Search Results for author: Hu Xu

Found 49 papers, 26 papers with code

Netmarble AI Center’s WMT21 Automatic Post-Editing Shared Task Submission

no code implementations WMT (EMNLP) 2021 Shinhyeok Oh, Sion Jang, Hu Xu, Shounan An, Insoo Oh

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.

Automatic Post-Editing Multi-Task Learning +1

Text Quality-Based Pruning for Efficient Training of Language Models

no code implementations26 Apr 2024 Vasu Sharma, Karthik Padthe, Newsha Ardalani, Kushal Tirumala, Russell Howes, Hu Xu, Po-Yao Huang, Shang-Wen Li, Armen Aghajanyan, Gargi Ghosh, Luke Zettlemoyer

In recent times training Language Models (LMs) have relied on computationally heavy training over massive datasets which makes this training process extremely laborious.

MoDE: CLIP Data Experts via Clustering

1 code implementation24 Apr 2024 Jiawei Ma, Po-Yao Huang, Saining Xie, Shang-Wen Li, Luke Zettlemoyer, Shih-Fu Chang, Wen-tau Yih, Hu Xu

The success of contrastive language-image pretraining (CLIP) relies on the supervision from the pairing between images and captions, which tends to be noisy in web-crawled data.

Clustering Image Classification +1

Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM

1 code implementation12 Mar 2024 Sainbayar Sukhbaatar, Olga Golovneva, Vasu Sharma, Hu Xu, Xi Victoria Lin, Baptiste Rozière, Jacob Kahn, Daniel Li, Wen-tau Yih, Jason Weston, Xian Li

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.

Arithmetic Reasoning Code Generation +6

Demystifying CLIP Data

2 code implementations28 Sep 2023 Hu Xu, Saining Xie, Xiaoqing Ellen Tan, Po-Yao Huang, Russell Howes, Vasu Sharma, Shang-Wen Li, Gargi Ghosh, Luke Zettlemoyer, Christoph Feichtenhofer

We believe that the main ingredient to the success of CLIP is its data and not the model architecture or pre-training objective.

Adapting a Language Model While Preserving its General Knowledge

2 code implementations21 Jan 2023 Zixuan Ke, Yijia Shao, Haowei Lin, Hu Xu, Lei Shu, Bing Liu

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.

Continual Learning General Knowledge +1

CiT: Curation in Training for Effective Vision-Language Data

1 code implementation ICCV 2023 Hu Xu, Saining Xie, Po-Yao Huang, Licheng Yu, Russell Howes, Gargi Ghosh, Luke Zettlemoyer, Christoph Feichtenhofer

Large vision-language models are generally applicable to many downstream tasks, but come at an exorbitant training cost that only large institutions can afford.

Continual Training of Language Models for Few-Shot Learning

3 code implementations11 Oct 2022 Zixuan Ke, Haowei Lin, Yijia Shao, Hu Xu, Lei Shu, Bing Liu

Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications.

Continual Learning Continual Pretraining +2

Masked Autoencoders that Listen

4 code implementations13 Jul 2022 Po-Yao Huang, Hu Xu, Juncheng Li, Alexei Baevski, Michael Auli, Wojciech Galuba, Florian Metze, Christoph Feichtenhofer

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)

Audio Classification Decoder +2

Zero-Shot Aspect-Based Sentiment Analysis

no code implementations4 Feb 2022 Lei Shu, Hu Xu, Bing Liu, Jiahua Chen

Aspect-based sentiment analysis (ABSA) typically requires in-domain annotated data for supervised training/fine-tuning.

Aspect-Based Sentiment Analysis Aspect Extraction +2

CM3: A Causal Masked Multimodal Model of the Internet

no code implementations19 Jan 2022 Armen Aghajanyan, Bernie Huang, Candace Ross, Vladimir Karpukhin, Hu Xu, Naman Goyal, Dmytro Okhonko, Mandar Joshi, Gargi Ghosh, Mike Lewis, Luke Zettlemoyer

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.

Entity Disambiguation Entity Linking

CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks

1 code implementation EMNLP 2021 Zixuan Ke, Bing Liu, Hu Xu, Lei Shu

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.

Classification Continual Learning +6

Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning

1 code implementation NeurIPS 2021 Zixuan Ke, Bing Liu, Nianzu Ma, Hu Xu, Lei Shu

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.

Continual Learning Language Modelling +2

VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding

2 code implementations EMNLP 2021 Hu Xu, Gargi Ghosh, Po-Yao Huang, Dmytro Okhonko, Armen Aghajanyan, Florian Metze, Luke Zettlemoyer, Christoph Feichtenhofer

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

no code implementations14 Sep 2021 Shinhyeok Oh, Sion Jang, Hu Xu, Shounan An, Insoo Oh

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.

Automatic Post-Editing Multi-Task Learning +1

Co-Imitation Learning without Expert Demonstration

no code implementations27 Mar 2021 Kun-Peng Ning, Hu Xu, Kun Zhu, Sheng-Jun Huang

Imitation learning is a primary approach to improve the efficiency of reinforcement learning by exploiting the expert demonstrations.

