Search Results for author:
Found 46 papers, 25 papers with code
Netmarble AI Center’s WMT21 Automatic Post-Editing Shared Task Submission
As experimental results show, our APE system significantly improves the translations of provided MT results by -2. 848 and +3. 74 on the development dataset in terms of TER and BLEU, respectively.
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
We investigate efficient methods for training Large Language Models (LLMs) to possess capabilities in multiple specialized domains, such as coding, math reasoning and world knowledge.
Ranked #30 on
Question Answering
on TriviaQA
Demystifying CLIP Data
We believe that the main ingredient to the success of CLIP is its data and not the model architecture or pre-training objective.
DINOv2: Learning Robust Visual Features without Supervision
The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision.
Ranked #1 on
Image Classification
on CIFAR-10
Diffusion Models as Masked Autoencoders
There has been a longstanding belief that generation can facilitate a true understanding of visual data.
Adapting a Language Model While Preserving its General Knowledge
This paper shows that the existing methods are suboptimal and proposes a novel method to perform a more informed adaptation of the knowledge in the LM by (1) soft-masking the attention heads based on their importance to best preserve the general knowledge in the LM and (2) contrasting the representations of the general and the full (both general and domain knowledge) to learn an integrated representation with both general and domain-specific knowledge.
CiT: Curation in Training for Effective Vision-Language Data
Large vision-language models are generally applicable to many downstream tasks, but come at an exorbitant training cost that only large institutions can afford.
MAViL: Masked Audio-Video Learners
We present Masked Audio-Video Learners (MAViL) to train audio-visual representations.
Continual Training of Language Models for Few-Shot Learning
Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications.
Ranked #1 on
Continual Pretraining
on AG News
Masked Autoencoders that Listen
Following the Transformer encoder-decoder design in MAE, our Audio-MAE first encodes audio spectrogram patches with a high masking ratio, feeding only the non-masked tokens through encoder layers.
Ranked #2 on
Speaker Identification
on VoxCeleb1
(using extra training data)
Zero-Shot Aspect-Based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) typically requires in-domain annotated data for supervised training/fine-tuning.
CM3: A Causal Masked Multimodal Model of the Internet
We introduce CM3, a family of causally masked generative models trained over a large corpus of structured multi-modal documents that can contain both text and image tokens.
Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks
This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks.
Ranked #3 on
Continual Learning
on ASC (19 tasks)
CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks
The key novelty is a contrastive continual learning method that enables both knowledge transfer across tasks and knowledge distillation from old tasks to the new task, which eliminates the need for task ids in testing.
Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning
Although several papers have tried to deal with both CF and KT, our experiments show that they suffer from serious CF when the tasks do not have much shared knowledge.
Ranked #1 on
Continual Learning
on DSC (10 tasks)
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding
We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks.
Ranked #1 on
Temporal Action Localization
on CrossTask
(using extra training data)
Action Segmentation
Long Video Retrieval (Background Removed)
+4
Netmarble AI Center's WMT21 Automatic Post-Editing Shared Task Submission
As experimental results show, our APE system significantly improves the translations of provided MT results by -2. 848 and +3. 74 on the development dataset in terms of TER and BLEU, respectively.
HTLM: Hyper-Text Pre-Training and Prompting of Language Models
We introduce HTLM, a hyper-text language model trained on a large-scale web crawl.
Ranked #1 on
Table-to-Text Generation
on DART
VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding
We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks.
Ranked #2 on
Temporal Action Localization
on CrossTask
(using extra training data)
Co-Imitation Learning without Expert Demonstration
Imitation learning is a primary approach to improve the efficiency of reinforcement learning by exploiting the expert demonstrations.
Robust Small Object Detection on the Water Surface Through Fusion of Camera and Millimeter Wave Radar
In our work, we focus on a relatively unexplored task for USVs in inland waters: small object detection on water surfaces, which is of vital importance for safe autonomous navigation and USVs' certain missions such as floating waste cleaning.
Understanding Pre-trained BERT for Aspect-based Sentiment Analysis
Most features in the representation of an aspect are dedicated to the fine-grained semantics of the domain (or product category) and the aspect itself, instead of carrying summarized opinions from its context.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions
As there is no clean mapping for a user's free form utterance to an ontology, we first model the user preferences as estimated distributions over the system ontology and map the users' utterances to such distributions.
