Search Results for author:
Found 96 papers, 47 papers with code
Parsing Natural Language into Propositional and First-Order Logic with Dual Reinforcement Learning
In this paper, we propose a scoring model to automatically learn a model-based reward, and an effective training strategy based on curriculum learning is further proposed to stabilize the training process.
Different Data, Different Modalities! Reinforced Data Splitting for Effective Multimodal Information Extraction from Social Media Posts
In this paper, we argue that different social media posts should consider different modalities for multimodal information extraction.
From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models
It is imperative for Large language models (LLMs) to follow instructions with elaborate requirements (i. e. Complex Instructions Following).
AutoCrawler: A Progressive Understanding Web Agent for Web Crawler Generation
We propose AutoCrawler, a two-stage framework that leverages the hierarchical structure of HTML for progressive understanding.
Character is Destiny: Can Large Language Models Simulate Persona-Driven Decisions in Role-Playing?
Can Large Language Models substitute humans in making important decisions?
Enhancing Confidence Expression in Large Language Models Through Learning from Past Experience
Specifically, we first identify three key problems: (1) How to capture the inherent confidence of the LLM?
Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction
The framework includes an evaluation model that can extract related entity pairs with high precision.
Negation Triplet Extraction with Syntactic Dependency and Semantic Consistency
To achieve NTE, we devise a novel Syntax&Semantic-Enhanced Negation Extraction model, namely SSENE, which is built based on a generative pretrained language model (PLM) {of Encoder-Decoder architecture} with a multi-task learning framework.
Large Language Model Can Continue Evolving From Mistakes
Continual Learning (CL) is a commonly used method to address this issue.
SurveyAgent: A Conversational System for Personalized and Efficient Research Survey
In the rapidly advancing research fields such as AI, managing and staying abreast of the latest scientific literature has become a significant challenge for researchers.
How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?
By leveraging the retrieval of information from external knowledge databases, Large Language Models (LLMs) exhibit enhanced capabilities for accomplishing many knowledge-intensive tasks.
Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding
Large Language Models (LLMs) have demonstrated good performance in many reasoning tasks, but they still struggle with some complicated reasoning tasks including logical reasoning.
Is There a One-Model-Fits-All Approach to Information Extraction? Revisiting Task Definition Biases
Definition bias is a negative phenomenon that can mislead models.
AgentGroupChat: An Interactive Group Chat Simulacra For Better Eliciting Emergent Behavior
Language significantly influences the formation and evolution of Human emergent behavior, which is crucial in understanding collective intelligence within human societies.
Laying the Foundation First? Investigating the Generalization from Atomic Skills to Complex Reasoning Tasks
In our experiments, we find that atomic skills can not spontaneously generalize to compositional tasks.
The Missing Piece in Model Editing: A Deep Dive into the Hidden Damage Brought By Model Editing
Large Language Models have revolutionized numerous tasks with their remarkable efficacy. However, the editing of these models, crucial for rectifying outdated or erroneous information, often leads to a complex issue known as the ripple effect in the hidden space.
OVEL: Large Language Model as Memory Manager for Online Video Entity Linking
In this paper, we propose a task called Online Video Entity Linking OVEL, aiming to establish connections between mentions in online videos and a knowledge base with high accuracy and timeliness.
GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick
Large language models (LLMs) excellently generate human-like text, but also raise concerns about misuse in fake news and academic dishonesty.
TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation
Despite remarkable advancements in emulating human-like behavior through Large Language Models (LLMs), current textual simulations do not adequately address the notion of time.
TravelPlanner: A Benchmark for Real-World Planning with Language Agents
Are these language agents capable of planning in more complex settings that are out of the reach of prior AI agents?
Exploiting Duality in Open Information Extraction with Predicate Prompt
Open information extraction (OpenIE) aims to extract the schema-free triplets in the form of (\emph{subject}, \emph{predicate}, \emph{object}) from a given sentence.
Small Language Model Can Self-correct
In this paper, we introduce the \underline{I}ntrinsic \underline{S}elf-\underline{C}orrection (ISC) in generative language models, aiming to correct the initial output of LMs in a self-triggered manner, even for those small LMs with 6 billion parameters.
ConcEPT: Concept-Enhanced Pre-Training for Language Models
In this paper, we propose ConcEPT, which stands for Concept-Enhanced Pre-Training for language models, to infuse conceptual knowledge into PLMs.
