Search Results for author:
Found 83 papers, 36 papers with code
MMEKG: Multi-modal Event Knowledge Graph towards Universal Representation across Modalities
Events are fundamental building blocks of real-world happenings.
Sketch: A Toolkit for Streamlining LLM Operations
Sketch comprises the following components: (1) a suite of task description schemas and prompt templates encompassing various NLP tasks; (2) a user-friendly, interactive process for building structured output LLM services tailored to various NLP tasks; (3) an open-source dataset for output format control, along with tools for dataset construction; and (4) an open-source model based on LLaMA3-8B-Instruct that adeptly comprehends and adheres to output formatting instructions.
Not All Videos Become Outdated: Short-Video Recommendation by Learning to Deconfound Release Interval Bias
Our analysis, based on a causal graph modeling short-video recommendation, suggests that the release interval serves as a confounder, establishing a backdoor path between users and videos.
Open-domain Implicit Format Control for Large Language Model Generation
Controlling the format of outputs generated by large language models (LLMs) is a critical functionality in various applications.
The Crowd in MOOCs: A Study of Learning Patterns at Scale
The increasing availability of learning activity data in Massive Open Online Courses (MOOCs) enables us to conduct a large-scale analysis of learners' learning behavior.
TVR-Ranking: A Dataset for Ranked Video Moment Retrieval with Imprecise Queries
To facilitate research in RVMR, we develop the TVR-Ranking dataset, based on the raw videos and existing moment annotations provided in the TVR dataset.
52B to 1T: Lessons Learned via Tele-FLM Series
Large Language Models (LLMs) represent a significant stride toward Artificial General Intelligence.
MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations
Moreover, 33. 2% of the questions are cross-page questions requiring evidence across multiple pages.
Tele-FLM Technical Report
Large language models (LLMs) have showcased profound capabilities in language understanding and generation, facilitating a wide array of applications.
Beyond Collaborative Filtering: A Relook at Task Formulation in Recommender Systems
That is, we often conceptualize RecSys as the task of predicting missing values in a static user-item interaction matrix, rather than predicting a user's decision on the next interaction within a dynamic, changing, and application-specific context.
Not All Layers of LLMs Are Necessary During Inference
That is, not all layers of LLMs are necessary during inference.
Recommender for Its Purpose: Repeat and Exploration in Food Delivery Recommendations
This paper emphasizes the importance of dedicated analyses and methods for domain-specific characteristics for the recommender system studies.
SciAgent: Tool-augmented Language Models for Scientific Reasoning
To make this task more practical and solvable for LLMs, we introduce a new task setting named tool-augmented scientific reasoning.
Parameter-Efficient Conversational Recommender System as a Language Processing Task
Conversational recommender systems (CRS) aim to recommend relevant items to users by eliciting user preference through natural language conversation.
On Context Utilization in Summarization with Large Language Models
In this paper, we conduct the first comprehensive study on context utilization and position bias in summarization.
Towards Verifiable Generation: A Benchmark for Knowledge-aware Language Model Attribution
Although achieving great success, Large Language Models (LLMs) usually suffer from unreliable hallucinations.
An Image Dataset for Benchmarking Recommender Systems with Raw Pixels
Then, to show the effectiveness of the dataset's image features, we substitute the itemID embeddings (from IDNet) with a powerful vision encoder that represents items using their raw image pixels.
Ranked #1 on
Recommendation Systems
on PixelRec
FLM-101B: An Open LLM and How to Train It with $100K Budget
We demonstrate that a 101B-parameter LLM with 0. 31T tokens can be trained with a budget of 100K US dollars.
Our Model Achieves Excellent Performance on MovieLens: What Does it Mean?
First, there are significant differences in user interactions at the different stages when a user interacts with the MovieLens platform.
Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Prompting
However, the fine-tuned PLMs often overwhelmingly focus on the textual information and overlook structural knowledge.
MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction
Given a query, the task of Natural Language Video Localization (NLVL) is to localize a temporal moment in an untrimmed video that semantically matches the query.
Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation
Goal-oriented Script Generation is a new task of generating a list of steps that can fulfill the given goal.
Shall We Trust All Relational Tuples by Open Information Extraction? A Study on Speculation Detection
We formally define the research problem of tuple-level speculation detection and conduct a detailed data analysis on the LSOIE dataset which contains labels for speculative tuples.
Open Information Extraction via Chunks
Accordingly, we propose a simple BERT-based model for sentence chunking, and propose Chunk-OIE for tuple extraction on top of SaC.
