Search Results for author:
Found 84 papers, 47 papers with code
New Frontiers of Information Extraction
This tutorial targets researchers and practitioners who are interested in AI and ML technologies for structural information extraction (IE) from unstructured textual sources.
Robust Natural Language Understanding with Residual Attention Debiasing
However, previous ensemble-based debiasing methods typically apply debiasing on top-level logits without directly addressing biased attention patterns.
Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
Instruction-tuned models are trained on crowdsourcing datasets with task instructions to achieve superior performance.
From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
Language models are often at risk of diverse backdoor attacks, especially data poisoning.
Adversarial Demonstration Attacks on Large Language Models
With the emergence of more powerful large language models (LLMs), such as ChatGPT and GPT-4, in-context learning (ICL) has gained significant prominence in leveraging these models for specific tasks by utilizing data-label pairs as precondition prompts.
Improving Factuality of Abstractive Summarization without Sacrificing Summary Quality
However, most of the prior works on training factuality-aware models have ignored the negative effect it has on summary quality.
Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning
Event temporal reasoning aims at identifying the temporal relations between two or more events.
Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations
It is unclear whether the compositional semantics of sentences can be directly reflected as compositional operations in the embedding space.
A Causal View of Entity Bias in (Large) Language Models
Meanwhile, our in-context intervention effectively reduces the knowledge conflicts between parametric knowledge and contextual knowledge in GPT-3. 5 and improves the F1 score by 9. 14 points on a challenging test set derived from Re-TACRED.
How Fragile is Relation Extraction under Entity Replacements?
In principle, textual context determines the ground-truth relation and the RE models should be able to correctly identify the relations reflected by the textual context.
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.
Context-faithful Prompting for Large Language Models
Large language models (LLMs) encode parametric knowledge about world facts and have shown remarkable performance in knowledge-driven NLP tasks.
Continual Contrastive Finetuning Improves Low-Resource Relation Extraction
In this paper, we aim at bridging the gap and propose to pretrain and finetune the RE model using consistent objectives of contrastive learning.
Multi-hop Evidence Retrieval for Cross-document Relation Extraction
Additionally, we show that Mr. CoD facilitates evidence retrieval and boosts end-to-end RE performance with effective multi-hop reasoning in both closed and open settings of RE.
Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?
Two key obstacles in biomedical relation extraction (RE) are the scarcity of annotations and the prevalence of instances without explicitly pre-defined labels due to low annotation coverage.
On-the-fly Denoising for Data Augmentation in Natural Language Understanding
However, data augmentation may introduce noisy data that impairs training.
PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales
Neural language models (LMs) have achieved impressive results on various language-based reasoning tasks by utilizing latent knowledge encoded in their own pretrained parameters.
Salience Allocation as Guidance for Abstractive Summarization
Recent literature adds extractive summaries as guidance for abstractive summarization models to provide hints of salient content and achieves better performance.
Ranked #6 on
Abstractive Text Summarization
on CNN / Daily Mail
SpaBERT: A Pretrained Language Model from Geographic Data for Geo-Entity Representation
Characterizing geo-entities is integral to various application domains, such as geo-intelligence and map comprehension, while a key challenge is to capture the spatial-varying context of an entity.
Parameter-Efficient Tuning with Special Token Adaptation
Parameter-efficient tuning aims at updating only a small subset of parameters when adapting a pretrained model to downstream tasks.
Extracting or Guessing? Improving Faithfulness of Event Temporal Relation Extraction
In this paper, we seek to improve the faithfulness of TempRel extraction models from two perspectives.
Ranked #3 on
Temporal Relation Classification
on MATRES
Are All Steps Equally Important? Benchmarking Essentiality Detection of Events
In this paper, we seek to fill this gap by studying how well current models can understand the essentiality of different step events towards a goal event.
VIPHY: Probing "Visible" Physical Commonsense Knowledge
While such tasks measure the requisite knowledge to ground and reason over a given visual instance, they do not, however, measure the ability of VLMs to retain and generalize such knowledge.
