Search Results for author:
Found 39 papers, 12 papers with code
What Makes Good In-Context Examples for GPT-3?
In this work, we investigate whether there are more effective strategies for judiciously selecting in-context examples (relative to random sampling) that better leverage GPT-3’s in-context learning capabilities. Inspired by the recent success of leveraging a retrieval module to augment neural networks, we propose to retrieve examples that are semantically-similar to a test query sample to formulate its corresponding prompt.
HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalizability
Fine-tuning large pre-trained models with task-specific data has achieved great success in NLP.
HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalization
Fine-tuning large pre-trained models with task-specific data has achieved great success in NLP.
What Makes Good In-Context Examples for GPT-$3$?
Inspired by the recent success of leveraging a retrieval module to augment large-scale neural network models, we propose to retrieve examples that are semantically-similar to a test sample to formulate its corresponding prompt.
MixKD: Towards Efficient Distillation of Large-scale Language Models
Large-scale language models have recently demonstrated impressive empirical performance.
CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding
To verify the effectiveness of the proposed framework, we apply CoDA to Transformer-based models on a wide range of natural language understanding tasks.
Improving Self-supervised Pre-training via a Fully-Explored Masked Language Model
We prove, from a theoretical perspective, that the gradients derived from this new masking schema have a smaller variance and can lead to more efficient self-supervised training.
Ranked #1 on
Sentence Classification
on ACL-ARC
Improving Text Generation with Student-Forcing Optimal Transport
An extension is further proposed to improve the OT learning, based on the structural and contextual information of the text sequences.
A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation
Adversarial training has been shown effective at endowing the learned representations with stronger generalization ability.
Ranked #9 on
Machine Translation
on IWSLT2014 German-English
Generative Semantic Hashing Enhanced via Boltzmann Machines
Generative semantic hashing is a promising technique for large-scale information retrieval thanks to its fast retrieval speed and small memory footprint.
Improving Disentangled Text Representation Learning with Information-Theoretic Guidance
Learning disentangled representations of natural language is essential for many NLP tasks, e. g., conditional text generation, style transfer, personalized dialogue systems, etc.
Improving Adversarial Text Generation by Modeling the Distant Future
Auto-regressive text generation models usually focus on local fluency, and may cause inconsistent semantic meaning in long text generation.
Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding
Attention-based models have shown significant improvement over traditional algorithms in several NLP tasks.
An End-to-End Generative Architecture for Paraphrase Generation
Generating high-quality paraphrases is a fundamental yet challenging natural language processing task.
Straight-Through Estimator as Projected Wasserstein Gradient Flow
The Straight-Through (ST) estimator is a widely used technique for back-propagating gradients through discrete random variables.
Document Hashing with Mixture-Prior Generative Models
Hashing is promising for large-scale information retrieval tasks thanks to the efficiency of distance evaluation between binary codes.
Improving Textual Network Embedding with Global Attention via Optimal Transport
Constituting highly informative network embeddings is an important tool for network analysis.
Syntax-Infused Variational Autoencoder for Text Generation
We present a syntax-infused variational autoencoder (SIVAE), that integrates sentences with their syntactic trees to improve the grammar of generated sentences.
Topic-Guided Variational Auto-Encoder for Text Generation
We propose a topic-guided variational auto-encoder (TGVAE) model for text generation.
Topic-Guided Variational Autoencoders for Text Generation
We propose a topic-guided variational autoencoder (TGVAE) model for text generation.
Improving Sequence-to-Sequence Learning via Optimal Transport
Sequence-to-sequence models are commonly trained via maximum likelihood estimation (MLE).
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
Vision-language navigation (VLN) is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments.
Ranked #2 on
Vision-Language Navigation
on Room2Room
Sequence Generation with Guider Network
Sequence generation with reinforcement learning (RL) has received significant attention recently.
Adversarial Text Generation via Feature-Mover's Distance
However, the discrete nature of text hinders the application of GAN to text-generation tasks.
Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment
Network embeddings, which learn low-dimensional representations for each vertex in a large-scale network, have received considerable attention in recent years.
Diffusion Maps for Textual Network Embedding
Textual network embedding leverages rich text information associated with the network to learn low-dimensional vectorial representations of vertices.
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
Many deep learning architectures have been proposed to model the compositionality in text sequences, requiring a substantial number of parameters and expensive computations.
Ranked #1 on
Named Entity Recognition (NER)
on CoNLL 2000
NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing
Semantic hashing has become a powerful paradigm for fast similarity search in many information retrieval systems.
Joint Embedding of Words and Labels for Text Classification
Word embeddings are effective intermediate representations for capturing semantic regularities between words, when learning the representations of text sequences.
Ranked #11 on
Text Classification
on DBpedia
On the Use of Word Embeddings Alone to Represent Natural Language Sequences
In this paper, we conduct an extensive comparative study between Simple Word Embeddings-based Models (SWEMs), with no compositional parameters, relative to employing word embeddings within RNN/CNN-based models.
Topic Compositional Neural Language Model
The TCNLM learns the global semantic coherence of a document via a neural topic model, and the probability of each learned latent topic is further used to build a Mixture-of-Experts (MoE) language model, where each expert (corresponding to one topic) is a recurrent neural network (RNN) that accounts for learning the local structure of a word sequence.
Parametric t-Distributed Stochastic Exemplar-centered Embedding
Parametric embedding methods such as parametric t-SNE (pt-SNE) have been widely adopted for data visualization and out-of-sample data embedding without further computationally expensive optimization or approximation.
Learning Context-Sensitive Convolutional Filters for Text Processing
The role of meta network is to abstract the contextual information of a sentence or document into a set of input-aware filters.
Ranked #13 on
Text Classification
on DBpedia
Deconvolutional Paragraph Representation Learning
Learning latent representations from long text sequences is an important first step in many natural language processing applications.
Adversarial Feature Matching for Text Generation
We propose a framework for generating realistic text via adversarial training.
