Search Results for author: Biao Zhang

Found 48 papers, 24 papers with code

ParBLEU: Augmenting Metrics with Automatic Paraphrases for the WMT’20 Metrics Shared Task

no code implementations WMT (EMNLP) 2020 Rachel Bawden, Biao Zhang, Andre Tättar, Matt Post

We describe parBLEU, parCHRF++, and parESIM, which augment baseline metrics with automatically generated paraphrases produced by PRISM (Thompson and Post, 2020a), a multilingual neural machine translation system.

Machine Translation Translation

When Does Monolingual Data Help Multilingual Translation: The Role of Domain and Model Scale

no code implementations23 May 2023 Christos Baziotis, Biao Zhang, Alexandra Birch, Barry Haddow

Next, we analyze the impact of scale (from 90M to 1. 6B parameters) and find it is important for both methods, particularly DAE.

Denoising Machine Translation +1

SLTUNET: A Simple Unified Model for Sign Language Translation

1 code implementation International Conference on Learning Representations (ICLR) 2023 Biao Zhang, Mathias Müller, Rico Sennrich

We propose SLTUNET, a simple unified neural model designed to support multiple SLTrelated tasks jointly, such as sign-to-gloss, gloss-to-text and sign-to-text translation.

Machine Translation Sign Language Translation +1

Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation

1 code implementation21 Feb 2023 Biao Zhang, Barry Haddow, Rico Sennrich

For end-to-end speech translation, regularizing the encoder with the Connectionist Temporal Classification (CTC) objective using the source transcript or target translation as labels can greatly improve quality metrics.


Prompting Large Language Model for Machine Translation: A Case Study

no code implementations17 Jan 2023 Biao Zhang, Barry Haddow, Alexandra Birch

Research on prompting has shown excellent performance with little or even no supervised training across many tasks.

Language Modelling Large Language Model +5

Investigating Neuron Disturbing in Fusing Heterogeneous Neural Networks

no code implementations24 Oct 2022 Biao Zhang, Peng Xiao, Shuqin Zhang

Fusing deep learning models trained on separately located clients into a global model in a one-shot communication round is a straightforward implementation of Federated Learning.

Federated Learning

Revisiting End-to-End Speech-to-Text Translation From Scratch

1 code implementation9 Jun 2022 Biao Zhang, Barry Haddow, Rico Sennrich

Finally, we discuss neural acoustic feature modeling, where a neural model is designed to extract acoustic features from raw speech signals directly, with the goal to simplify inductive biases and add freedom to the model in describing speech.

speech-recognition Speech Recognition +2

3DILG: Irregular Latent Grids for 3D Generative Modeling

1 code implementation27 May 2022 Biao Zhang, Matthias Nießner, Peter Wonka

All probabilistic experiments confirm that we are able to generate detailed and high quality shapes to yield the new state of the art in generative 3D shape modeling.

3D Shape Modeling

Data Scaling Laws in NMT: The Effect of Noise and Architecture

no code implementations4 Feb 2022 Yamini Bansal, Behrooz Ghorbani, Ankush Garg, Biao Zhang, Maxim Krikun, Colin Cherry, Behnam Neyshabur, Orhan Firat

In this work, we study the effect of varying the architecture and training data quality on the data scaling properties of Neural Machine Translation (NMT).

Language Modelling Machine Translation +1

Examining Scaling and Transfer of Language Model Architectures for Machine Translation

no code implementations1 Feb 2022 Biao Zhang, Behrooz Ghorbani, Ankur Bapna, Yong Cheng, Xavier Garcia, Jonathan Shen, Orhan Firat

Natural language understanding and generation models follow one of the two dominant architectural paradigms: language models (LMs) that process concatenated sequences in a single stack of layers, and encoder-decoder models (EncDec) that utilize separate layer stacks for input and output processing.

Language Modelling Machine Translation +2

Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents

no code implementations ACL 2022 Biao Zhang, Ankur Bapna, Melvin Johnson, Ali Dabirmoghaddam, Naveen Arivazhagan, Orhan Firat

Using simple concatenation-based DocNMT, we explore the effect of 3 factors on the transfer: the number of teacher languages with document level data, the balance between document and sentence level data at training, and the data condition of parallel documents (genuine vs. backtranslated).

Machine Translation Transfer Learning +1

Beyond Sentence-Level End-to-End Speech Translation: Context Helps

1 code implementation ACL 2021 Biao Zhang, Ivan Titov, Barry Haddow, Rico Sennrich

Document-level contextual information has shown benefits to text-based machine translation, but whether and how context helps end-to-end (E2E) speech translation (ST) is still under-studied.

feature selection Machine Translation +1

Exploring Dynamic Selection of Branch Expansion Orders for Code Generation

1 code implementation ACL 2021 Hui Jiang, Chulun Zhou, Fandong Meng, Biao Zhang, Jie zhou, Degen Huang, Qingqiang Wu, Jinsong Su

Due to the great potential in facilitating software development, code generation has attracted increasing attention recently.

Code Generation

Sparse Attention with Linear Units

2 code implementations EMNLP 2021 Biao Zhang, Ivan Titov, Rico Sennrich

Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants.

Machine Translation Translation +1

Fast Interleaved Bidirectional Sequence Generation

1 code implementation WMT (EMNLP) 2020 Biao Zhang, Ivan Titov, Rico Sennrich

Instead of assuming independence between neighbouring tokens (semi-autoregressive decoding, SA), we take inspiration from bidirectional sequence generation and introduce a decoder that generates target words from the left-to-right and right-to-left directions simultaneously.

Document Summarization Machine Translation

Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization

no code implementations ICLR 2022 Biao Zhang, Peter Wonka

We combine training data generating networks with bi-level optimization algorithms to obtain a complete framework for which all components can be jointly trained.

