Search Results for author:
Found 53 papers, 31 papers with code
AESOP: Paraphrase Generation with Adaptive Syntactic Control
We propose to control paraphrase generation through carefully chosen target syntactic structures to generate more proper and higher quality paraphrases.
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
The quadratic complexity and weak length extrapolation of Transformers limits their ability to scale to long sequences, and while sub-quadratic solutions like linear attention and state space models exist, they empirically underperform Transformers in pretraining efficiency and downstream task accuracy.
Evaluating Large Language Models on Controlled Generation Tasks
While recent studies have looked into the abilities of large language models in various benchmark tasks, including question generation, reading comprehension, multilingual and etc, there have been few studies looking into the controllability of large language models on generation tasks.
DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training
FlashAttention (Dao, 2023) effectively reduces the quadratic peak memory usage to linear in training transformer-based large language models (LLMs) on a single GPU.
MIDDAG: Where Does Our News Go? Investigating Information Diffusion via Community-Level Information Pathways
We present MIDDAG, an intuitive, interactive system that visualizes the information propagation paths on social media triggered by COVID-19-related news articles accompanied by comprehensive insights, including user/community susceptibility level, as well as events and popular opinions raised by the crowd while propagating the information.
RECAP: Retrieval-Enhanced Context-Aware Prefix Encoder for Personalized Dialogue Response Generation
Endowing chatbots with a consistent persona is essential to an engaging conversation, yet it remains an unresolved challenge.
Challenges in Context-Aware Neural Machine Translation
Context-aware neural machine translation involves leveraging information beyond sentence-level context to resolve inter-sentential discourse dependencies and improve document-level translation quality, and has given rise to a number of recent techniques.
Look-back Decoding for Open-Ended Text Generation
Given a prefix (context), open-ended generation aims to decode texts that are coherent, which do not abruptly drift from previous topics, and informative, which do not suffer from undesired repetitions.
LIMA: Less Is More for Alignment
Large language models are trained in two stages: (1) unsupervised pretraining from raw text, to learn general-purpose representations, and (2) large scale instruction tuning and reinforcement learning, to better align to end tasks and user preferences.
On Human Visual Contrast Sensitivity and Machine Vision Robustness: A Comparative Study
It is well established in neuroscience that color vision plays an essential part in the human visual perception system.
Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification
In this paper, we provide 20, 000 non-trivial human annotations on popular datasets as a first step to bridge gap to studying how natural semantic spurious features affect image classification, as prior works often study datasets mixing low-level features due to limitations in accessing realistic datasets.
Improving Stability of Fine-Tuning Pretrained Language Models via Component-Wise Gradient Norm Clipping
Despite its superior performance, such fine-tuning can be unstable, resulting in significant variance in performance and potential risks for practical applications.
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
Know Where You're Going: Meta-Learning for Parameter-Efficient Fine-Tuning
A recent family of techniques, dubbed lightweight fine-tuning methods, facilitates parameter-efficient transfer learning by updating only a small set of additional parameters while keeping the parameters of the pretrained language model frozen.
Investigating the Benefits of Free-Form Rationales
After controlling for instances where rationales leak the correct answer while not providing additional background knowledge, we find that incorporating only 5% of rationales during training can boost model performance by 47. 22% for CoS-E and 57. 14% for ECQA during inference.
Prompt Consistency for Zero-Shot Task Generalization
One of the most impressive results of recent NLP history is the ability of pre-trained language models to solve new tasks in a zero-shot setting.
Learning Representations Robust to Group Shifts and Adversarial Examples
Despite the high performance achieved by deep neural networks on various tasks, extensive studies have demonstrated that small tweaks in the input could fail the model predictions.
Towards a Unified View of Parameter-Efficient Transfer Learning
Furthermore, our unified framework enables the transfer of design elements across different approaches, and as a result we are able to instantiate new parameter-efficient fine-tuning methods that tune less parameters than previous methods while being more effective, achieving comparable results to fine-tuning all parameters on all four tasks.
Examining and Combating Spurious Features under Distribution Shift
Group distributionally robust optimization (DRO) provides an effective tool to alleviate covariate shift by minimizing the worst-case training loss over a set of pre-defined groups.
Luna: Linear Unified Nested Attention
Specifically, with the first attention function, Luna packs the input sequence into a sequence of fixed length.
COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences
To this end, we introduce a new commonsense reasoning benchmark dataset comprising natural language true/false statements, with each sample paired with its complementary counterpart, resulting in 4k sentence pairs.