Enhancing Quantitative Reasoning Skills of Large Language Models through Dimension Perception
Hence, we present a framework to enhance the quantitative reasoning ability of language models based on dimension perception.
M2ConceptBase: A Fine-grained Aligned Multi-modal Conceptual Knowledge Base
To collect concept-image and concept-description alignments, we propose a context-aware multi-modal symbol grounding approach that considers context information in existing large-scale image-text pairs with respect to each concept.
A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics
We use Winoground-T2I with a dual objective: to evaluate the performance of T2I models and the metrics used for their evaluation.
Source Prompt: Coordinated Pre-training of Language Models on Diverse Corpora from Multiple Sources
Pre-trained language models (PLMs) have established the new paradigm in the field of NLP.
InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews
This paper, instead, introduces a novel perspective to evaluate the personality fidelity of RPAs with psychological scales.
Can Large Language Models Understand Real-World Complex Instructions?
To bridge this gap, we propose CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically.
Towards Visual Taxonomy Expansion
Specifically, on the Chinese taxonomy dataset, our method significantly improves accuracy by 8. 75 %.
Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Models
To translate well, machine translation (MT) systems and general-purposed language models (LMs) need a deep understanding of both source and target languages and cultures.
KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases
Large language models (LLMs) have demonstrated impressive impact in the field of natural language processing, but they still struggle with several issues regarding, such as completeness, timeliness, faithfulness and adaptability.
AspectMMKG: A Multi-modal Knowledge Graph with Aspect-aware Entities
Multi-modal knowledge graphs (MMKGs) combine different modal data (e. g., text and image) for a comprehensive understanding of entities.
Piecing Together Clues: A Benchmark for Evaluating the Detective Skills of Large Language Models
We introduces the DetectBench, a reading comprehension dataset designed to assess a model's ability to jointly ability in key information detection and multi-hop reasoning when facing complex and implicit information.
Adaptive Ordered Information Extraction with Deep Reinforcement Learning
Information extraction (IE) has been studied extensively.
M3PT: A Multi-Modal Model for POI Tagging
In this paper, we propose a novel Multi-Modal Model for POI Tagging, namely M3PT, which achieves enhanced POI tagging through fusing the target POI's textual and visual features, and the precise matching between the multi-modal representations.
HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation
Similes play an imperative role in creative writing such as story and dialogue generation.
QUERT: Continual Pre-training of Language Model for Query Understanding in Travel Domain Search
In this paper, we propose QUERT, A Continual Pre-trained Language Model for QUERy Understanding in Travel Domain Search.
Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs).
Beneath Surface Similarity: Large Language Models Make Reasonable Scientific Analogies after Structure Abduction
The vital role of analogical reasoning in human cognition allows us to grasp novel concepts by linking them with familiar ones through shared relational structures.
Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge
Large language models (LLMs) have been widely studied for their ability to store and utilize positive knowledge.
ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base
Analogical reasoning is a fundamental cognitive ability of humans.
Distilling Script Knowledge from Large Language Models for Constrained Language Planning
In everyday life, humans often plan their actions by following step-by-step instructions in the form of goal-oriented scripts.
Causality-aware Concept Extraction based on Knowledge-guided Prompting
The prompt adopts the topic of the given entity from the existing knowledge in KGs to mitigate the spurious co-occurrence correlations between entities and biased concepts.
Domain Mastery Benchmark: An Ever-Updating Benchmark for Evaluating Holistic Domain Knowledge of Large Language Model--A Preliminary Release
Domain knowledge refers to the in-depth understanding, expertise, and familiarity with a specific subject, industry, field, or area of special interest.
Sem4SAP: Synonymous Expression Mining From Open Knowledge Graph For Language Model Synonym-Aware Pretraining
The model's ability to understand synonymous expression is crucial in many kinds of downstream tasks.
GANTEE: Generative Adversatial Network for Taxonomy Entering Evaluation
The previous methods suffer from low-efficiency since they waste much time when most of the new coming concepts are indeed noisy concepts.
BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model, Corpus and Benchmark
Our aim is to facilitate research in the development of NLP within the Chinese financial domain.
MAPS-KB: A Million-scale Probabilistic Simile Knowledge Base
The ability to understand and generate similes is an imperative step to realize human-level AI.
Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review
The rapid development and application of natural language generation (NLG) techniques has revolutionized the field of automatic text production.
Group Buying Recommendation Model Based on Multi-task Learning
Furthermore, we propose two auxiliary losses corresponding to the two sub-tasks, to refine the representation learning in our model.
Converge to the Truth: Factual Error Correction via Iterative Constrained Editing
Given a possibly false claim sentence, how can we automatically correct it with minimal editing?
Improving Continual Relation Extraction through Prototypical Contrastive Learning
Continual relation extraction (CRE) aims to extract relations towards the continuous and iterative arrival of new data, of which the major challenge is the catastrophic forgetting of old tasks.
Generative Entity Typing with Curriculum Learning
To overcome these drawbacks, we propose a novel generative entity typing (GET) paradigm: given a text with an entity mention, the multiple types for the role that the entity plays in the text are generated with a pre-trained language model (PLM).
Large-scale Multi-granular Concept Extraction Based on Machine Reading Comprehension
In order to supply existing KGs with more fine-grained and new concepts, we propose a novel concept extraction framework, namely MRC-CE, to extract large-scale multi-granular concepts from the descriptive texts of entities.
Factorial User Modeling with Hierarchical Graph Neural Network for Enhanced Sequential Recommendation
Most sequential recommendation (SR) systems employing graph neural networks (GNNs) only model a user's interaction sequence as a flat graph without hierarchy, overlooking diverse factors in the user's preference.
Contextual Information and Commonsense Based Prompt for Emotion Recognition in Conversation
The newly proposed ERC models have leveraged pre-trained language models (PLMs) with the paradigm of pre-training and fine-tuning to obtain good performance.
Language Models as Knowledge Embeddings
In this paper, we propose LMKE, which adopts Language Models to derive Knowledge Embeddings, aiming at both enriching representations of long-tail entities and solving problems of prior description-based methods.
Ranked #3 on
Link Prediction
on WN18RR
Tackling Math Word Problems with Fine-to-Coarse Abstracting and Reasoning
Math Word Problems (MWP) is an important task that requires the ability of understanding and reasoning over mathematical text.
Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints
To this end, we propose a plug-in algorithm for this line of work, i. e., Aligned Constrained Training (ACT), which alleviates this problem by familiarizing the model with the source-side context of the constraints.
WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types
In this paper, we present WikiDiverse, a high-quality human-annotated MEL dataset with diversified contextual topics and entity types from Wikinews, which uses Wikipedia as the corresponding knowledge base.
Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision
Specifically, i) to fully exploit user behavioral information, we extract candidate hyponymy relations that match user interests from query-click concepts; ii) to enhance the semantic information of new concepts and better detect hyponymy relations, we model concepts and relations through both user-generated content and structural information in existing taxonomies and user click logs, by leveraging Pre-trained Language Models and Graph Neural Network combined with Contrastive Learning; iii) to reduce the cost of dataset construction and overcome data skews, we construct a high-quality and balanced training dataset from existing taxonomy with no supervision.
Can Pre-trained Language Models Interpret Similes as Smart as Human?
In this paper, we investigate the ability of PLMs in simile interpretation by designing a novel task named Simile Property Probing, i. e., to let the PLMs infer the shared properties of similes.
E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning
Holding the belief that models capable of reasoning should be right for the right reasons, we propose a first-of-its-kind Explainable Knowledge-intensive Analogical Reasoning benchmark (E-KAR).
Rule Mining over Knowledge Graphs via Reinforcement Learning
Knowledge graphs (KGs) are an important source repository for a wide range of applications and rule mining from KGs recently attracts wide research interest in the KG-related research community.
Multi-Modal Knowledge Graph Construction and Application: A Survey
In this survey on MMKGs constructed by texts and images, we first give definitions of MMKGs, followed with the preliminaries on multi-modal tasks and techniques.
Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanation
In this research, we argue that the evidences of an answer is critical to enhancing the interpretability of QA models.
Semantic-based Data Augmentation for Math Word Problems
In this paper, we propose a set of novel data augmentation approaches to supplement existing datasets with such data that are augmented with different kinds of local variances, and help to improve the generalization ability of current neural models.
Unsupervised Editing for Counterfactual Stories
We also propose a new metric to alleviate the shortcomings of current automatic metrics and better evaluate the trade-off.