Imitation Learning

Robust Small Object Detection on the Water Surface Through Fusion of Camera and Millimeter Wave Radar

no code implementations ICCV 2021 Yuwei Cheng, Hu Xu, Yimin Liu

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.

Autonomous Navigation Object +2

Understanding Pre-trained BERT for Aspect-based Sentiment Analysis

2 code implementations COLING 2020 Hu Xu, Lei Shu, Philip S. Yu, Bing Liu

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

1 code implementation Findings (EMNLP) 2021 Zhiyu Chen, Honglei Liu, Hu Xu, Seungwhan Moon, Hao Zhou, Bing Liu

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.

Dialogue State Tracking

User Memory Reasoning for Conversational Recommendation

no code implementations COLING 2020 Hu Xu, Seungwhan Moon, Honglei Liu, Pararth Shah, Bing Liu, Philip S. Yu

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

1 code implementation Findings of the Association for Computational Linguistics 2020 Hu Xu, Bing Liu, Lei Shu, Philip S. Yu

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

1 code implementation4 Nov 2019 Hu Xu, Bing Liu, Lei Shu, Philip S. Yu

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.

General Classification Sentence +2

Modeling Multi-Action Policy for Task-Oriented Dialogues

1 code implementation IJCNLP 2019 Lei Shu, Hu Xu, Bing Liu, Piero Molino

Dialogue management (DM) plays a key role in the quality of the interaction with the user in a task-oriented dialogue system.

Dialogue Management Management

Flexibly-Structured Model for Task-Oriented Dialogues

1 code implementation WS 2019 Lei Shu, Piero Molino, Mahdi Namazifar, Hu Xu, Bing Liu, Huaixiu Zheng, Gokhan Tur

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.

Decoder Task-Oriented Dialogue Systems +1

BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis

1 code implementation NAACL 2019 Hu Xu, Bing Liu, Lei Shu, Philip S. Yu

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.

Aspect-Based Sentiment Analysis Aspect Extraction +1

Review Conversational Reading Comprehension

1 code implementation3 Feb 2019 Hu Xu, Bing Liu, Lei Shu, Philip S. Yu

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.

Language Modelling Machine Reading Comprehension

Open-world Learning and Application to Product Classification

1 code implementation17 Sep 2018 Hu Xu, Bing Liu, Lei Shu, P. Yu

Classic supervised learning makes the closed-world assumption, meaning that classes seen in testing must have been seen in training.

Classification General Classification +1

Lifelong Domain Word Embedding via Meta-Learning

1 code implementation25 May 2018 Hu Xu, Bing Liu, Lei Shu, Philip S. Yu

Learning high-quality domain word embeddings is important for achieving good performance in many NLP tasks.

Meta-Learning Word Embeddings

Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction

2 code implementations ACL 2018 Hu Xu, Bing Liu, Lei Shu, Philip S. Yu

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.

Aspect Extraction

Unseen Class Discovery in Open-world Classification

1 code implementation ICLR 2018 Lei Shu, Hu Xu, Bing Liu

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.

Classification Clustering +1

Lifelong Word Embedding via Meta-Learning

no code implementations ICLR 2018 Hu Xu, Bing Liu, Lei Shu, Philip S. Yu

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.

Meta-Learning Word Embeddings

Dual Attention Network for Product Compatibility and Function Satisfiability Analysis

no code implementations6 Dec 2017 Hu Xu, Sihong Xie, Lei Shu, Philip S. Yu

Product compatibility and their functionality are of utmost importance to customers when they purchase products, and to sellers and manufacturers when they sell products.

Product Function Need Recognition via Semi-supervised Attention Network

no code implementations6 Dec 2017 Hu Xu, Sihong Xie, Lei Shu, Philip S. Yu

Functionality is of utmost importance to customers when they purchase products.

DOC: Deep Open Classification of Text Documents

no code implementations EMNLP 2017 Lei Shu, Hu Xu, Bing Liu

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.

General Classification text-classification +1

Supervised Complementary Entity Recognition with Augmented Key-value Pairs of Knowledge

no code implementations29 May 2017 Hu Xu, Lei Shu, Philip S. Yu

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.

Sentiment Analysis

Supervised Opinion Aspect Extraction by Exploiting Past Extraction Results

no code implementations23 Dec 2016 Lei Shu, Bing Liu, Hu Xu, Annice Kim

When "screen" appears in a review of a new domain (or product), it is likely to be an aspect too.

Aspect Extraction Sentiment Analysis

CER: Complementary Entity Recognition via Knowledge Expansion on Large Unlabeled Product Reviews

no code implementations4 Dec 2016 Hu Xu, Sihong Xie, Lei Shu, Philip S. Yu

One important product feature is the complementary entity (products) that may potentially work together with the reviewed product.

Cannot find the paper you are looking for? You can Submit a new open access paper.