Search Results for author:
Found 89 papers, 45 papers with code
PALM: Pre-training an Autoencoding\&Autoregressive Language Model for Context-conditioned Generation
An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks covering generative question answering (Rank 1 on the official MARCO leaderboard), abstractive summarization on CNN/DailyMail as well as Gigaword, question generation on SQuAD, and conversational response generation on Cornell Movie Dialogues.
Abstractive Text Summarization
Conversational Response Generation
+9
Adaptive Feature Discrimination and Denoising for Asymmetric Text Matching
Asymmetric text matching has becoming increasingly indispensable for many downstream tasks (e. g., IR and NLP).
Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality
To address this problem, we propose the first two-timescale single-loop IRL algorithm under neural network parameterized reward and provide a non-asymptotic convergence analysis under overparameterization.
MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audio
The rapid advancement of large language models (LLMs) and artificial intelligence-generated content (AIGC) has accelerated AI-native applications, such as AI-based storybooks that automate engaging story production for children.
WritingBench: A Comprehensive Benchmark for Generative Writing
Recent advancements in large language models (LLMs) have significantly enhanced text generation capabilities, yet evaluating their performance in generative writing remains a challenge.
ProFuser: Progressive Fusion of Large Language Models
While fusing the capacities and advantages of various large language models (LLMs) offers a pathway to construct more powerful and versatile models, a fundamental challenge is to properly select advantageous model during the training.
Efficient Sparse Attention needs Adaptive Token Release
In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide array of text-centric tasks.
Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment
Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI.
Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment
State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning (SFT), where the model is fine-tuned by learning from human demonstration data; 2) Preference learning, where preference data is used to learn a reward model, which is in turn used by a reinforcement learning (RL) step to fine-tune the model.
SocialBench: Sociality Evaluation of Role-Playing Conversational Agents
In this paper, we introduce SocialBench, the first benchmark designed to systematically evaluate the sociality of role-playing conversational agents at both individual and group levels of social interactions.
Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training
In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment.
Side Information-Driven Session-based Recommendation: A Survey
Emerging efforts incorporate various kinds of side information into their methods for enhancing task performance.
Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval
In this work, we propose the UNIFY framework, which learns lexicon representations to capture fine-grained semantics and combines the strengths of latent and lexicon representations for video-text retrieval.
Small LLMs Are Weak Tool Learners: A Multi-LLM Agent
Each component is implemented by a single LLM that focuses on a specific capability and collaborates with others to accomplish the task.
Knowledge Distillation of Black-Box Large Language Models
Given the exceptional performance of proprietary large language models (LLMs) like GPT-4, recent research has increasingly focused on boosting the capabilities of smaller models through knowledge distillation (KD) from these powerful yet black-box teachers.
Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection
Vision Transformers (ViTs) have become increasingly popular in large-scale Vision and Language Pre-training (VLP) models.
mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Model
In this work, towards a more versatile copilot for academic paper writing, we mainly focus on strengthening the multi-modal diagram analysis ability of Multimodal LLMs.
Bi-Preference Learning Heterogeneous Hypergraph Networks for Session-based Recommendation
Secondly, price preference and interest preference are interdependent and collectively determine user choice, necessitating that we jointly consider both price and interest preference for intent modeling.
On the Opportunities of Green Computing: A Survey
To tackle the challenges of computing resources and environmental impact of AI, Green Computing has become a hot research topic.
One Model for All: Large Language Models are Domain-Agnostic Recommendation Systems
We expect that by mixing the user's behaviors across different domains, we can exploit the common knowledge encoded in the pre-trained language model to alleviate the problems of data sparsity and cold start problems.
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model
Text is ubiquitous in our visual world, conveying crucial information, such as in documents, websites, and everyday photographs.
Beyond Co-occurrence: Multi-modal Session-based Recommendation
(2) How to fuse these heterogeneous descriptive information to comprehensively infer user interests?
A Bayesian Approach to Robust Inverse Reinforcement Learning
We consider a Bayesian approach to offline model-based inverse reinforcement learning (IRL).
ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models
Large language models (LLMs) have recently demonstrated remarkable capabilities to comprehend human intentions, engage in reasoning, and design planning-like behavior.
Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community
The research field of Information Retrieval (IR) has evolved significantly, expanding beyond traditional search to meet diverse user information needs.
BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization
Specifically, We incorporate a Text-Semantics-Aware Patch Selector (TSPS) into the ViT backbone to perform a coarse-grained visual token extraction and then attach a flexible Transformer-based Patch Abstraction Decoder (PAD) upon the backbone for top-level visual abstraction.
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
Nevertheless, without in-domain training, these models tend to ignore fine-grained OCR features, such as sophisticated tables or large blocks of text, which are essential for OCR-free document understanding.
Multi-Scenario Ranking with Adaptive Feature Learning
Recently, Multi-Scenario Learning (MSL) is widely used in recommendation and retrieval systems in the industry because it facilitates transfer learning from different scenarios, mitigating data sparsity and reducing maintenance cost.
Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks
In addition, to facilitate a comprehensive evaluation of video-language models, we carefully build the largest human-annotated Chinese benchmarks covering three popular video-language tasks of cross-modal retrieval, video captioning, and video category classification.
Unconfounded Propensity Estimation for Unbiased Ranking
The goal of unbiased learning to rank (ULTR) is to leverage implicit user feedback for optimizing learning-to-rank systems.
mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality
Our code, pre-trained model, instruction-tuned models, and evaluation set are available at https://github. com/X-PLUG/mPLUG-Owl.
Ranked #1 on
Visual Question Answering (VQA)
on HallusionBench
(Question Pair Acc metric)
Visual Question Answering (VQA)
Zero-Shot Video Question Answer
On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training
In this study, we propose to enhance the ABSA robustness by systematically rethinking the bottlenecks from all possible angles, including model, data, and training.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
ChatPLUG: Open-Domain Generative Dialogue System with Internet-Augmented Instruction Tuning for Digital Human
In this paper, we present ChatPLUG, a Chinese open-domain dialogue system for digital human applications that instruction finetunes on a wide range of dialogue tasks in a unified internet-augmented format.
DiffuRec: A Diffusion Model for Sequential Recommendation
Mainstream solutions to Sequential Recommendation (SR) represent items with fixed vectors.
When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning
Offline inverse reinforcement learning (Offline IRL) aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent.
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
In contrast to predominant paradigms of solely relying on sequence-to-sequence generation or encoder-based instance discrimination, mPLUG-2 introduces a multi-module composition network by sharing common universal modules for modality collaboration and disentangling different modality modules to deal with modality entanglement.
Ranked #1 on
Video Captioning
on MSR-VTT
Learning Trajectory-Word Alignments for Video-Language Tasks
To amend this, we propose a novel TW-BERT to learn Trajectory-Word alignment by a newly designed trajectory-to-word (T2W) attention for solving video-language tasks.
BUS: Efficient and Effective Vision-Language Pre-Training with Bottom-Up Patch Summarization.
In this paper, we propose a Bottom-Up Patch Summarization approach named BUS which is inspired by the Document Summarization Task in NLP to learn a concise visual summary of lengthy visual token sequences, guided by textual semantics.
Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees
To reduce the computational burden of a nested loop, novel methods such as SQIL [1] and IQ-Learn [2] emphasize policy estimation at the expense of reward estimation accuracy.
Inheriting the Wisdom of Predecessors: A Multiplex Cascade Framework for Unified Aspect-based Sentiment Analysis
So far, aspect-based sentiment analysis (ABSA) has involved with total seven subtasks, in which, however the interactions among them have been left unexplored sufficiently.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+4
Global inference with explicit syntactic and discourse structures for dialogue-level relation extraction
In our global reasoning framework, D2G and ARG work collaboratively, iteratively performing lexical, syntactic and semantic information exchange and representation learning over the entire dialogue context.
Ranked #3 on
Dialog Relation Extraction
on DialogRE
Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation
Further ablation studies validate the effectiveness of our model design and benefits of the new MBHT framework.
Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding
Multi-modal document pre-trained models have proven to be very effective in a variety of visually-rich document understanding (VrDU) tasks.
Safe-FinRL: A Low Bias and Variance Deep Reinforcement Learning Implementation for High-Freq Stock Trading
In recent years, many practitioners in quantitative finance have attempted to use Deep Reinforcement Learning (DRL) to build better quantitative trading (QT) strategies.
