Search Results for author:
Found 22 papers, 10 papers with code
SHAPE : Shifted Absolute Position Embedding for Transformers
Position representation is crucial for building position-aware representations in Transformers.
Spike No More: Stabilizing the Pre-training of Large Language Models
Loss spikes often occur during pre-training of large language models.
B2T Connection: Serving Stability and Performance in Deep Transformers
Recent Transformers tend to be Pre-LN because, in Post-LN with deep Transformers (e. g., those with ten or more layers), the training is often unstable, resulting in useless models.
Decomposing NeRF for Editing via Feature Field Distillation
Emerging neural radiance fields (NeRF) are a promising scene representation for computer graphics, enabling high-quality 3D reconstruction and novel view synthesis from image observations.
Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model
Ensembling is a popular method used to improve performance as a last resort.
Instance-Based Neural Dependency Parsing
Interpretable rationales for model predictions are crucial in practical applications.
SHAPE: Shifted Absolute Position Embedding for Transformers
Position representation is crucial for building position-aware representations in Transformers.
Efficient Estimation of Influence of a Training Instance
Understanding the influence of a training instance on a neural network model leads to improving interpretability.
Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition
Interpretable rationales for model predictions play a critical role in practical applications.
All Word Embeddings from One Embedding
The proposed method, ALONE (all word embeddings from one), constructs the embedding of a word by modifying the shared embedding with a filter vector, which is word-specific but non-trainable.
Ranked #3 on
Text Summarization
on DUC 2004 Task 1
Data Interpolating Prediction: Alternative Interpretation of Mixup
Data augmentation by mixing samples, such as Mixup, has widely been used typically for classification tasks.
Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN
Training of Generative Adversarial Network (GAN) on a video dataset is a challenge because of the sheer size of the dataset and the complexity of each observation.
DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback
A remedy for this is to train an agent with real-time feedback from a human observer who immediately gives rewards for some actions.
Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions
As well as deriving PMI from mutual information, we derive this new measure from the Hilbert--Schmidt independence criterion (HSIC); thus, we call the new measure the pointwise HSIC (PHSIC).
Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations
We stochastically replace words with other words that are predicted by a bi-directional language model at the word positions.
Unsupervised Learning of Style-sensitive Word Vectors
This paper presents the first study aimed at capturing stylistic similarity between words in an unsupervised manner.
Generating Stylistically Consistent Dialog Responses with Transfer Learning
We propose a novel, data-driven, and stylistically consistent dialog response generation system.
Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions
In this paper, we propose the first comprehensive system that can handle unconstrained spoken language and is able to effectively resolve ambiguity in spoken instructions.
A Neural Language Model for Dynamically Representing the Meanings of Unknown Words and Entities in a Discourse
This study addresses the problem of identifying the meaning of unknown words or entities in a discourse with respect to the word embedding approaches used in neural language models.
An RNN-based Binary Classifier for the Story Cloze Test
In this paper we present a system that performs this task using a supervised binary classifier on top of a recurrent neural network to predict the probability that a given story ending is correct.
