Related papers: N-gram Injection into Transformers for Dynamic Lan…
We present a simple and effective approach to incorporating syntactic structure into neural attention-based encoder-decoder models for machine translation. We rely on graph-convolutional networks (GCNs), a recent class of neural networks…
The Bidirectional long short-term memory networks (BiLSTM) have been widely used as an encoder in models solving the named entity recognition (NER) task. Recently, the Transformer is broadly adopted in various Natural Language Processing…
Impressive performance of Transformer has been attributed to self-attention, where dependencies between entire input in a sequence are considered at every position. In this work, we reform the neural $n$-gram model, which focuses on only…
Neural machine translation aims at building a single large neural network that can be trained to maximize translation performance. The encoder-decoder architecture with an attention mechanism achieves a translation performance comparable to…
The mismatch between an external language model (LM) and the implicitly learned internal LM (ILM) of RNN-Transducer (RNN-T) can limit the performance of LM integration such as simple shallow fusion. A Bayesian interpretation suggests to…
We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts.…
We propose Fast-and-Frugal Text-Graph (FnF-TG) Transformers, a Transformer-based framework that unifies textual and structural information for inductive link prediction in text-attributed knowledge graphs. We demonstrate that, by…
Sequence generation models trained with teacher-forcing suffer from issues related to exposure bias and lack of differentiability across timesteps. Our proposed method, Teacher-Forcing with N-grams (TeaForN), addresses both these problems…
Transformers have demonstrated exceptional in-context learning capabilities, yet the theoretical understanding of the underlying mechanisms remains limited. A recent work (Elhage et al., 2021) identified a ``rich'' in-context mechanism…
Neural machine translation (NMT) models generally adopt an encoder-decoder architecture for modeling the entire translation process. The encoder summarizes the representation of input sentence from scratch, which is potentially a problem if…
While many systems have been developed to train Graph Neural Networks (GNNs), efficient model inference and evaluation remain to be addressed. For instance, using the widely adopted node-wise approach, model evaluation can account for up to…
Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…
In this paper, we try to understand neural machine translation (NMT) via simplifying NMT architectures and training encoder-free NMT models. In an encoder-free model, the sums of word embeddings and positional embeddings represent the…
Transformer-based NLP models are powerful but have high computational costs that limit deployment. Finetuned encoder-decoder models are popular in specialized domains and can outperform larger more generalized decoder-only models, such as…
There have been significant efforts to interpret the encoder of Transformer-based encoder-decoder architectures for neural machine translation (NMT); meanwhile, the decoder remains largely unexamined despite its critical role. During…
We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation. With our novel graph self-attention, the encoding of a node relies on all nodes in the input graph - not only direct neighbors -…
In recent years, deep learning-based models have significantly improved the Natural Language Processing (NLP) tasks. Specifically, the Convolutional Neural Network (CNN), initially used for computer vision, has shown remarkable performance…
Transformer based large-language models (LLMs) display extreme proficiency with language yet a precise understanding of how they work remains elusive. One way of demystifying transformer predictions would be to describe how they depend on…
The inference of gene regulatory networks (GRNs) is a foundational stride towards deciphering the fundamentals of complex biological systems. Inferring a possible regulatory link between two genes can be formulated as a link prediction…
While some studies have proven that Swin Transformer (Swin) with window self-attention (WSA) is suitable for single image super-resolution (SR), the plain WSA ignores the broad regions when reconstructing high-resolution images due to a…