Automatic Expert Selection for Multi-Scenario and Multi-Task Search
At each multi-scenario/multi-task layer, a novel expert selection algorithm is proposed to automatically identify scenario-/task-specific and shared experts for each input.
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections
Large-scale pretrained foundation models have been an emerging paradigm for building artificial intelligence (AI) systems, which can be quickly adapted to a wide range of downstream tasks.
Ranked #1 on
Image Captioning
on COCO Captions
When Multi-Level Meets Multi-Interest: A Multi-Grained Neural Model for Sequential Recommendation
Specifically, multi-interest methods such as ComiRec and MIMN, focus on extracting different interests for a user by performing historical item clustering, while graph convolution methods including TGSRec and SURGE elect to refine user preferences based on multi-level correlations between historical items.
Knowledge Graph Contrastive Learning for Recommendation
However, the success of such methods relies on the high quality knowledge graphs, and may not learn quality representations with two challenges: i) The long-tail distribution of entities results in sparse supervision signals for KG-enhanced item representation; ii) Real-world knowledge graphs are often noisy and contain topic-irrelevant connections between items and entities.
Do Loyal Users Enjoy Better Recommendations? Understanding Recommender Accuracy from a Time Perspective
Our study offers a different perspective to understand recommender accuracy, and our findings could trigger a revisit of recommender model design.
Achieving Human Parity on Visual Question Answering
The Visual Question Answering (VQA) task utilizes both visual image and language analysis to answer a textual question with respect to an image.
Ranked #8 on
Visual Question Answering (VQA)
on VQA v2 test-dev
Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation
In this paper, we propose a novel concept-aware denoising graph neural network (named CONDE) for micro-video recommendation.
Grid-VLP: Revisiting Grid Features for Vision-Language Pre-training
Existing approaches to vision-language pre-training (VLP) heavily rely on an object detector based on bounding boxes (regions), where salient objects are first detected from images and then a Transformer-based model is used for cross-modal fusion.
Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction
This work focuses on generative QA which aims to generate an abstractive answer to a given question instead of extracting an answer span from a provided passage.
MinD at SemEval-2021 Task 6: Propaganda Detection using Transfer Learning and Multimodal Fusion
We describe our systems of subtask1 and subtask3 for SemEval-2021 Task 6 on Detection of Persuasion Techniques in Texts and Images.
E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks.
StructuralLM: Structural Pre-training for Form Understanding
Large pre-trained language models achieve state-of-the-art results when fine-tuned on downstream NLP tasks.
Path-based Deep Network for Candidate Item Matching in Recommenders
PDN utilizes Trigger Net to capture the user's interest in each of his/her interacted item, and Similarity Net to evaluate the similarity between each interacted item and the target item based on these items' profile and CF information.
SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels
Vision-language pre-training (VLP) on large-scale image-text pairs has recently witnessed rapid progress for learning cross-modal representations.
UnihanLM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database
Chinese and Japanese share many characters with similar surface morphology.
A Critical Study on Data Leakage in Recommender System Offline Evaluation
To evaluate recommendation systems in a realistic manner in offline setting, we propose a timeline scheme, which calls for a revisit of the recommendation model design.
Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification
The idea is to allow the dependency graph to guide the representation learning of the transformer encoder and vice versa.
A Re-visit of the Popularity Baseline in Recommender Systems
On the widely used MovieLens dataset, we show that the performance of popularity could be significantly improved by 70% or more, if we consider the popular items at the time point when a user interacts with the system.
ESAM: Discriminative Domain Adaptation with Non-Displayed Items to Improve Long-Tail Performance
Most of ranking models are trained only with displayed items (most are hot items), but they are utilized to retrieve items in the entire space which consists of both displayed and non-displayed items (most are long-tail items).
CATN: Cross-Domain Recommendation for Cold-Start Users via Aspect Transfer Network
Given two relevant domains (e. g., Book and Movie), users may have interactions with items in one domain but not in the other domain.
MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization
Recently, large-scale datasets have vastly facilitated the development in nearly all domains of Natural Language Processing.
PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation
An extensive set of experiments show that PALM achieves new state-of-the-art results on a variety of language generation benchmarks covering generative question answering (Rank 1 on the official MARCO leaderboard), abstractive summarization on CNN/DailyMail as well as Gigaword, question generation on SQuAD, and conversational response generation on Cornell Movie Dialogues.
