Related papers: Analysing the potential of seq-to-seq models for i…

While transformer-based Large Language Models (LLMs) theoretically support massive context windows, they suffer from severe performance degradation when processing long numerical sequences. We attribute this failure to the attention…

Recently multimodal transformer models have gained popularity because their performance on language and vision tasks suggest they learn rich visual-linguistic representations. Focusing on zero-shot image retrieval tasks, we study three…

Sequence-to-sequence models have achieved impressive results on various tasks. However, they are unsuitable for tasks that require incremental predictions to be made as more data arrives or tasks that have long input sequences and output…

Natural language processing has greatly benefited from the introduction of the attention mechanism. However, standard attention models are of limited interpretability for tasks that involve a series of inference steps. We describe an…

We compare sequential fine-tuning with a model for multi-task learning in the context where we are interested in boosting performance on two tasks, one of which depends on the other. We test these models on the FigLang2022 shared task which…

Since its introduction, the transformer has shifted the development trajectory away from traditional models (e.g., RNN, MLP) in time series forecasting, which is attributed to its ability to capture global dependencies within temporal…

Transfer learning is an exciting area of Natural Language Processing that has the potential to both improve model performance and increase data efficiency. This study explores the effects of varying quantities of target task training data…

Prior to deep learning the semantic parsing community has been interested in understanding and modeling the range of possible word alignments between natural language sentences and their corresponding meaning representations.…

Text-to-image generation models suffer from alignment problems, where generated images fail to accurately capture the objects and relations in the text prompt. Prior work has focused on improving alignment by refining the diffusion process,…

Data scarcity is a long-standing and crucial challenge that hinders quick development of task-oriented dialogue systems across multiple domains: task-oriented dialogue models are expected to learn grammar, syntax, dialogue reasoning,…

Self-supervised speech representation models, particularly those leveraging transformer architectures, have demonstrated remarkable performance across various tasks such as speech recognition, speaker identification, and emotion detection.…

Learned self-attention functions in state-of-the-art NLP models often correlate with human attention. We investigate whether self-attention in large-scale pre-trained language models is as predictive of human eye fixation patterns during…

We consider problems of making sequences of decisions to accomplish tasks, interacting via the medium of language. These problems are often tackled with reinforcement learning approaches. We find that these models do not generalize well…

This work shows how to improve and interpret the commonly used dual encoder model for response suggestion in dialogue. We present an attentive dual encoder model that includes an attention mechanism on top of the extracted word-level…

We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the encoding and decoding representations our algorithm permits…

This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising…

Dysfluent speech modeling requires time-accurate and silence-aware transcription at both the word-level and phonetic-level. However, current research in dysfluency modeling primarily focuses on either transcription or detection, and the…

End-to-end neural approaches are becoming increasingly common in conversational scenarios due to their promising performances when provided with sufficient amount of data. In this paper, we present a novel methodology to address the…

Recent advances in deep learning have relied heavily on the use of large Transformers due to their ability to learn at scale. However, the core building block of Transformers, the attention operator, exhibits quadratic cost in sequence…

Deep Equilibrium Models (DEQs) are an interesting class of implicit model where the model output is implicitly defined as the fixed point of a learned function. These models have been shown to outperform explicit (fixed-depth) models in…