…

In this paper, a novel architecture for a deep recurrent neural network, residual LSTM is introduced. A plain LSTM has an internal memory cell that can learn long term dependencies of sequential data. It also provides a temporal shortcut…

Matching pedestrians across multiple camera views known as human re-identification (re-identification) is a challenging problem in visual surveillance. In the existing works concentrating on feature extraction, representations are formed…