Controllable Text Generation with Focused Variation
This work introduces Focused-Variation Network (FVN), a novel model to control language generation.
User Memory Reasoning for Conversational Recommendation
We study a conversational recommendation model which dynamically manages users' past (offline) preferences and current (online) requests through a structured and cumulative user memory knowledge graph, to allow for natural interactions and accurate recommendations.
DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis
This paper focuses on learning domain-oriented language models driven by end tasks, which aims to combine the worlds of both general-purpose language models (such as ELMo and BERT) and domain-specific language understanding.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
A Failure of Aspect Sentiment Classifiers and an Adaptive Re-weighting Solution
Aspect-based sentiment classification (ASC) is an important task in fine-grained sentiment analysis.~Deep supervised ASC approaches typically model this task as a pair-wise classification task that takes an aspect and a sentence containing the aspect and outputs the polarity of the aspect in that sentence.
Modeling Multi-Action Policy for Task-Oriented Dialogues
Dialogue management (DM) plays a key role in the quality of the interaction with the user in a task-oriented dialogue system.
Flexibly-Structured Model for Task-Oriented Dialogues
It is based on a simple and practical yet very effective sequence-to-sequence approach, where language understanding and state tracking tasks are modeled jointly with a structured copy-augmented sequential decoder and a multi-label decoder for each slot.
Controlled CNN-based Sequence Labeling for Aspect Extraction
The modified CNN has two types of control modules.
BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
Since ReviewRC has limited training examples for RRC (and also for aspect-based sentiment analysis), we then explore a novel post-training approach on the popular language model BERT to enhance the performance of fine-tuning of BERT for RRC.
Review Conversational Reading Comprehension
Inspired by conversational reading comprehension (CRC), this paper studies a novel task of leveraging reviews as a source to build an agent that can answer multi-turn questions from potential consumers of online businesses.
Open-world Learning and Application to Product Classification
Classic supervised learning makes the closed-world assumption, meaning that classes seen in testing must have been seen in training.
Lifelong Domain Word Embedding via Meta-Learning
Learning high-quality domain word embeddings is important for achieving good performance in many NLP tasks.
Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction
Unlike other highly sophisticated supervised deep learning models, this paper proposes a novel and yet simple CNN model employing two types of pre-trained embeddings for aspect extraction: general-purpose embeddings and domain-specific embeddings.
Unseen Class Discovery in Open-world Classification
It is reasonable to assume that this knowledge can be transferred to the rejected examples and used to discover the hidden unseen classes in them.
Lifelong Word Embedding via Meta-Learning
We observe that domains are not isolated and a small domain corpus can leverage the learned knowledge from many past domains to augment that corpus in order to generate high-quality embeddings.
Product Function Need Recognition via Semi-supervised Attention Network
Functionality is of utmost importance to customers when they purchase products.
Dual Attention Network for Product Compatibility and Function Satisfiability Analysis
Product compatibility and their functionality are of utmost importance to customers when they purchase products, and to sellers and manufacturers when they sell products.
DOC: Deep Open Classification of Text Documents
As learning is used increasingly in dynamic open environments where some new/test documents may not belong to any of the training classes, identifying these novel documents during classification presents an important problem.
Supervised Complementary Entity Recognition with Augmented Key-value Pairs of Knowledge
Extracting opinion targets is an important task in sentiment analysis on product reviews and complementary entities (products) are one important type of opinion targets that may work together with the reviewed product.
Lifelong Learning CRF for Supervised Aspect Extraction
This paper makes a focused contribution to supervised aspect extraction.
Supervised Opinion Aspect Extraction by Exploiting Past Extraction Results
When "screen" appears in a review of a new domain (or product), it is likely to be an aspect too.
Mining Compatible/Incompatible Entities from Question and Answering via Yes/No Answer Classification using Distant Label Expansion
In this paper, we address the problem of extracting compatible and incompatible products from yes/no questions in PCQA.
CER: Complementary Entity Recognition via Knowledge Expansion on Large Unlabeled Product Reviews
One important product feature is the complementary entity (products) that may potentially work together with the reviewed product.
