Search Results for author:
Found 22 papers, 12 papers with code
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
Through careful and comprehensive ablations of the image encoder, the vision language connector, and various pre-training data choices, we identified several crucial design lessons.
Ranked #18 on
Visual Question Answering
on MM-Vet
Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation
In this paper, we propose a method to evaluate the response preference by using the output probabilities of response pairs under contrastive prompt pairs, which could achieve better performance on LLaMA2-7B and LLaMA2-13B compared to RLAIF.
Mega: Moving Average Equipped Gated Attention
The design choices in the Transformer attention mechanism, including weak inductive bias and quadratic computational complexity, have limited its application for modeling long sequences.
Ranked #1 on
Long-range modeling
on LRA
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.
BLT: Bidirectional Layout Transformer for Controllable Layout Generation
During inference, BLT first generates a draft layout from the input and then iteratively refines it into a high-quality layout by masking out low-confident attributes.
Luna: Linear Unified Nested Attention
Specifically, with the first attention function, Luna packs the input sequence into a sequence of fixed length.
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.
Incorporating a Local Translation Mechanism into Non-autoregressive Translation
In this work, we introduce a novel local autoregressive translation (LAT) mechanism into non-autoregressive translation (NAT) models so as to capture local dependencies among tar-get outputs.
Ranked #2 on
Machine Translation
on WMT2016 English-Romanian
An Empirical Exploration of Local Ordering Pre-training for Structured Prediction
Recently, pre-training contextualized encoders with language model (LM) objectives has been shown an effective semi-supervised method for structured prediction.
Deep Transformers with Latent Depth
As an extension of this framework, we propose a novel method to train one shared Transformer network for multilingual machine translation with different layer selection posteriors for each language pair.
A Two-Step Approach for Implicit Event Argument Detection
It remains a challenge to detect implicit arguments, calling for more future work of document-level modeling for this task.
SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations
We introduce SCDE, a dataset to evaluate the performance of computational models through sentence prediction.
Ranked #3 on
Question Answering
on SCDE
Decoupling Global and Local Representations via Invertible Generative Flows
In this work, we propose a new generative model that is capable of automatically decoupling global and local representations of images in an entirely unsupervised setting, by embedding a generative flow in the VAE framework to model the decoder.
Decompressing Knowledge Graph Representations for Link Prediction
Specifically, embeddings of entities and relationships are first decompressed to a more expressive and robust space by decompressing functions, then knowledge graph embedding models are trained in this new feature space.
Ranked #26 on
Link Prediction
on FB15k-237
Generalized Data Augmentation for Low-Resource Translation
Translation to or from low-resource languages LRLs poses challenges for machine translation in terms of both adequacy and fluency.
MaCow: Masked Convolutional Generative Flow
Flow-based generative models, conceptually attractive due to tractability of both the exact log-likelihood computation and latent-variable inference, and efficiency of both training and sampling, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations.
Ranked #3 on
Image Generation
on CelebA 256x256
An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
In this work, we propose a method for neural dialogue response generation that allows not only generating semantically reasonable responses according to the dialogue history, but also explicitly controlling the sentiment of the response via sentiment labels.
Neural Machine Translation with Adequacy-Oriented Learning
Although Neural Machine Translation (NMT) models have advanced state-of-the-art performance in machine translation, they face problems like the inadequate translation.
Ranked #35 on
Machine Translation
on WMT2014 English-German
Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation
Mixture of Softmaxes (MoS) has been shown to be effective at addressing the expressiveness limitation of Softmax-based models.
Ranked #18 on
Machine Translation
on WMT2014 English-French
Evaluating Automatic Speech Recognition Systems in Comparison With Human Perception Results Using Distinctive Feature Measures
This paper describes methods for evaluating automatic speech recognition (ASR) systems in comparison with human perception results, using measures derived from linguistic distinctive features.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Performance Improvements of Probabilistic Transcript-adapted ASR with Recurrent Neural Network and Language-specific Constraints
Mismatched transcriptions have been proposed as a mean to acquire probabilistic transcriptions from non-native speakers of a language. Prior work has demonstrated the value of these transcriptions by successfully adapting cross-lingual ASR systems for different tar-get languages.
Landmark-based consonant voicing detection on multilingual corpora
Three consonant voicing classifiers were developed: (1) manually selected acoustic features anchored at a phonetic landmark, (2) MFCCs (either averaged across the segment or anchored at the landmark), and(3) acoustic features computed using a convolutional neural network (CNN).
