Search Results for author:
Found 70 papers, 37 papers with code
KEViN: A Knowledge Enhanced Validity and Novelty Classifier for Arguments
The ArgMining 2022 Shared Task is concerned with predicting the validity and novelty of an inference for a given premise and conclusion pair.
Ranked #2 on
ValNov
on ValNov Subtask A
GeAR: Graph-enhanced Agent for Retrieval-augmented Generation
Retrieval-augmented generation systems rely on effective document retrieval capabilities.
MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge
To bridge this gap, we introduce MINTQA (Multi-hop Question Answering on New and Tail Knowledge), a comprehensive benchmark to evaluate LLMs' capabilities in multi-hop reasoning across four critical dimensions: question handling strategy, sub-question generation, retrieval-augmented generation, and iterative or dynamic decomposition and retrieval.
From An LLM Swarm To A PDDL-Empowered HIVE: Planning Self-Executed Instructions In A Multi-Modal Jungle
In response to the call for agent-based solutions that leverage the ever-increasing capabilities of the deep models' ecosystem, we introduce Hive -- a comprehensive solution for selecting appropriate models and subsequently planning a set of atomic actions to satisfy the end-users' instructions.
Multi-level Matching Network for Multimodal Entity Linking
To address these issues, we propose a Multi-level Matching network for Multimodal Entity Linking (M3EL).
Atomic Fact Decomposition Helps Attributed Question Answering
Attributed Question Answering (AQA) aims to provide both a trustworthy answer and a reliable attribution report for a given question.
MiCEval: Unveiling Multimodal Chain of Thought's Quality via Image Description and Reasoning Steps
To address this gap, we propose Multimodal Chain-of-Thought Evaluation (MiCEval), a framework designed to assess the correctness of reasoning chains by evaluating the quality of both the description and each reasoning step.
AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction
In this paper, we introduce \texttt{AppBench}, the first benchmark to evaluate LLMs' ability to plan and execute multiple APIs from various sources in order to complete the user's task.
Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQA
In this paper, we model the subgraph retrieval task as a conditional generation task handled by small language models.
CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering
Recent studies have explored the use of Large Language Models (LLMs) with Retrieval Augmented Generation (RAG) for Knowledge Graph Question Answering (KGQA).
How Reliable are LLMs as Knowledge Bases? Re-thinking Facutality and Consistency
Large Language Models (LLMs) are increasingly explored as knowledge bases (KBs), yet current evaluation methods focus too narrowly on knowledge retention, overlooking other crucial criteria for reliable performance.
Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning
We focus on Text-to-SQL semantic parsing from the perspective of retrieval-augmented generation.
Start from Zero: Triple Set Prediction for Automatic Knowledge Graph Completion
In this paper, we propose a novel graph-level automatic KG completion task called Triple Set Prediction (TSP) which assumes none of the elements in the missing triples is given.
Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs
LLMs fine-tuned with this data have improved planning capabilities, better equipping them to handle complex QA tasks that involve retrieval.
An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models
We aim to identify effective methods for enhancing the performance of MLLMs in scenarios where only a limited number of parameters are trained.
Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learning
Our study reveals that retrieval-augmented models can enhance robustness against test sample attacks, outperforming vanilla ICL with a 4. 87% reduction in Attack Success Rate (ASR); however, they exhibit overconfidence in the demonstrations, leading to a 2% increase in ASR for demonstration attacks.
COTET: Cross-view Optimal Transport for Knowledge Graph Entity Typing
Knowledge graph entity typing (KGET) aims to infer missing entity type instances in knowledge graphs.
Prompting Large Language Models with Knowledge Graphs for Question Answering Involving Long-tail Facts
Using this pipeline, we introduce the LTGen benchmark.
Leveraging Intra-modal and Inter-modal Interaction for Multi-Modal Entity Alignment
Multi-modal entity alignment (MMEA) aims to identify equivalent entity pairs across different multi-modal knowledge graphs (MMKGs).
HyperMono: A Monotonicity-aware Approach to Hyper-Relational Knowledge Representation
This paper proposes the HyperMono model for hyper-relational knowledge graph completion, which realizes stage reasoning and qualifier monotonicity.
UniArk: Improving Generalisation and Consistency for Factual Knowledge Extraction through Debiasing
We hypothesize that simultaneously debiasing these objectives can be the key to generalisation over unseen prompts.
Noise-powered Multi-modal Knowledge Graph Representation Framework
In this work, we explore the efficacy of models in accurately embedding entities within MMKGs through two pivotal tasks: Multi-modal Knowledge Graph Completion (MKGC) and Multi-modal Entity Alignment (MMEA).