Bending the Future: Autoregressive Modeling of Temporal Knowledge Graphs in Curvature-Variable Hyperbolic Spaces
The chronological hierarchies between knowledge graphs at different timestamps are represented by embedding the knowledge graphs as vectors in a common hyperbolic space.
Design and control analysis of a deployable clustered hyperbolic paraboloid cable net
This paper presents an analytical and experimental design and deployment control analysis of a hyperbolic paraboloid cable net based on clustering actuation strategies.
PInKS: Preconditioned Commonsense Inference with Minimal Supervision
Reasoning with preconditions such as "glass can be used for drinking water unless the glass is shattered" remains an open problem for language models.
Equilibrium and stiffness study of clustered tensegrity structures with the consideration of pulley sizes
This paper presents the equilibrium and stiffness study of clustered tensegrity structures (CTS) considering pulley sizes.
Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing
Due to shortcuts from surface patterns to annotated entity labels and biased training, existing entity typing models are subject to the problem of spurious correlations.
Summarization as Indirect Supervision for Relation Extraction
Considering that summarization tasks aim at acquiring concise expressions of synoptical information from the longer context, these tasks naturally align with the objective of RE, i. e., extracting a kind of synoptical information that describes the relation of entity mentions.
Ranked #6 on
Relation Extraction
on TACRED
GRAPHCACHE: Message Passing as Caching for Sentence-Level Relation Extraction
GRAPHCACHE aggregates the features from sentences in the whole dataset to learn global representations of properties, and use them to augment the local features within individual sentences.
Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis
In this paper, we propose the CORE (Counterfactual Analysis based Relation Extraction) debiasing method that guides the RE models to focus on the main effects of textual context without losing the entity information.
Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning
This prunes the full self-attention structure into an order-invariant graph attention that captures the connected graph structure of cells belonging to the same row or column, and it differentiates between relevant cells and irrelevant cells from the structural perspective.
Ranked #2 on
Data-to-Text Generation
on ToTTo
Dangling-Aware Entity Alignment with Mixed High-Order Proximities
We study dangling-aware entity alignment in knowledge graphs (KGs), which is an underexplored but important problem.
Unified Semantic Typing with Meaningful Label Inference
Semantic typing aims at classifying tokens or spans of interest in a textual context into semantic categories such as relations, entity types, and event types.
Ranked #2 on
Relation Extraction
on TACRED
Answer Consolidation: Formulation and Benchmarking
Current question answering (QA) systems primarily consider the single-answer scenario, where each question is assumed to be paired with one correct answer.
Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference
The task of ultra-fine entity typing (UFET) seeks to predict diverse and free-form words or phrases that describe the appropriate types of entities mentioned in sentences.
Ranked #1 on
Entity Typing
on FIGER
Sharpness-Aware Minimization with Dynamic Reweighting
Deep neural networks are often overparameterized and may not easily achieve model generalization.
Contextualized Scene Imagination for Generative Commonsense Reasoning
In this paper, we propose an Imagine-and-Verbalize (I&V) method, which learns to imagine a relational scene knowledge graph (SKG) with relations between the input concepts, and leverage the SKG as a constraint when generating a plausible scene description.
Structure-Aware Label Smoothing for Graph Neural Networks
Representing a label distribution as a one-hot vector is a common practice in training node classification models.
Dynamics and control of clustered tensegrity systems
This paper presents the formulations of nonlinear and linearized statics, dynamics, and control for any clustered tensegrity system (CTS).
Prix-LM: Pretraining for Multilingual Knowledge Base Construction
To achieve this, it is crucial to represent multilingual knowledge in a shared/unified space.
HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning
Taxonomies are valuable resources for many applications, but the limited coverage due to the expensive manual curation process hinders their general applicability.
Salience-Aware Event Chain Modeling for Narrative Understanding
Storytelling, whether via fables, news reports, documentaries, or memoirs, can be thought of as the communication of interesting and related events that, taken together, form a concrete process.
Learning Constraints and Descriptive Segmentation for Subevent Detection
The task of subevent detection aims to resolve this granularity issue, recognizing the membership of multi-granular events in event complexes.
