Search Results for author:
Found 67 papers, 29 papers with code
DINOISER: Diffused Conditional Sequence Learning by Manipulating Noises
In this paper, we introduce DINOISER to facilitate diffusion models for sequence generation by manipulating noises.
Beyond Triplet: Leveraging the Most Data for Multimodal Machine Translation
Therefore, this paper correspondingly establishes new methods and new datasets for MMT.
Diff-Glat: Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning
Autoregressive models can achieve high generation quality, but the sequential decoding scheme causes slow decoding speed.
SEScore2: Retrieval Augmented Pretraining for Text Generation Evaluation
Existing learned metrics have gaps to human judgements, are model-dependent or are limited to the domains or tasks where human ratings are available.
Controlling Styles in Neural Machine Translation with Activation Prompt
First, we re-visit this task and propose a multiway stylized machine translation (MSMT) benchmark, which includes multiple categories of styles in four language directions to push the boundary of this task.
Better Datastore, Better Translation: Generating Datastores from Pre-Trained Models for Nearest Neural Machine Translation
The effectiveness of kNNMT directly depends on the quality of retrieved neighbors.
M3ST: Mix at Three Levels for Speech Translation
How to solve the data scarcity problem for end-to-end speech-to-text translation (ST)?
Leveraging per Image-Token Consistency for Vision-Language Pre-training
(2) Under-utilization of the unmasked tokens: CMLM primarily focuses on the masked token but it cannot simultaneously leverage other tokens to learn vision-language associations.
The VolcTrans System for WMT22 Multilingual Machine Translation Task
This report describes our VolcTrans system for the WMT22 shared task on large-scale multilingual machine translation.
PARAGEN : A Parallel Generation Toolkit
PARAGEN is a PyTorch-based NLP toolkit for further development on parallel generation.
Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Prompts
Domain adaptation is an important challenge for neural machine translation.
Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation
Direct Speech-to-speech translation (S2ST) has drawn more and more attention recently.
Cross-modal Contrastive Learning for Speech Translation
Learning similar representations for semantically similar speech and text is important for speech translation.
GigaST: A 10,000-hour Pseudo Speech Translation Corpus
The training set is translated by a strong machine translation system and the test set is translated by human.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation
How to learn a better speech representation for end-to-end speech-to-text translation (ST) with limited labeled data?
Unified Multimodal Punctuation Restoration Framework for Mixed-Modality Corpus
The punctuation restoration task aims to correctly punctuate the output transcriptions of automatic speech recognition systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
LightSeq2: Accelerated Training for Transformer-based Models on GPUs
In this paper, we present LightSeq2, a system to accelerate training for a general family of Transformer models on GPUs.
Non-Autoregressive Models are Better Multilingual Translators
Multilingual machine translation aims to develop a single model for multiple language directions.
The Volctrans GLAT System: Non-autoregressive Translation Meets WMT21
This paper describes the Volctrans' submission to the WMT21 news translation shared task for German->English translation.
Learning Kernel-Smoothed Machine Translation with Retrieved Examples
How to effectively adapt neural machine translation (NMT) models according to emerging cases without retraining?
Learning When to Translate for Streaming Speech
Given a usually long speech sequence, we develop an efficient monotonic segmentation module inside an encoder-decoder model to accumulate acoustic information incrementally and detect proper speech unit boundaries for the input in speech translation task.
Multilingual Translation via Grafting Pre-trained Language Models
Can pre-trained BERT for one language and GPT for another be glued together to translate texts?
Secoco: Self-Correcting Encoding for Neural Machine Translation
This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with input noise for robust neural machine translation by introducing self-correcting predictors.
Pre-training Methods for Neural Machine Translation
This tutorial provides a comprehensive guide to make the most of pre-training for neural machine translation.
Language Tags Matter for Zero-Shot Neural Machine Translation
Language tag (LT) strategies are often adopted to indicate the translation directions in MNMT.
Autocorrect in the Process of Translation --- Multi-task Learning Improves Dialogue Machine Translation
Automatic translation of dialogue texts is a much needed demand in many real life scenarios.
Contrastive Learning for Many-to-many Multilingual Neural Machine Translation
Existing multilingual machine translation approaches mainly focus on English-centric directions, while the non-English directions still lag behind.
Learning Language Specific Sub-network for Multilingual Machine Translation
These jointly trained models often suffer from performance degradation on rich-resource language pairs.
The Volctrans Neural Speech Translation System for IWSLT 2021
For offline speech translation, our best end-to-end model achieves 8. 1 BLEU improvements over the benchmark on the MuST-C test set and is even approaching the results of a strong cascade solution.
Learning Shared Semantic Space for Speech-to-Text Translation
By projecting audio and text features to a common semantic representation, Chimera unifies MT and ST tasks and boosts the performance on ST benchmarks, MuST-C and Augmented Librispeech, to a new state-of-the-art.
End-to-end Speech Translation via Cross-modal Progressive Training
XSTNet takes both speech and text as input and outputs both transcription and translation text.
Counter-Interference Adapter for Multilingual Machine Translation
Developing a unified multilingual model has long been a pursuit for machine translation.
Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation
Automatic translation of dialogue texts is a much needed demand in many real life scenarios.
Non-iterative Parallel Text Generation via Glancing Transformer
Although non-autoregressive models with one-iteration generation achieves remarkable inference speed-up, they still falls behind their autoregressive counterparts inprediction accuracy.
