Search Results for author:
Found 66 papers, 26 papers with code
Non-Autoregressive Sequence Generation
Non-autoregressive sequence generation (NAR) attempts to generate the entire or partial output sequences in parallel to speed up the generation process and avoid potential issues (e. g., label bias, exposure bias) in autoregressive generation.
Non-autoregressive Translation with Disentangled Context Transformer
State-of-the-art neural machine translation models generate a translation from left to right and every step is conditioned on the previously generated tokens.
fairseq Sˆ2: A Scalable and Integrable Speech Synthesis Toolkit
This paper presents fairseq Sˆ2, a fairseq extension for speech synthesis.
Facebook AI’s WMT20 News Translation Task Submission
We approach the low resource problem using two main strategies, leveraging all available data and adapting the system to the target news domain.
PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model
Autoregressive models for text sometimes generate repetitive and low-quality output because errors accumulate during the steps of generation.
Learning Controllable 3D Diffusion Models from Single-view Images
To address these challenges, We present Control3Diff, a 3D diffusion model that combines the strengths of diffusion models and 3D GANs for versatile, controllable 3D-aware image synthesis for single-view datasets.
Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction
3D-aware image synthesis encompasses a variety of tasks, such as scene generation and novel view synthesis from images.
Stabilizing Transformer Training by Preventing Attention Entropy Collapse
We show that $\sigma$Reparam provides stability and robustness with respect to the choice of hyperparameters, going so far as enabling training (a) a Vision Transformer to competitive performance without warmup, weight decay, layer normalization or adaptive optimizers; (b) deep architectures in machine translation and (c) speech recognition to competitive performance without warmup and adaptive optimizers.
MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors
We do so by Masked Augmentation Subspace Training (or MAST) to encode in the single feature space the priors from different data augmentations in a factorized way.
Diffusion Probabilistic Fields
Diffusion probabilistic models have quickly become a major approach for generative modeling of images, 3D geometry, video and other domains.
NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion
Novel view synthesis from a single image requires inferring occluded regions of objects and scenes whilst simultaneously maintaining semantic and physical consistency with the input.
f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation
In this work, we propose f-DM, a generalized family of DMs which allows progressive signal transformation.
Progressively-connected Light Field Network for Efficient View Synthesis
ProLiF encodes a 4D light field, which allows rendering a large batch of rays in one training step for image- or patch-level losses.
Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders
Recent work in multilingual translation advances translation quality surpassing bilingual baselines using deep transformer models with increased capacity.
Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem
Without the use of a knowledge base or candidate sets, our model sets a new state of the art in two benchmark datasets of entity linking: COMETA in the biomedical domain, and AIDA-CoNLL in the news domain.
Unified Speech-Text Pre-training for Speech Translation and Recognition
Two pre-training configurations for speech translation and recognition, respectively, are presented to alleviate subtask interference.
IDPG: An Instance-Dependent Prompt Generation Method
Prompt tuning is a new, efficient NLP transfer learning paradigm that adds a task-specific prompt in each input instance during the model training stage.
Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation
Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues as there exists little parallel S2ST data, compared to the amount of data available for conventional cascaded systems that consist of automatic speech recognition (ASR), machine translation (MT), and text-to-speech (TTS) synthesis.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind.
Ranked #1 on
Paraphrase Identification
on Quora Question Pairs
(Accuracy metric)
Textless Speech-to-Speech Translation on Real Data
To our knowledge, we are the first to establish a textless S2ST technique that can be trained with real-world data and works for multiple language pairs.
StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis
We perform volume rendering only to produce a low-resolution feature map and progressively apply upsampling in 2D to address the first issue.
fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit
This paper presents fairseq S^2, a fairseq extension for speech synthesis.
Direct speech-to-speech translation with discrete units
When target text transcripts are available, we design a joint speech and text training framework that enables the model to generate dual modality output (speech and text) simultaneously in the same inference pass.
Volume Rendering of Neural Implicit Surfaces
Accurate sampling is important to provide a precise coupling of geometry and radiance; and (iii) it allows efficient unsupervised disentanglement of shape and appearance in volume rendering.
Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control
To address this problem, we utilize a coarse body model as the proxy to unwarp the surrounding 3D space into a canonical pose.
Lightweight Adapter Tuning for Multilingual Speech Translation
Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP.
Ranked #1 on
Speech-to-Text Translation
on MuST-C EN->ES
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
CLEAR: Contrastive Learning for Sentence Representation
Pre-trained language models have proven their unique powers in capturing implicit language features.
Ranked #5 on
Question Answering
on Quora Question Pairs
Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade
Fully non-autoregressive neural machine translation (NAT) is proposed to simultaneously predict tokens with single forward of neural networks, which significantly reduces the inference latency at the expense of quality drop compared to the Transformer baseline.
Facebook AI's WMT20 News Translation Task Submission
We approach the low resource problem using two main strategies, leveraging all available data and adapting the system to the target news domain.
Detecting Hallucinated Content in Conditional Neural Sequence Generation
Neural sequence models can generate highly fluent sentences, but recent studies have also shown that they are also prone to hallucinate additional content not supported by the input.
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation
We propose two variants of these architectures corresponding to two different levels of dependencies between the decoders, called the parallel and cross dual-decoder Transformers, respectively.
Ranked #1 on
Speech-to-Text Translation
on MuST-C EN->FR
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Multilingual Translation with Extensible Multilingual Pretraining and Finetuning
Recent work demonstrates the potential of multilingual pretraining of creating one model that can be used for various tasks in different languages.