Table-based Fact Verification with Salience-aware Learning
From one perspective, our system conducts masked salient token prediction to enhance the model for alignment and reasoning between the table and the statement.
Ranked #6 on
Table-based Fact Verification
on TabFact
Event-Centric Natural Language Processing
This tutorial targets researchers and practitioners who are interested in AI technologies that help machines understand natural language text, particularly real-world events described in the text.
Do Language Models Perform Generalizable Commonsense Inference?
Inspired by evidence that pretrained language models (LMs) encode commonsense knowledge, recent work has applied LMs to automatically populate commonsense knowledge graphs (CKGs).
Design and analysis of deployable clustered tensegrity cable domes
Results show that the proposed CTS cable dome always has one prestress mode and is globally stable in its deployment trajectory.
Knowing the No-match: Entity Alignment with Dangling Cases
Since KGs possess different sets of entities, there could be entities that cannot find alignment across them, leading to the problem of dangling entities.
Ranked #1 on
Entity Alignment
on DBP2.0 zh-en
Retrieving Complex Tables with Multi-Granular Graph Representation Learning
The task of natural language table retrieval (NLTR) seeks to retrieve semantically relevant tables based on natural language queries.
Contrastive Out-of-Distribution Detection for Pretrained Transformers
Pretrained Transformers achieve remarkable performance when training and test data are from the same distribution.
PaCo: Preconditions Attributed to Commonsense Knowledge
To address this gap, we propose a novel challenge of reasoning with circumstantial preconditions.
Learning from Noisy Labels for Entity-Centric Information Extraction
Recent information extraction approaches have relied on training deep neural models.
Ranked #1 on
Named Entity Recognition (NER)
on CoNLL++
Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning
Knowledge bases often consist of facts which are harvested from a variety of sources, many of which are noisy and some of which conflict, resulting in a level of uncertainty for each triple.
Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts
The cross-view association model is learned to bridge the embeddings of ontological concepts and their corresponding instance-view entities.
Bio-JOIE: Joint Representation Learning of Biological Knowledge Bases
Leveraging a wide-range of biological knowledge, such as gene ontology and protein-protein interaction (PPI) networks from other closely related species presents a vital approach to infer the molecular impact of a new species.
ReadNet: A Hierarchical Transformer Framework for Web Article Readability Analysis
Analyzing the readability of articles has been an important sociolinguistic task.
An Improved Baseline for Sentence-level Relation Extraction
Sentence-level relation extraction (RE) aims at identifying the relationship between two entities in a sentence.
Ranked #2 on
Relation Extraction
on Re-TACRED
Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
Since such temporal knowledge graphs often suffer from incompleteness, it is important to develop time-aware representation learning models that help to infer the missing temporal facts.
What Are You Trying to Do? Semantic Typing of Event Processes
This paper studies a new cognitively motivated semantic typing task, multi-axis event process typing, that, given anevent process, attempts to infer free-form typelabels describing (i) the type of action made bythe process and (ii) the type of object the pro-cess seeks to affect.
Analogous Process Structure Induction for Sub-event Sequence Prediction
Computational and cognitive studies of event understanding suggest that identifying, comprehending, and predicting events depend on having structured representations of a sequence of events and on conceptualizing (abstracting) its components into (soft) event categories.
Joint Constrained Learning for Event-Event Relation Extraction
Understanding natural language involves recognizing how multiple event mentions structurally and temporally interact with each other.
"What Are You Trying to Do?" Semantic Typing of Event Processes
This paper studies a new cognitively motivated semantic typing task, multi-axis event process typing, that, given an event process, attempts to infer free-form type labels describing (i) the type of action made by the process and (ii) the type of object the process seeks to affect.
Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer
Predicting missing facts in a knowledge graph (KG) is a crucial task in knowledge base construction and reasoning, and it has been the subject of much research in recent works using KG embeddings.
Ranked #2 on
Knowledge Graph Completion
on DPB-5L (French)
Knowledge Association with Hyperbolic Knowledge Graph Embeddings
Capturing associations for knowledge graphs (KGs) through entity alignment, entity type inference and other related tasks benefits NLP applications with comprehensive knowledge representations.