Finding Sparse Structures for Domain Specific Neural Machine Translation
Neural machine translation often adopts the fine-tuning approach to adapt to specific domains.
NeurST: Neural Speech Translation Toolkit
NeurST is an open-source toolkit for neural speech translation.
Ranked #1 on
Speech-to-Text Translation
on libri-trans
Reciprocal Supervised Learning Improves Neural Machine Translation
Despite the recent success on image classification, self-training has only achieved limited gains on structured prediction tasks such as neural machine translation (NMT).
On the Sentence Embeddings from Pre-trained Language Models
Pre-trained contextual representations like BERT have achieved great success in natural language processing.
Ranked #10 on
Semantic Textual Similarity
on STS16
The Volctrans Machine Translation System for WMT20
This paper describes our VolcTrans system on WMT20 shared news translation task.
Volctrans Parallel Corpus Filtering System for WMT 2020
In this paper, we describe our submissions to the WMT20 shared task on parallel corpus filtering and alignment for low-resource conditions.
LightSeq: A High Performance Inference Library for Transformers
Transformer, BERT and their variants have achieved great success in natural language processing.
Rethinking Document-level Neural Machine Translation
This paper does not aim at introducing a novel model for document-level neural machine translation.
Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information
We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs?
Ranked #3 on
Machine Translation
on WMT2014 English-French
(using extra training data)
"Listen, Understand and Translate": Triple Supervision Decouples End-to-end Speech-to-text Translation
Can we build a system to fully utilize signals in a parallel ST corpus?
Generative Imagination Elevates Machine Translation
Given a sentence in a source language, whether depicting the visual scene helps translation into a target language?
Ranked #6 on
Multimodal Machine Translation
on Multi30K
Consecutive Decoding for Speech-to-text Translation
The key idea is to generate source transcript and target translation text with a single decoder.
Glancing Transformer for Non-Autoregressive Neural Machine Translation
With GLM, we develop Glancing Transformer (GLAT) for machine translation.
Ranked #67 on
Machine Translation
on WMT2014 English-German
Xiaomingbot: A Multilingual Robot News Reporter
This paper proposes the building of Xiaomingbot, an intelligent, multilingual and multimodal software robot equipped with four integral capabilities: news generation, news translation, news reading and avatar animation.
Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation
Auto-regressive sequence generative models trained by Maximum Likelihood Estimation suffer the exposure bias problem in practical finite sample scenarios.
Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space
We propose adversarial uncertainty sampling in discrete space (AUSDS) to retrieve informative unlabeled samples more efficiently.
Cross-lingual Supervision Improves Unsupervised Neural Machine Translation
Neural machine translation~(NMT) is ineffective for zero-resource languages.
Non-autoregressive Transformer by Position Learning
Non-autoregressive models are promising on various text generation tasks.
PNAT: Non-autoregressive Transformer by Position Learning
However, position modeling of output words is an essential problem in non-autoregressive text generation.
Towards Making the Most of BERT in Neural Machine Translation
Our experiments in machine translation show CTNMT gains of up to 3 BLEU score on the WMT14 English-German language pair which even surpasses the previous state-of-the-art pre-training aided NMT by 1. 4 BLEU score.
Imitation Learning for Non-Autoregressive Neural Machine Translation
Non-autoregressive translation models (NAT) have achieved impressive inference speedup.
Towards Linear Time Neural Machine Translation with Capsule Networks
In this study, we first investigate a novel capsule network with dynamic routing for linear time Neural Machine Translation (NMT), referred as \textsc{CapsNMT}.
Tencent Neural Machine Translation Systems for WMT18
We participated in the WMT 2018 shared news translation task on English↔Chinese language pair.
Neural Machine Translation with Decoding History Enhanced Attention
Neural machine translation with source-side attention have achieved remarkable performance.
Deep Semantic Role Labeling with Self-Attention
Semantic Role Labeling (SRL) is believed to be a crucial step towards natural language understanding and has been widely studied.
Ranked #14 on
Semantic Role Labeling
on OntoNotes
Incorporating Word Reordering Knowledge into Attention-based Neural Machine Translation
This paper proposes three distortion models to explicitly incorporate the word reordering knowledge into attention-based Neural Machine Translation (NMT) for further improving translation performance.
Deep Neural Machine Translation with Linear Associative Unit
Deep Neural Networks (DNNs) have provably enhanced the state-of-the-art Neural Machine Translation (NMT) with their capability in modeling complex functions and capturing complex linguistic structures.
Memory-enhanced Decoder for Neural Machine Translation
We propose to enhance the RNN decoder in a neural machine translator (NMT) with external memory, as a natural but powerful extension to the state in the decoding RNN.
$gen$CNN: A Convolutional Architecture for Word Sequence Prediction
Different from previous work on neural network-based language modeling and generation (e. g., RNN or LSTM), we choose not to greedily summarize the history of words as a fixed length vector.
Syntax-based Deep Matching of Short Texts
Many tasks in natural language processing, ranging from machine translation to question answering, can be reduced to the problem of matching two sentences or more generally two short texts.
Encoding Source Language with Convolutional Neural Network for Machine Translation
The recently proposed neural network joint model (NNJM) (Devlin et al., 2014) augments the n-gram target language model with a heuristically chosen source context window, achieving state-of-the-art performance in SMT.