Retraining A Graph-based Recommender with Interests Disentanglement
Then we blend the historical and new preferences in the form of node embeddings in the new graph, through a Disentanglement Module.
Few-shot Event Detection: An Empirical Study and a Unified View
Few-shot event detection (ED) has been widely studied, while this brings noticeable discrepancies, e. g., various motivations, tasks, and experimental settings, that hinder the understanding of models for future progress. This paper presents a thorough empirical study, a unified view of ED models, and a better unified baseline.
FreeLM: Fine-Tuning-Free Language Model
FreeLM outperforms large models e. g., GPT-3 and InstructGPT, on a range of language understanding tasks in experiments.
nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales
With around 14% of the one-time pre-training cost, we can accurately forecast the loss for models up to 52B.
DiffuRec: A Diffusion Model for Sequential Recommendation
Mainstream solutions to Sequential Recommendation (SR) represent items with fixed vectors.
GCRE-GPT: A Generative Model for Comparative Relation Extraction
Given comparative text, comparative relation extraction aims to extract two targets (\eg two cameras) in comparison and the aspect they are compared for (\eg image quality).
Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!
Large Language Models (LLMs) have made remarkable strides in various tasks.
Dataset vs Reality: Understanding Model Performance from the Perspective of Information Need
The differences in these datasets can be attributed to the different information needs of the specific research tasks.
Syntactic Multi-view Learning for Open Information Extraction
In this paper, we model both constituency and dependency trees into word-level graphs, and enable neural OpenIE to learn from the syntactic structures.
Ranked #1 on
Open Information Extraction
on LSOIE-wiki
Perplexity from PLM Is Unreliable for Evaluating Text Quality
Recently, amounts of works utilize perplexity~(PPL) to evaluate the quality of the generated text.
Take a Fresh Look at Recommender Systems from an Evaluation Standpoint
We then move on to explore the two implications of neglecting a global timeline during evaluation: data leakage and oversimplification of user preference modeling.
CofeNet: Context and Former-Label Enhanced Net for Complicated Quotation Extraction
CofeNet is able to extract complicated quotations with components of variable lengths and complicated structures.
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.
A Survey on Neural Open Information Extraction: Current Status and Future Directions
Open Information Extraction (OpenIE) facilitates domain-independent discovery of relational facts from large corpora.
Ranked #1 on
Open Information Extraction
on CaRB
Natural Language Understanding
Open-Domain Question Answering
+1
A Study on Transformer Configuration and Training Objective
In this paper, we revisit these conventional configurations.
Ranked #103 on
Image Classification
on ImageNet
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.
Chat-Capsule: A Hierarchical Capsule for Dialog-level Emotion Analysis
These models hence are not optimized for dialog-level emotion detection, i. e. to predict the emotion category of a dialog as a whole.
Aspect-based Sentiment Analysis through EDU-level Attentions
A sentence may express sentiments on multiple aspects.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Temporal Sentence Grounding in Videos: A Survey and Future Directions
Temporal sentence grounding in videos (TSGV), \aka natural language video localization (NLVL) or video moment retrieval (VMR), aims to retrieve a temporal moment that semantically corresponds to a language query from an untrimmed video.
Towards Reducing Manual Workload in Technology-Assisted Reviews: Estimating Ranking Performance
This practice, known as screening prioritization (ie., document ranking approach), speeds up the process of conducting a SR as the documents labelled as relevant can move to the next tasks earlier.
Mirror Matching: Document Matching Approach in Seed-driven Document Ranking for Medical Systematic Reviews
Alternatively, we formulate the SDR task as finding similar documents to a query document and produce rankings based on similarity scores.
Towards Debiasing Temporal Sentence Grounding in Video
In this paper, we propose two debiasing strategies, data debiasing and model debiasing, to "force" a TSGV model to capture cross-modal interactions.
A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict
Based on this dual-channel framework, we design the Dual-Channel Network~(DC-Net) to recognize sentiment conflict.
SelfCF: A Simple Framework for Self-supervised Collaborative Filtering
Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions.
Parallel Attention Network with Sequence Matching for Video Grounding
In this work, we propose a Parallel Attention Network with Sequence matching (SeqPAN) to address the challenges in this task: multi-modal representation learning, and target moment boundary prediction.
Video Corpus Moment Retrieval with Contrastive Learning
We adopt the first approach and introduce two contrastive learning objectives to refine video encoder and text encoder to learn video and text representations separately but with better alignment for VCMR.