Ranked #26 on
Entity Alignment
on DBP15k zh-en
Visual Pivoting for (Unsupervised) Entity Alignment
This work studies the use of visual semantic representations to align entities in heterogeneous knowledge graphs (KGs).
Ranked #11 on
Entity Alignment
on dbp15k ja-en
(using extra training data)
Cross-lingual Entity Alignment with Incidental Supervision
Much research effort has been put to multilingual knowledge graph (KG) embedding methods to address the entity alignment task, which seeks to match entities in different languagespecific KGs that refer to the same real-world object.
Ranked #17 on
Entity Alignment
on DBP15k zh-en
A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
Recent advancement in KG embedding impels the advent of embedding-based entity alignment, which encodes entities in a continuous embedding space and measures entity similarities based on the learned embeddings.
Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation
As the direct neighbors of counterpart entities are usually dissimilar due to the schema heterogeneity, AliNet introduces distant neighbors to expand the overlap between their neighborhood structures.
Ranked #27 on
Entity Alignment
on DBP15k zh-en
Retrofitting Contextualized Word Embeddings with Paraphrases
Contextualized word embedding models, such as ELMo, generate meaningful representations of words and their context.
Examining Gender Bias in Languages with Grammatical Gender
Recent studies have shown that word embeddings exhibit gender bias inherited from the training corpora.
Fast and Accurate Network Embeddings via Very Sparse Random Projection
Two key features of FastRP are: 1) it explicitly constructs a node similarity matrix that captures transitive relationships in a graph and normalizes matrix entries based on node degrees; 2) it utilizes very sparse random projection, which is a scalable optimization-free method for dimension reduction.
Learning Bilingual Word Embeddings Using Lexical Definitions
Bilingual word embeddings, which representlexicons of different languages in a shared em-bedding space, are essential for supporting se-mantic and knowledge transfers in a variety ofcross-lingual NLP tasks.
Multi-view Knowledge Graph Embedding for Entity Alignment
Furthermore, we design some cross-KG inference methods to enhance the alignment between two KGs.
Learning to Identify High Betweenness Centrality Nodes from Scratch: A Novel Graph Neural Network Approach
By training on small-scale networks, the learned model is capable of assigning relative BC scores to nodes for any unseen networks, and thus identifying the highly-ranked nodes.
Quantification and Analysis of Scientific Language Variation Across Research Fields
Quantifying differences in terminologies from various academic domains has been a longstanding problem yet to be solved.
Embedding Uncertain Knowledge Graphs
However, there are many KGs that model uncertain knowledge, which typically model the inherent uncertainty of relations facts with a confidence score, and embedding such uncertain knowledge represents an unresolved challenge.
Enhanced Network Embeddings via Exploiting Edge Labels
Network embedding methods aim at learning low-dimensional latent representation of nodes in a network.
Social and Information Networks Physics and Society
On2Vec: Embedding-based Relation Prediction for Ontology Population
Recent advances in translation-based graph embedding methods for populating instance-level knowledge graphs lead to promising new approaching for the ontology population problem.
Learning to Represent Bilingual Dictionaries
Bilingual word embeddings have been widely used to capture the similarity of lexical semantics in different human languages.
Neural Article Pair Modeling for Wikipedia Sub-article Matching
Nowadays, editors tend to separate different subtopics of a long Wiki-pedia article into multiple sub-articles.
Co-training Embeddings of Knowledge Graphs and Entity Descriptions for Cross-lingual Entity Alignment
Since many multilingual KGs also provide literal descriptions of entities, in this paper, we introduce an embedding-based approach which leverages a weakly aligned multilingual KG for semi-supervised cross-lingual learning using entity descriptions.
Attention-based Natural Language Person Retrieval
Following the recent progress in image classification and captioning using deep learning, we develop a novel natural language person retrieval system based on an attention mechanism.
Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment
Many recent works have demonstrated the benefits of knowledge graph embeddings in completing monolingual knowledge graphs.
Ranked #36 on
Entity Alignment
on DBP15k zh-en