A Review on Graph Neural Network Methods in Financial Applications
With multiple components and relations, financial data are often presented as graph data, since it could represent both the individual features and the complicated relations.
A Probit Tensor Factorization Model For Relational Learning
A large number of models and algorithms have been proposed to perform link prediction, among which tensor factorization method has proven to achieve state-of-the-art performance in terms of computation efficiency and prediction accuracy.
FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusion
Today data is often scattered among billions of resource-constrained edge devices with security and privacy constraints.
Relation Aware Semi-autoregressive Semantic Parsing for NL2SQL
It first learns relation embedding over the schema entities and question words with predefined schema relations with ELECTRA and relation aware transformer layer as backbone.
Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction
As a typical task of continual learning, continual relation extraction (CRE) aims to extract relations between entities from texts, where the samples of different relations are delivered into the model continuously.
Revisiting the Negative Data of Distantly Supervised Relation Extraction
Next, we formulate the problem of relation extraction into as a positive unlabeled learning task to alleviate false negative problem.
Ranked #1 on
Relation Extraction
on NYT11-HRL
A Question-answering Based Framework for Relation Extraction Validation
However, few works have focused on how to validate and correct the results generated by the existing relation extraction models.
LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification
The final claim verification is based on all latent variables.
InSRL: A Multi-view Learning Framework Fusing Multiple Information Sources for Distantly-supervised Relation Extraction
We see information sources as multiple views and fusing them to construct an intact space with sufficient information.
Complex Relation Extraction: Challenges and Opportunities
In recent years, many complex relation extraction tasks, i. e., the variants of simple binary relation extraction, are proposed to meet the complex applications in practice.
Knowledge-guided Open Attribute Value Extraction with Reinforcement Learning
Effectively filtering out noisy articles as well as bad answers is the key to improving extraction accuracy.
Convolutional Gaussian Embeddings for Personalized Recommendation with Uncertainty
Most of existing embedding based recommendation models use embeddings (vectors) corresponding to a single fixed point in low-dimensional space, to represent users and items.
A Knowledge-Enhanced Recommendation Model with Attribute-Level Co-Attention
Deep neural networks (DNNs) have been widely employed in recommender systems including incorporating attention mechanism for performance improvement.
Incorporating User Micro-behaviors and Item Knowledge into Multi-task Learning for Session-based Recommendation
These insights motivate us to propose a novel SR model MKM-SR in this paper, which incorporates user Micro-behaviors and item Knowledge into Multi-task learning for Session-based Recommendation.
Attacking Recommender Systems with Augmented User Profiles
Recommendation Systems (RS) have become an essential part of many online services.
Collective Loss Function for Positive and Unlabeled Learning
On the contrary, traditional machine learning algorithms often rely on negative examples, otherwise the model would be prone to collapse and always-true predictions.
Modeling Multi-mapping Relations for Precise Cross-lingual Entity Alignment
We calibrate embeddings of different KGs via a small set of pre-aligned seeds.
Interpretable Text Classification Using CNN and Max-pooling
Deep neural networks have been widely used in text classification.
Bayes EMbedding (BEM): Refining Representation by Integrating Knowledge Graphs and Behavior-specific Networks
Low-dimensional embeddings of knowledge graphs and behavior graphs have proved remarkably powerful in varieties of tasks, from predicting unobserved edges between entities to content recommendation.
Ensuring Readability and Data-fidelity using Head-modifier Templates in Deep Type Description Generation
A type description is a succinct noun compound which helps human and machines to quickly grasp the informative and distinctive information of an entity.
KBQA: Learning Question Answering over QA Corpora and Knowledge Bases
Based on these templates, our QA system KBQA effectively supports binary factoid questions, as well as complex questions which are composed of a series of binary factoid questions.
CN-Probase: A Data-driven Approach for Large-scale Chinese Taxonomy Construction
Taxonomies play an important role in machine intelligence.
Deep Short Text Classification with Knowledge Powered Attention
For the purpose of measuring the importance of knowledge, we introduce attention mechanisms and propose deep Short Text Classification with Knowledge powered Attention (STCKA).
Verb Pattern: A Probabilistic Semantic Representation on Verbs
In this paper, we introduce verb patterns to represent verbs' semantics, such that each pattern corresponds to a single semantic of the verb.
Entity Suggestion by Example using a Conceptual Taxonomy
This paper provides a query processing method based on the relevance models between entity sets and concepts.