3D Shape Reconstruction 3D Shape Representation +2

Adaptive Feature Selection for End-to-End Speech Translation

1 code implementation Findings of the Association for Computational Linguistics 2020 Biao Zhang, Ivan Titov, Barry Haddow, Rico Sennrich

Information in speech signals is not evenly distributed, making it an additional challenge for end-to-end (E2E) speech translation (ST) to learn to focus on informative features.

Data Augmentation feature selection +1

Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation

3 code implementations ACL 2020 Biao Zhang, Philip Williams, Ivan Titov, Rico Sennrich

Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations.

Machine Translation NMT +1

On Sparsifying Encoder Outputs in Sequence-to-Sequence Models

1 code implementation Findings (ACL) 2021 Biao Zhang, Ivan Titov, Rico Sennrich

Inspired by these observations, we explore the feasibility of specifying rule-based patterns that mask out encoder outputs based on information such as part-of-speech tags, word frequency and word position.

Document Summarization Machine Translation

Root Mean Square Layer Normalization

2 code implementations NeurIPS 2019 Biao Zhang, Rico Sennrich

RMSNorm regularizes the summed inputs to a neuron in one layer according to root mean square (RMS), giving the model re-scaling invariance property and implicit learning rate adaptation ability.

A Lightweight Recurrent Network for Sequence Modeling

1 code implementation ACL 2019 Biao Zhang, Rico Sennrich

We apply LRN as a drop-in replacement of existing recurrent units in several neural sequential models.

Revisiting Low-Resource Neural Machine Translation: A Case Study

2 code implementations ACL 2019 Rico Sennrich, Biao Zhang

It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data to achieve competitive results.

Low-Resource Neural Machine Translation NMT +1

Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks

3 code implementations EMNLP 2018 Biao Zhang, Deyi Xiong, Jinsong Su, Qian Lin, Huiji Zhang

Experiments on WMT14 translation tasks demonstrate that ATR-based neural machine translation can yield competitive performance on English- German and English-French language pairs in terms of both translation quality and speed.

Chinese Word Segmentation Machine Translation +2

Otem&Utem: Over- and Under-Translation Evaluation Metric for NMT

1 code implementation24 Jul 2018 Jing Yang, Biao Zhang, Yue Qin, Xiangwen Zhang, Qian Lin, Jinsong Su

Although neural machine translation(NMT) yields promising translation performance, it unfortunately suffers from over- and under-translation is- sues [Tu et al., 2016], of which studies have become research hotspots in NMT.

Machine Translation NMT +1

Accelerating Neural Transformer via an Average Attention Network

1 code implementation ACL 2018 Biao Zhang, Deyi Xiong, Jinsong Su

To alleviate this issue, we propose an average attention network as an alternative to the self-attention network in the decoder of the neural Transformer.

Machine Translation Translation

Variational Recurrent Neural Machine Translation

no code implementations16 Jan 2018 Jinsong Su, Shan Wu, Deyi Xiong, Yaojie Lu, Xianpei Han, Biao Zhang

Partially inspired by successful applications of variational recurrent neural networks, we propose a novel variational recurrent neural machine translation (VRNMT) model in this paper.

Machine Translation NMT +1

A GRU-Gated Attention Model for Neural Machine Translation

no code implementations27 Apr 2017 Biao Zhang, Deyi Xiong, Jinsong Su

In this paper, we propose a novel GRU-gated attention model (GAtt) for NMT which enhances the degree of discrimination of context vectors by enabling source representations to be sensitive to the partial translation generated by the decoder.

Machine Translation NMT +1

Cseq2seq: Cyclic Sequence-to-Sequence Learning

no code implementations29 Jul 2016 Biao Zhang, Deyi Xiong, Jinsong Su

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.

Machine Translation Translation +1

BattRAE: Bidimensional Attention-Based Recursive Autoencoders for Learning Bilingual Phrase Embeddings

1 code implementation25 May 2016 Biao Zhang, Deyi Xiong, Jinsong Su

In this paper, we propose a bidimensional attention based recursive autoencoder (BattRAE) to integrate clues and sourcetarget interactions at multiple levels of granularity into bilingual phrase representations.

Semantic Similarity Semantic Textual Similarity

Variational Neural Machine Translation

1 code implementation EMNLP 2016 Biao Zhang, Deyi Xiong, Jinsong Su, Hong Duan, Min Zhang

Models of neural machine translation are often from a discriminative family of encoderdecoders that learn a conditional distribution of a target sentence given a source sentence.

Machine Translation Translation

Neural Discourse Relation Recognition with Semantic Memory

no code implementations12 Mar 2016 Biao Zhang, Deyi Xiong, Jinsong Su

Inspired by this, we propose a neural recognizer for implicit discourse relation analysis, which builds upon a semantic memory that stores knowledge in a distributed fashion.

General Knowledge Word Embeddings

Variational Neural Discourse Relation Recognizer

1 code implementation EMNLP 2016 Biao Zhang, Deyi Xiong, Jinsong Su, Qun Liu, Rongrong Ji, Hong Duan, Min Zhang

In order to perform efficient inference and learning, we introduce neural discourse relation models to approximate the prior and posterior distributions of the latent variable, and employ these approximated distributions to optimize a reparameterized variational lower bound.

Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising

no code implementations CVPR 2014 Yi Peng, Deyu Meng, Zongben Xu, Chenqiang Gao, Yi Yang, Biao Zhang

As compared to the conventional RGB or gray-scale images, multispectral images (MSI) can deliver more faithful representation for real scenes, and enhance the performance of many computer vision tasks.

Dictionary Learning Image Denoising

Cannot find the paper you are looking for? You can Submit a new open access paper.