A Usage-centric Take on Intent Understanding in E-Commerce
In this paper, we focus on predicative user intents as "how a customer uses a product", and pose intent understanding as a natural language reasoning task, independent of product ontologies.
Archer: A Human-Labeled Text-to-SQL Dataset with Arithmetic, Commonsense and Hypothetical Reasoning
We present Archer, a challenging bilingual text-to-SQL dataset specific to complex reasoning, including arithmetic, commonsense and hypothetical reasoning.
TrustScore: Reference-Free Evaluation of LLM Response Trustworthiness
Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, prompting a surge in their practical applications.
Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey
In this survey, we carefully review over 300 articles, focusing on KG-aware research in two principal aspects: KG-driven Multi-Modal (KG4MM) learning, where KGs support multi-modal tasks, and Multi-Modal Knowledge Graph (MM4KG), which extends KG studies into the MMKG realm.
Knowledge-Aware Neuron Interpretation for Scene Classification
Specifically, for concept completeness, we present core concepts of a scene based on knowledge graph, ConceptNet, to gauge the completeness of concepts.
Benchmarking Large Language Models in Complex Question Answering Attribution using Knowledge Graphs
The attribution of question answering is to provide citations for supporting generated statements, and has attracted wide research attention.
UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems
To better plan and incorporate the use of multiple sources in generating personalized response, we firstly decompose it into three sub-tasks: Knowledge Source Selection, Knowledge Retrieval, and Response Generation.
Prompting Disentangled Embeddings for Knowledge Graph Completion with Pre-trained Language Model
Accordingly, we propose a new KGC method named PDKGC with two prompts -- a hard task prompt which is to adapt the KGC task to the PLM pre-training task of token prediction, and a disentangled structure prompt which learns disentangled graph representation so as to enable the PLM to combine more relevant structure knowledge with the text information.
Code-Switching with Word Senses for Pretraining in Neural Machine Translation
Lexical ambiguity is a significant and pervasive challenge in Neural Machine Translation (NMT), with many state-of-the-art (SOTA) NMT systems struggling to handle polysemous words (Campolungo et al., 2022).
Multi-view Contrastive Learning for Entity Typing over Knowledge Graphs
Knowledge graph entity typing (KGET) aims at inferring plausible types of entities in knowledge graphs.
Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification
Hierarchical multi-label text classification (HMTC) aims at utilizing a label hierarchy in multi-label classification.
HyperFormer: Enhancing Entity and Relation Interaction for Hyper-Relational Knowledge Graph Completion
Hyper-relational knowledge graph completion (HKGC) aims at inferring unknown triples while considering its qualifiers.
Large Language Models and Knowledge Graphs: Opportunities and Challenges
Large Language Models (LLMs) have taken Knowledge Representation -- and the world -- by storm.
Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment
As a crucial extension of entity alignment (EA), multi-modal entity alignment (MMEA) aims to identify identical entities across disparate knowledge graphs (KGs) by exploiting associated visual information.
Ranked #1 on
Multi-modal Entity Alignment
on UMVM-oea-d-w-v2
(using extra training data)
KATIE: A System for Key Attributes Identification in Product Knowledge Graph Construction
This is particularly challenging when the attributes and their values are mined from online product catalogues, i. e. HTML pages.
BUCA: A Binary Classification Approach to Unsupervised Commonsense Question Answering
Unsupervised commonsense reasoning (UCR) is becoming increasingly popular as the construction of commonsense reasoning datasets is expensive, and they are inevitably limited in their scope.
InstructIE: A Bilingual Instruction-based Information Extraction Dataset
Experimental results demonstrate that large language models trained with InstructIE can not only obtain better IE capabilities but also enhance zero-shot performance compared with baselines.
An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answering
Large-scale pre-trained language models (PLMs) such as BERT have recently achieved great success and become a milestone in natural language processing (NLP).
Entity-Agnostic Representation Learning for Parameter-Efficient Knowledge Graph Embedding
In our proposed model, Entity-Agnostic Representation Learning (EARL), we only learn the embeddings for a small set of entities and refer to them as reserved entities.
Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs
In this paper, we use a set of general terminologies to unify these methods and refer to them collectively as Knowledge Extrapolation.
MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid
Multi-modal entity alignment (MMEA) aims to discover identical entities across different knowledge graphs (KGs) whose entities are associated with relevant images.
Ranked #1 on
Entity Alignment
on FBYG15k
(using extra training data)
Transformer-based Entity Typing in Knowledge Graphs
We investigate the knowledge graph entity typing task which aims at inferring plausible entity types.
