English
Related papers

Related papers: Enhancing the Transformer Decoder with Transition-…

200 papers

Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks, often performing well on specific task by leveraging input-output examples. Despite their empirical success, a comprehensive…

Machine Learning · Computer Science 2025-06-03 Yifan Hao , Chenlu Ye , Chi Han , Tong Zhang

In this paper, we propose a transformer based approach for visual grounding. Unlike previous proposal-and-rank frameworks that rely heavily on pretrained object detectors or proposal-free frameworks that upgrade an off-the-shelf one-stage…

Computer Vision and Pattern Recognition · Computer Science 2022-03-15 Ye Du , Zehua Fu , Qingjie Liu , Yunhong Wang

Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to…

Computation and Language · Computer Science 2016-05-23 Dzmitry Bahdanau , Kyunghyun Cho , Yoshua Bengio

Short text classification is a crucial and challenging aspect of Natural Language Processing. For this reason, there are numerous highly specialized short text classifiers. However, in recent short text research, State of the Art (SOTA)…

Computation and Language · Computer Science 2023-08-14 Fabian Karl , Ansgar Scherp

Deep learning models generalize well to in-distribution data but struggle to generalize compositionally, i.e., to combine a set of learned primitives to solve more complex tasks. In sequence-to-sequence (seq2seq) learning, transformers are…

Machine Learning · Computer Science 2021-12-13 Luana Ruiz , Joshua Ainslie , Santiago Ontañón

Transformer networks are the de facto standard architecture in natural language processing. To date, there are no theoretical analyses of the Transformer's ability to capture tree structures. We focus on the ability of Transformer networks…

Computation and Language · Computer Science 2021-12-23 Qi He , João Sedoc , Jordan Rodu

Non-autoregressive models achieve significant decoding speedup in neural machine translation but lack the ability to capture sequential dependency. Directed Acyclic Transformer (DA-Transformer) was recently proposed to model sequential…

Computation and Language · Computer Science 2023-03-03 Chenze Shao , Zhengrui Ma , Yang Feng

While transformer-based models have achieved state-of-the-art results in a variety of classification and generation tasks, their black-box nature makes them challenging for interpretability. In this work, we present a novel visual…

Computation and Language · Computer Science 2023-11-22 Raymond Li , Ruixin Yang , Wen Xiao , Ahmed AbuRaed , Gabriel Murray , Giuseppe Carenini

Multimodalities provide promising performance than unimodality in most tasks. However, learning the semantic of the representations from multimodalities efficiently is extremely challenging. To tackle this, we propose the Transformer based…

Computer Vision and Pattern Recognition · Computer Science 2019-11-14 Wubo Li , Wei Zou , Xiangang Li

We find limits to the Transformer architecture for language modeling and show it has a universal prediction property in an information-theoretic sense. We further analyze performance in non-asymptotic data regimes to understand the role of…

Machine Learning · Computer Science 2023-07-18 Sourya Basu , Moulik Choraria , Lav R. Varshney

While convolutional neural networks have shown a tremendous impact on various computer vision tasks, they generally demonstrate limitations in explicitly modeling long-range dependencies due to the intrinsic locality of the convolution…

Computer Vision and Pattern Recognition · Computer Science 2021-08-06 Guanglei Yang , Hao Tang , Mingli Ding , Nicu Sebe , Elisa Ricci

Long document classification presents challenges in capturing both local and global dependencies due to their extensive content and complex structure. Existing methods often struggle with token limits and fail to adequately model…

Computation and Language · Computer Science 2024-10-07 Sudipta Singha Roy , Xindi Wang , Robert E. Mercer , Frank Rudzicz

We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We convert decoding - basically a discrete optimization problem - into a continuous optimization problem. The resulting constrained…

Computation and Language · Computer Science 2017-07-25 Cong Duy Vu Hoang , Gholamreza Haffari , Trevor Cohn

It has been of increasing interest in the field to develop automatic machineries to facilitate the design process. In this paper, we focus on assisting graphical user interface (UI) layout design, a crucial task in app development. Given a…

Human-Computer Interaction · Computer Science 2020-01-16 Yang Li , Julien Amelot , Xin Zhou , Samy Bengio , Si Si

Dependency parsing research, which has made significant gains in recent years, typically focuses on improving the accuracy of single-tree predictions. However, ambiguity is inherent to natural language syntax, and communicating such…

Computation and Language · Computer Science 2018-04-18 Katherine A. Keith , Su Lin Blodgett , Brendan O'Connor

We introduce a novel multi-source technique for incorporating source syntax into neural machine translation using linearized parses. This is achieved by employing separate encoders for the sequential and parsed versions of the same source…

Computation and Language · Computer Science 2018-08-31 Anna Currey , Kenneth Heafield

Transformers flexibly operate over sets of real-valued vectors representing task-specific entities and their attributes, where each vector might encode one word-piece token and its position in a sequence, or some piece of information that…

Machine Learning · Computer Science 2023-03-14 Cameron Diao , Ricky Loynd

We present a simple method to incorporate syntactic information about the target language in a neural machine translation system by translating into linearized, lexicalized constituency trees. An experiment on the WMT16 German-English news…

Computation and Language · Computer Science 2017-05-09 Roee Aharoni , Yoav Goldberg

A common and effective way to train translation systems between related languages is to consider sub-word level basic units. However, this increases the length of the sentences resulting in increased decoding time. The increase in length is…

Computation and Language · Computer Science 2016-11-02 Anoop Kunchukuttan , Pushpak Bhattacharyya

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…

‹ Prev 1 8 9 10 Next ›