Related papers: Promoting the Knowledge of Source Syntax in Transf…
The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or…
The addition of syntax-aware decoding in Neural Machine Translation (NMT) systems requires an effective tree-structured neural network, a syntax-aware attention model and a language generation model that is sensitive to sentence structure.…
Word representations induced from models with discrete latent variables (e.g.\ HMMs) have been shown to be beneficial in many NLP applications. In this work, we exploit labeled syntactic dependency trees and formalize the induction problem…
Deep learning based question answering (QA) on English documents has achieved success because there is a large amount of English training examples. However, for most languages, training examples for high-quality QA models are not available.…
The remarkable capability of over-parameterised neural networks to generalise effectively has been explained by invoking a ``simplicity bias'': neural networks prevent overfitting by initially learning simple classifiers before progressing…
While a considerable amount of semantic parsing approaches have employed RNN architectures for code generation tasks, there have been only few attempts to investigate the applicability of Transformers for this task. Including hierarchical…
Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism concerning the sequence length. This…
State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence and convolution…
Document-level machine translation manages to outperform sentence level models by a small margin, but have failed to be widely adopted. We argue that previous research did not make a clear use of the global context, and propose a new…
Syntactic structures used to play a vital role in natural language processing (NLP), but since the deep learning revolution, NLP has been gradually dominated by neural models that do not consider syntactic structures in their design. One…
Asking clarifying questions in response to ambiguous or faceted queries has been recognized as a useful technique for various information retrieval systems, especially conversational search systems with limited bandwidth interfaces.…
Deep imitation learning is promising for solving dexterous manipulation tasks because it does not require an environment model and pre-programmed robot behavior. However, its application to dual-arm manipulation tasks remains challenging.…
Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…
We present graph-based translation models which translate source graphs into target strings. Source graphs are constructed from dependency trees with extra links so that non-syntactic phrases are connected. Inspired by phrase-based models,…
When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic…
The Transformer is a fully attention-based alternative to recurrent networks that has achieved state-of-the-art results across a range of NLP tasks. In this paper, we analyze the structure of attention in a Transformer language model, the…
Neural attention, especially the self-attention made popular by the Transformer, has become the workhorse of state-of-the-art natural language processing (NLP) models. Very recent work suggests that the self-attention in the Transformer…
Morphologically rich languages pose difficulties to machine translation. Machine translation engines that rely on statistical learning from parallel training data, such as state-of-the-art neural systems, face challenges especially with…
Neural machine translation (NMT) models learn representations containing substantial linguistic information. However, it is not clear if such information is fully distributed or if some of it can be attributed to individual neurons. We…
Since the popularization of the Transformer as a general-purpose feature encoder for NLP, many studies have attempted to decode linguistic structure from its novel multi-head attention mechanism. However, much of such work focused almost…