Ranked #1 on
Text Generation
on CNN/Daily Mail
Abstractive Text Summarization
Conversational Response Generation
+9
CASE: Context-Aware Semantic Expansion
In this study, we demonstrate that annotations for this task can be harvested at scale from existing corpora, in a fully automatic manner.
Cross-Domain Recommendation via Preference Propagation GraphNet
We find there are mainly three problems in their formulations: 1) their knowledge transfer is unaware of the cross-domain graph structure.
Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders
Conditional Text Generation has drawn much attention as a topic of Natural Language Generation (NLG) which provides the possibility for humans to control the properties of generated contents.
Incorporating External Knowledge into Machine Reading for Generative Question Answering
Different from existing work on knowledge-aware QA, we focus on a more challenging task of leveraging external knowledge to generate answers in natural language for a given question with context.
Exploiting Multiple Embeddings for Chinese Named Entity Recognition
Identifying the named entities mentioned in text would enrich many semantic applications at the downstream level.
Chinese Named Entity Recognition
named-entity-recognition
+2
Obj-GloVe: Scene-Based Contextual Object Embedding
Recently, with the prevalence of large-scale image dataset, the co-occurrence information among classes becomes rich, calling for a new way to exploit it to facilitate inference.
A Capsule Network for Recommendation and Explaining What You Like and Dislike
A sentiment capsule architecture with a novel Routing by Bi-Agreement mechanism is proposed to identify the informative logic unit and the sentiment based representations in user-item level for rating prediction.
A Review-Driven Neural Model for Sequential Recommendation
Given a sequence of historical purchased items for a user, we devise a novel hierarchical attention over attention mechanism to capture sequential patterns at both union-level and individual-level.
Targeted Sentiment Analysis: A Data-Driven Categorization
Targeted sentiment analysis (TSA), also known as aspect based sentiment analysis (ABSA), aims at detecting fine-grained sentiment polarity towards targets in a given opinion document.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
Review-Driven Answer Generation for Product-Related Questions in E-Commerce
Then, we devise a mechanism to identify the relevant information from the noise-prone review snippets and incorporate this information to guide the answer generation.
Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
In this article, we review research works that address this difference and generatetextual adversarial examples on DNNs.
DLocRL: A Deep Learning Pipeline for Fine-Grained Location Recognition and Linking in Tweets
Recognizing and linking such fine-grained location mentions to well-defined location profiles are beneficial for retrieval and recommendation systems.
A Survey on Deep Learning for Named Entity Recognition
In this paper, we provide a comprehensive review on existing deep learning techniques for NER.
Enhancing Topic Modeling for Short Texts with Auxiliary Word Embeddings
Recent studies show that the Dirichlet Multinomial Mixture (DMM) model is effective for topic inference over short texts by assuming that each piece of short text is generated by a single topic.
Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embedding
Recent efforts on this issue suggest training a neighborhood aggregator in conjunction with the conventional entity and relation embeddings, which may help embed new entities inductively via their existing neighbors.
S2SPMN: A Simple and Effective Framework for Response Generation with Relevant Information
In this paper, we propose Sequence to Sequence with Prototype Memory Network (S2SPMN) to exploit the relevant information provided by the large dialogue corpus to enhance response generation.
A Deep Relevance Model for Zero-Shot Document Filtering
In the era of big data, focused analysis for diverse topics with a short response time becomes an urgent demand.
Guiding Generation for Abstractive Text Summarization Based on Key Information Guide Network
Then, we introduce a Key Information Guide Network (KIGN), which encodes the keywords to the key information representation, to guide the process of generation.
Ranked #10 on
Text Summarization
on CNN / Daily Mail (Anonymized)
Pair-Linking for Collective Entity Disambiguation: Two Could Be Better Than All
For the first time, we show that the semantic relationships between the mentioned entities are in fact less dense than expected.
Multi-label Dataless Text Classification with Topic Modeling
With a few seed words relevant to each category, SMTM conducts multi-label classification for a collection of documents without any labeled document.
NEXT: A Neural Network Framework for Next POI Recommendation
Inspired by the recent success of neural networks in many areas, in this paper, we present a simple but effective neural network framework for next POI recommendation, named NEXT.