SimulEval: An Evaluation Toolkit for Simultaneous Translation
We also adapt latency metrics from text simultaneous translation to the speech task.
Neural Sparse Voxel Fields
We also demonstrate several challenging tasks, including multi-scene learning, free-viewpoint rendering of a moving human, and large-scale scene rendering.
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
To this end, we select a suite of diverse datasets and tasks to measure the effect of unsupervised pre-training on a large source set of 3D scenes.
Addressing Posterior Collapse with Mutual Information for Improved Variational Neural Machine Translation
This paper proposes a simple and effective approach to address the problem of posterior collapse in conditional variational autoencoders (CVAEs).
FINDINGS OF THE IWSLT 2020 EVALUATION CAMPAIGN
The evaluation campaign of the International Conference on Spoken Language Translation (IWSLT 2020) featured this year six challenge tracks: (i) Simultaneous speech translation, (ii) Video speech translation, (iii) Offline speech translation, (iv) Conversational speech translation, (v) Open domain translation, and (vi) Non-native speech translation.
Self-Supervised Representations Improve End-to-End Speech Translation
End-to-end speech-to-text translation can provide a simpler and smaller system but is facing the challenge of data scarcity.
Cross-lingual Retrieval for Iterative Self-Supervised Training
Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models.
Improving Cross-Lingual Transfer Learning for End-to-End Speech Recognition with Speech Translation
Even with pseudo-labels from low-resource MT (200K examples), ST-enhanced transfer brings up to 8. 9% WER reduction to direct transfer.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus
Spoken language translation has recently witnessed a resurgence in popularity, thanks to the development of end-to-end models and the creation of new corpora, such as Augmented LibriSpeech and MuST-C.
Multilingual Denoising Pre-training for Neural Machine Translation
This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks.
Non-Autoregressive Machine Translation with Disentangled Context Transformer
State-of-the-art neural machine translation models generate a translation from left to right and every step is conditioned on the previously generated tokens.
Understanding Knowledge Distillation in Non-autoregressive Machine Translation
We find that knowledge distillation can reduce the complexity of data sets and help NAT to model the variations in the output data.
Depth-Adaptive Transformer
State of the art sequence-to-sequence models for large scale tasks perform a fixed number of computations for each input sequence regardless of whether it is easy or hard to process.
Revisiting Self-Training for Neural Sequence Generation
In this work, we first empirically show that self-training is able to decently improve the supervised baseline on neural sequence generation tasks.
The Source-Target Domain Mismatch Problem in Machine Translation
While we live in an increasingly interconnected world, different places still exhibit strikingly different cultures and many events we experience in our every day life pertain only to the specific place we live in.
Monotonic Multihead Attention
Simultaneous machine translation models start generating a target sequence before they have encoded or read the source sequence.
Improved Variational Neural Machine Translation by Promoting Mutual Information
Posterior collapse plagues VAEs for text, especially for conditional text generation with strong autoregressive decoders.
Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade
In this work, we evaluate several data augmentation and pretraining approaches for AST, by comparing all on the same datasets.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
VizSeq: A Visual Analysis Toolkit for Text Generation Tasks
Automatic evaluation of text generation tasks (e. g. machine translation, text summarization, image captioning and video description) usually relies heavily on task-specific metrics, such as BLEU and ROUGE.
Neural Machine Translation with Byte-Level Subwords
Representing text at the level of bytes and using the 256 byte set as vocabulary is a potential solution to this issue.
Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations
Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings.
Levenshtein Transformer
We further confirm the flexibility of our model by showing a Levenshtein Transformer trained by machine translation can straightforwardly be used for automatic post-editing.
Ranked #5 on
Machine Translation
on WMT2016 Romanian-English
Insertion-based Decoding with automatically Inferred Generation Order
Conventional neural autoregressive decoding commonly assumes a fixed left-to-right generation order, which may be sub-optimal.
Meta-Learning for Low-Resource Neural Machine Translation
We frame low-resource translation as a meta-learning problem, and we learn to adapt to low-resource languages based on multilingual high-resource language tasks.
Universal Neural Machine Translation for Extremely Low Resource Languages
Our proposed approach utilizes a transfer-learning approach to share lexical and sentence level representations across multiple source languages into one target language.
Non-Autoregressive Neural Machine Translation
Existing approaches to neural machine translation condition each output word on previously generated outputs.
Ranked #3 on
Machine Translation
on IWSLT2015 English-German
Neural Machine Translation with Gumbel-Greedy Decoding
Previous neural machine translation models used some heuristic search algorithms (e. g., beam search) in order to avoid solving the maximum a posteriori problem over translation sentences at test time.
Search Engine Guided Non-Parametric Neural Machine Translation
In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training.
Trainable Greedy Decoding for Neural Machine Translation
Instead of trying to build a new decoding algorithm for any specific decoding objective, we propose the idea of trainable decoding algorithm in which we train a decoding algorithm to find a translation that maximizes an arbitrary decoding objective.
Learning to Translate in Real-time with Neural Machine Translation
Translating in real-time, a. k. a.
Incorporating Copying Mechanism in Sequence-to-Sequence Learning
CopyNet can nicely integrate the regular way of word generation in the decoder with the new copying mechanism which can choose sub-sequences in the input sequence and put them at proper places in the output sequence.
Efficient Learning for Undirected Topic Models
Replicated Softmax model, a well-known undirected topic model, is powerful in extracting semantic representations of documents.