DocOIE: A Document-level Context-Aware Dataset for OpenIE
Both DocOIE dataset and DocIE model are released for public.
Ranked #1 on
Open Information Extraction
on DocOIE-transportation
Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference
Recent advances in reinforcement learning have inspired increasing interest in learning user modeling adaptively through dynamic interactions, e. g., in reinforcement learning based recommender systems.
Natural Language Video Localization: A Revisit in Span-based Question Answering Framework
Our study suggests that the span-based QA framework is an effective strategy to solve the NLVL problem.
An Embarrassingly Simple Model for Dialogue Relation Extraction
Dialogue relation extraction (RE) is to predict the relation type of two entities mentioned in a dialogue.
Ranked #9 on
Dialog Relation Extraction
on DialogRE
GDPNet: Refining Latent Multi-View Graph for Relation Extraction
Recent advances on RE task are from BERT-based sequence modeling and graph-based modeling of relationships among the tokens in the sequence.
Ranked #4 on
Dialog Relation Extraction
on DialogRE
(F1c (v1) metric)
Generative Inverse Deep Reinforcement Learning for Online Recommendation
Deep reinforcement learning uses a reward function to learn user's interest and to control the learning process.
Pre-training Graph Transformer with Multimodal Side Information for Recommendation
Side information of items, e. g., images and text description, has shown to be effective in contributing to accurate recommendations.
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.
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.
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.
Span-based Localizing Network for Natural Language Video Localization
Given an untrimmed video and a text query, natural language video localization (NLVL) is to locate a matching span from the video that semantically corresponds to the query.
Efficient Approximation Algorithms for Adaptive Influence Maximization
In this paper, we propose the first practical algorithm for the adaptive IM problem that could provide the worst-case approximation guarantee of $1-\mathrm{e}^{\rho_b(\varepsilon-1)}$, where $\rho_b=1-(1-1/b)^b$ and $\varepsilon \in (0, 1)$ is a user-specified parameter.
Social and Information Networks
UFTR: A Unified Framework for Ticket Routing
In short, our results demonstrate that the UFTR is a superior solution to the ticket routing problem because it takes into account previously unexploited interrelationships between the group assignment and group transfer problems.
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.
Subtopic-driven Multi-Document Summarization
In multi-document summarization, a set of documents to be summarized is assumed to be on the same topic, known as the underlying topic in this paper.
Robust Representation Learning of Biomedical Names
Moreover, our proposed method is also able to compute meaningful representations for unseen names, resulting in high practical utility in real-world applications.
ChID: A Large-scale Chinese IDiom Dataset for Cloze Test
Cloze-style reading comprehension in Chinese is still limited due to the lack of various corpora.
DeepRec: An Open-source Toolkit for Deep Learning based Recommendation
In this toolkit, we have implemented a number of deep learning based recommendation algorithms using Python and the widely used deep learning package - Tensorflow.
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)
A Study on Agreement in PICO Span Annotations
Based on the analysis, we report two observations: (i) Boundaries of PICO span annotations by individual human annotators are very diverse.
Understanding the Stability of Medical Concept Embeddings
In this work, we conduct a detailed analysis on the stability of concept embeddings in medical domain, particularly the relation with concept frequency.
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.
A Survey on Deep Learning for Named Entity Recognition
In this paper, we provide a comprehensive review on existing deep learning techniques for NER.
Next Item Recommendation with Self-Attention
In this paper, we propose a novel sequence-aware recommendation model.
NeuRec: On Nonlinear Transformation for Personalized Ranking
Modeling user-item interaction patterns is an important task for personalized recommendations.
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.
Sentiment Analysis by Capsules
Based on capsule representation, the probability module computes the capsule’s state probability.
Ranked #6 on
Sentiment Analysis
on MR
Deep Learning based Recommender System: A Survey and New Perspectives
This article aims to provide a comprehensive review of recent research efforts on deep learning based recommender systems.
Time Expression Analysis and Recognition Using Syntactic Token Types and General Heuristic Rules
Extracting time expressions from free text is a fundamental task for many applications.
A Survey of Location Prediction on Twitter
Specifically, we concentrate on the prediction of user home locations, tweet locations, and mentioned locations.
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.
Graph-based Point-of-interest Recommendation with Geographical and Temporal Influences
In this paper, we focus on the problem of time-aware POI recommendation, which aims at recommending a list of POIs for a user to visit at a given time.