Personalized Response Generation via Generative Split Memory Network
Despite the impressive successes of generation and dialogue systems, how to endow a text generation system with particular personality traits to deliver more personalized responses remains under-investigated.
DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation
Having engaging and informative conversations with users is the utmost goal for open-domain conversational systems.
Apollo: An Adaptive Parameter-wised Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization
In this paper, we introduce Apollo, a quasi-newton method for noncovex stochastic optimization, which dynamically incorporates the curvature of the loss function by approximating the Hessian via a diagonal matrix.
Apollo: An Adaptive Parameter-wise Diagonal Quasi-Newton Method for Nonconvex Stochastic Optimization
In this paper, we introduce Apollo, a quasi-Newton method for nonconvex stochastic optimization, which dynamically incorporates the curvature of the loss function by approximating the Hessian via a diagonal matrix.
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.
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.
Cross-lingual Dependency Parsing with Unlabeled Auxiliary Languages
We conduct experiments on cross-lingual dependency parsing where we train a dependency parser on a source language and transfer it to a wide range of target languages.
FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
Most sequence-to-sequence (seq2seq) models are autoregressive; they generate each token by conditioning on previously generated tokens.
Ranked #3 on
Machine Translation
on WMT2016 English-Romanian
Handling Syntactic Divergence in Low-resource Machine Translation
Despite impressive empirical successes of neural machine translation (NMT) on standard benchmarks, limited parallel data impedes the application of NMT models to many language pairs.
An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing
In this paper, we investigate the aspect of structured output modeling for the state-of-the-art graph-based neural dependency parser (Dozat and Manning, 2017).
Choosing Transfer Languages for Cross-Lingual Learning
Cross-lingual transfer, where a high-resource transfer language is used to improve the accuracy of a low-resource task language, is now an invaluable tool for improving performance of natural language processing (NLP) on low-resource languages.
Density Matching for Bilingual Word Embedding
Recent approaches to cross-lingual word embedding have generally been based on linear transformations between the sets of embedding vectors in the two languages.
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
MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders
Variational Autoencoder (VAE), a simple and effective deep generative model, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations.
On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing
Different languages might have different word orders.
Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation
The versatile toolkit also fosters technique sharing across different text generation tasks.
Texar: A Modularized, Versatile, and Extensible Toolbox for Text Generation
The features make Texar particularly suitable for technique sharing and generalization across different text generation applications.
Stack-Pointer Networks for Dependency Parsing
Combining pointer networks~\citep{vinyals2015pointer} with an internal stack, the proposed model first reads and encodes the whole sentence, then builds the dependency tree top-down (from root-to-leaf) in a depth-first fashion.
Ranked #14 on
Dependency Parsing
on Penn Treebank
STCP: Simplified-Traditional Chinese Conversion and Proofreading
This paper aims to provide an effective tool for conversion between Simplified Chinese and Traditional Chinese.
Softmax Q-Distribution Estimation for Structured Prediction: A Theoretical Interpretation for RAML
Reward augmented maximum likelihood (RAML), a simple and effective learning framework to directly optimize towards the reward function in structured prediction tasks, has led to a number of impressive empirical successes.
An Interpretable Knowledge Transfer Model for Knowledge Base Completion
Knowledge bases are important resources for a variety of natural language processing tasks but suffer from incompleteness.
Neural Probabilistic Model for Non-projective MST Parsing
In this paper, we propose a probabilistic parsing model, which defines a proper conditional probability distribution over non-projective dependency trees for a given sentence, using neural representations as inputs.
Dropout with Expectation-linear Regularization
Algorithmically, we show that our proposed measure of the inference gap can be used to regularize the standard dropout training objective, resulting in an \emph{explicit} control of the gap.
Harnessing Deep Neural Networks with Logic Rules
Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models.
Ranked #65 on
Sentiment Analysis
on SST-2 Binary classification
Unsupervised Ranking Model for Entity Coreference Resolution
Coreference resolution is one of the first stages in deep language understanding and its importance has been well recognized in the natural language processing community.
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing.
Ranked #7 on
Named Entity Recognition (NER)
on CoNLL++
Probabilistic Models for High-Order Projective Dependency Parsing
This paper presents generalized probabilistic models for high-order projective dependency parsing and an algorithmic framework for learning these statistical models involving dependency trees.
