Related papers: Transcoding compositionally: using attention to fi…
Chain-of-Thought (CoT) training has markedly advanced the reasoning capabilities of large language models (LLMs), yet the mechanisms by which CoT training enhances generalization remain inadequately understood. In this work, we demonstrate…
With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we…
The ability to learn and compose functions is foundational to efficient learning and reasoning in humans, enabling flexible generalizations such as creating new dishes from known cooking processes. Beyond sequential chaining of functions,…
The vanilla sequence-to-sequence learning (seq2seq) reads and encodes a source sequence into a fixed-length vector only once, suffering from its insufficiency in modeling structural correspondence between the source and target sequence.…
Attention networks have proven to be an effective approach for embedding categorical inference within a deep neural network. However, for many tasks we may want to model richer structural dependencies without abandoning end-to-end training.…
We apply a general recurrent neural network (RNN) encoder framework to community question answering (cQA) tasks. Our approach does not rely on any linguistic processing, and can be applied to different languages or domains. Further…
We investigate two specific manifestations of compositionality in Neural Machine Translation (NMT) : (1) Productivity - the ability of the model to extend its predictions beyond the observed length in training data and (2) Systematicity -…
Natural language exhibits patterns of hierarchically governed dependencies, in which relations between words are sensitive to syntactic structure rather than linear ordering. While re-current network models often fail to generalize in a…
Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…
Autoregressive (AR) Transformer-based sequence models are known to have difficulty generalizing to sequences longer than those seen during training. When applied to text-to-speech (TTS), these models tend to drop or repeat words or produce…
Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language…
Neural networks are surprisingly good at interpolating and perform remarkably well when the training set examples resemble those in the test set. However, they are often unable to extrapolate patterns beyond the seen data, even when the…
Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions…
We propose a novel framework for modeling the interaction between graphical structures and the natural language text associated with their nodes and edges. Existing approaches typically fall into two categories. On group ignores the…
Despite achieving tremendous success, existing deep learning models have exposed limitations in compositional generalization, the capability to learn compositional rules and apply them to unseen cases in a systematic manner. To tackle this…
Semantic composition functions have been playing a pivotal role in neural representation learning of text sequences. In spite of their success, most existing models suffer from the underfitting problem: they use the same shared…
Pre-trained sequence-to-sequence (seq-to-seq) models have significantly improved the accuracy of several language generation tasks, including abstractive summarization. Although the fluency of abstractive summarization has been greatly…
Sequence modeling has demonstrated state-of-the-art performance on natural language and document understanding tasks. However, it is challenging to correctly serialize tokens in form-like documents in practice due to their variety of layout…
Music relies heavily on repetition to build structure and meaning. Self-reference occurs on multiple timescales, from motifs to phrases to reusing of entire sections of music, such as in pieces with ABA structure. The Transformer (Vaswani…
Several studies have reported the inability of Transformer models to generalize compositionally, a key type of generalization in many NLP tasks such as semantic parsing. In this paper we explore the design space of Transformer models…