Relational Message Passing for Fully Inductive Knowledge Graph Completion
Subgraph reasoning with message passing is a promising and popular solution.
Construction and Applications of Billion-Scale Pre-Trained Multimodal Business Knowledge Graph
We release all the open resources (OpenBG benchmarks) derived from it for the community and report experimental results of KG-centric tasks.
Task-specific Pre-training and Prompt Decomposition for Knowledge Graph Population with Language Models
Our system is the winner of track 1 of the LM-KBC challenge, based on BERT LM; it achieves 55. 0% F-1 score on the hidden test set of the challenge.
Target-oriented Sentiment Classification with Sequential Cross-modal Semantic Graph
Multi-modal aspect-based sentiment classification (MABSC) is task of classifying the sentiment of a target entity mentioned in a sentence and an image.
UnCommonSense: Informative Negative Knowledge about Everyday Concepts
This way, positive statements about comparable concepts that are absent for the target concept become seeds for negative statement candidates.
DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning
Specifically, we (1) developed a cross-modal semantic grounding network to investigate the model's capability of disentangling semantic attributes from the images; (2) applied an attribute-level contrastive learning strategy to further enhance the model's discrimination on fine-grained visual characteristics against the attribute co-occurrence and imbalance; (3) proposed a multi-task learning policy for considering multi-model objectives.
Ranked #2 on
Zero-Shot Learning
on CUB-200-2011
Disentangled Ontology Embedding for Zero-shot Learning
In this paper, we focus on ontologies for augmenting ZSL, and propose to learn disentangled ontology embeddings guided by ontology properties to capture and utilize more fine-grained class relationships in different aspects.
Type-aware Embeddings for Multi-Hop Reasoning over Knowledge Graphs
Multi-hop reasoning over real-life knowledge graphs (KGs) is a highly challenging problem as traditional subgraph matching methods are not capable to deal with noise and missing information.
Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspective
Knowledge graph (KG) reasoning is becoming increasingly popular in both academia and industry.
Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey
Machine learning especially deep neural networks have achieved great success but many of them often rely on a number of labeled samples for supervision.
Geometric Models for (Temporally) Attributed Description Logics
It has been shown that convex geometric regions capture the so-called quasi-chained rules.
A Knowledge-Guided Framework for Frame Identification
In this paper, we propose a Knowledge-Guided Frame Identification framework (KGFI) that integrates three types frame knowledge, including frame definitions, frame elements and frame-to-frame relations, to learn better frame representation, which guides the KGFI to jointly map target words and frames into the same embedding space and subsequently identify the best frame by calculating the dot-product similarity scores between the target word embedding and all of the frame embeddings.
Zero-shot Visual Question Answering using Knowledge Graph
Incorporating external knowledge to Visual Question Answering (VQA) has become a vital practical need.
Ranked #1 on
Visual Question Answering (VQA)
on F-VQA
Knowledge-aware Zero-Shot Learning: Survey and Perspective
Zero-shot learning (ZSL) which aims at predicting classes that have never appeared during the training using external knowledge (a. k. a.
OntoZSL: Ontology-enhanced Zero-shot Learning
The key of implementing ZSL is to leverage the prior knowledge of classes which builds the semantic relationship between classes and enables the transfer of the learned models (e. g., features) from training classes (i. e., seen classes) to unseen classes.
Ontology-guided Semantic Composition for Zero-Shot Learning
Zero-shot learning (ZSL) is a popular research problem that aims at predicting for those classes that have never appeared in the training stage by utilizing the inter-class relationship with some side information.
Negative Statements Considered Useful
Negative statements are useful to overcome limitations of question answering systems that are mainly geared for positive questions; they can also contribute to informative summaries of entities.
A Framework for Evaluating Snippet Generation for Dataset Search
Reusing existing datasets is of considerable significance to researchers and developers.
Augmenting Transfer Learning with Semantic Reasoning
We exploit their semantics to augment transfer learning by dealing with when to transfer with semantic measurements and what to transfer with semantic embeddings.
Commonsense Properties from Query Logs and Question Answering Forums
Commonsense knowledge about object properties, human behavior and general concepts is crucial for robust AI applications.
Knowledge-based Transfer Learning Explanation
Machine learning explanation can significantly boost machine learning's application in decision making, but the usability of current methods is limited in human-centric explanation, especially for transfer learning, an important machine learning branch that aims at utilizing knowledge from one learning domain (i. e., a pair of dataset and prediction task) to enhance prediction model training in another learning domain.
