Search Results for author:
Found 100 papers, 73 papers with code
PCR4ALL: A Comprehensive Evaluation Benchmark for Pronoun Coreference Resolution in English
Pronoun Coreference Resolution (PCR) is the task of resolving pronominal expressions to all mentions they refer to.
A Brief Survey and Comparative Study of Recent Development of Pronoun Coreference Resolution in English
Pronoun Coreference Resolution (PCR) is the task of resolving pronominal expressions to all mentions they refer to.
Comparative Evaluation of Label-Agnostic Selection Bias in Multilingual Hate Speech Datasets
Work on bias in hate speech typically aims to improve classification performance while relatively overlooking the quality of the data.
Rare and Zero-shot Word Sense Disambiguation using Z-Reweighting
However, the imbalanced training dataset leads to poor performance on rare senses and zero-shot senses.
You Don’t Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers’ Private Personas
To this end, we propose effective defense objectives to protect persona leakage from hidden states.
Logical Message Passing Networks with One-hop Inference on Atomic Formulas
On top of the query graph, we propose the Logical Message Passing Neural Network (LMPNN) that connects the \textit{local} one-hop inferences on atomic formulas to the \textit{global} logical reasoning for complex query answering.
On-the-fly Denoising for Data Augmentation in Natural Language Understanding
However, data augmentation may introduce noisy data that impairs training.
FolkScope: Intention Knowledge Graph Construction for Discovering E-commerce Commonsense
We annotate a large amount of assertions for both plausibility and typicality of an intention that can explain a purchasing or co-purchasing behavior, where the intention can be an open reason or a predicate falling into one of 18 categories aligning with ConceptNet, e. g., IsA, MadeOf, UsedFor, etc.
Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier Transform
However, the performance of the hyperbolic KG embedding models for non-transitive relations is still unpromising, while the complex hyperbolic embeddings do not deal with multi-relations.
BEKG: A Built Environment Knowledge Graph
In this paper, more than 80, 000 paper abstracts in the built environment field were obtained to build a knowledge graph, a knowledge base storing entities and their connective relations in a graph-structured data model.
Kuaipedia: a Large-scale Multi-modal Short-video Encyclopedia
In this paper, we propose Kuaipedia, a large-scale multi-modal encyclopedia consisting of items, aspects, and short videos lined to them, which was extracted from billions of videos of Kuaishou (Kwai), a well-known short-video platform in China.
An Empirical Revisiting of Linguistic Knowledge Fusion in Language Understanding Tasks
Though linguistic knowledge emerges during large-scale language model pretraining, recent work attempt to explicitly incorporate human-defined linguistic priors into task-specific fine-tuning.
PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population
We propose PseudoReasoner, a semi-supervised learning framework for CSKB population that uses a teacher model pre-trained on CSKBs to provide pseudo labels on the unlabeled candidate dataset for a student model to learn from.
Multilingual Word Sense Disambiguation with Unified Sense Representation
As a key natural language processing (NLP) task, word sense disambiguation (WSD) evaluates how well NLP models can understand the lexical semantics of words under specific contexts.
MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation
Commonsense reasoning tasks such as commonsense knowledge graph completion and commonsense question answering require powerful representation learning.
SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller
In this paper, we propose a new task of sub-event generation for an unseen process to evaluate the understanding of the coherence of sub-event actions and objects.
CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm
We first align commonsense tasks with relevant knowledge from commonsense knowledge bases and ask humans to annotate whether the knowledge is enough or not.
Cross-domain Cross-architecture Black-box Attacks on Fine-tuned Models with Transferred Evolutionary Strategies
To successfully attack fine-tuned models under both settings, we propose to first train an adversarial generator against the source model, which adopts an encoder-decoder architecture and maps a clean input to an adversarial example.
Boosting Graph Structure Learning with Dummy Nodes
We extend graph kernels and graph neural networks with dummy nodes and conduct experiments on graph classification and subgraph isomorphism matching tasks.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization
Conceptualization, or viewing entities and situations as instances of abstract concepts in mind and making inferences based on that, is a vital component in human intelligence for commonsense reasoning.
VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolution
In this paper, we propose VD-PCR, a novel framework to improve Visual Dialog understanding with Pronoun Coreference Resolution in both implicit and explicit ways.
Weakly Supervised Text Classification using Supervision Signals from a Language Model
In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision signals.
Query2Particles: Knowledge Graph Reasoning with Particle Embeddings
The query embedding method is proposed to answer these queries by jointly encoding queries and entities to the same embedding space.
You Don't Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers' Private Personas
To this end, we propose effective defense objectives to protect persona leakage from hidden states.
Graph Convolutional Networks with Dual Message Passing for Subgraph Isomorphism Counting and Matching
Based on this observation, we propose dual message passing neural networks (DMPNNs) to enhance the substructure representation learning in an asynchronous way for subgraph isomorphism counting and matching as well as unsupervised node classification.
Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs
Besides, our work, for the first time, provides a benchmark to evaluate and analyze the impact of different operators and normal forms by using (a) 7 choices of the operator systems and (b) 9 forms of complex queries.
Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset
Experimental results show that generalizing commonsense reasoning on unseen assertions is inherently a hard task.
Exophoric Pronoun Resolution in Dialogues with Topic Regularization
Resolving pronouns to their referents has long been studied as a fundamental natural language understanding problem.
Multi-Relational Graph based Heterogeneous Multi-Task Learning in Community Question Answering
To tackle this challenge, we develop a multi-relational graph based MTL model called Heterogeneous Multi-Task Graph Isomorphism Network (HMTGIN) which efficiently solves heterogeneous CQA tasks.
Probing Toxic Content in Large Pre-Trained Language Models
Large pre-trained language models (PTLMs) have been shown to carry biases towards different social groups which leads to the reproduction of stereotypical and toxic content by major NLP systems.
Manifold Alignment across Geometric Spaces for Knowledge Base Representation Learning
Nevertheless, transitivity is a special property that cannot be modeled efficiently in the Euclidean space.
Do Boat and Ocean Suggest Beach? Dialogue Summarization with External Knowledge
To evaluate the inference capability of different methods, we also propose a new evaluation metric based on CODC.
Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model
Recently, there is an effort to extend fine-grained entity typing by using a richer and ultra-fine set of types, and labeling noun phrases including pronouns and nominal nouns instead of just named entity mentions.
Ranked #1 on
Entity Typing
on Ontonotes v5 (English)
(using extra training data)
Exploring Discourse Structures for Argument Impact Classification
Discourse relations among arguments reveal logical structures of a debate conversation.
Differentially Private Federated Knowledge Graphs Embedding
However, for multiple cross-domain knowledge graphs, state-of-the-art embedding models cannot make full use of the data from different knowledge domains while preserving the privacy of exchanged data.
Unit Ball Model for Embedding Hierarchical Structures in the Complex Hyperbolic Space
Specifically, we propose to learn the embeddings of hierarchically structured data in the unit ball model of the complex hyperbolic space.
Variational Weakly Supervised Sentiment Analysis with Posterior Regularization
In this paper, we propose a posterior regularization framework for the variational approach to the weakly supervised sentiment analysis to better control the posterior distribution of the label assignment.
Fair Representation Learning for Heterogeneous Information Networks
Recently, much attention has been paid to the societal impact of AI, especially concerns regarding its fairness.
ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities
After conceptualization with Probase, a selectional preference based concept-instance relational knowledge base, our concept graph contains 15 million conceptualized eventualities and 224 million edges between them.
Streaming Social Event Detection and Evolution Discovery in Heterogeneous Information Networks
Third, we propose a streaming social event detection and evolution discovery framework for HINs based on meta-path similarity search, historical information about meta-paths, and heterogeneous DBSCAN clustering method.
Wasserstein Graph Neural Networks for Graphs with Missing Attributes
In this paper, we propose an innovative node representation learning framework, Wasserstein Graph Neural Network (WGNN), to mitigate the problem.
Joint Coreference Resolution and Character Linking for Multiparty Conversation
Character linking, the task of linking mentioned people in conversations to the real world, is crucial for understanding the conversations.
BiGCN: A Bi-directional Low-Pass Filtering Graph Neural Network
Graph convolutional networks (GCNs) have achieved great success on graph-structured data.
DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge
On the other hand, generation models have the potential to automatically generate more knowledge.
CoCoLM: COmplex COmmonsense Enhanced Language Model with Discourse Relations
Large-scale pre-trained language models have demonstrated strong knowledge representation ability.
Learning Contextual Causality from Time-consecutive Images
Compared with pure text-based approaches, learning causality from the visual signal has the following advantages: (1) Causality knowledge belongs to the commonsense knowledge, which is rarely expressed in the text but rich in videos; (2) Most events in the video are naturally time-ordered, which provides a rich resource for us to mine causality knowledge from; (3) All the objects in the video can be used as context to study the contextual property of causal relations.
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.
When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models
We also demonstrate that distributional methods are ideal to make up for pattern-based ones in such cases.
A Brief Survey and Comparative Study of Recent Development of Pronoun Coreference Resolution
Pronoun Coreference Resolution (PCR) is the task of resolving pronominal expressions to all mentions they refer to.
Two Sides of the Same Coin: White-box and Black-box Attacks for Transfer Learning
To systematically measure the effect of both white-box and black-box attacks, we propose a new metric to evaluate how transferable are the adversarial examples produced by a source model to a target model.
Peer-inspired Student Performance Prediction in Interactive Online Question Pools with Graph Neural Network
Specifically, we model the relationship between students and questions using student interactions to construct the student-interaction-question network and further present a new GNN model, called R^2GCN, which intrinsically works for the heterogeneous networks, to achieve generalizable student performance prediction in interactive online question pools.
Enriching Large-Scale Eventuality Knowledge Graph with Entailment Relations
Computational and cognitive studies suggest that the abstraction of eventualities (activities, states, and events) is crucial for humans to understand daily eventualities.
WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge
Experimental results prove that even though pre-trained language representation models have achieved promising progress on the original WSC dataset, they are still struggling at WinoWhy.
SocialTrans: A Deep Sequential Model with Social Information for Web-Scale Recommendation Systems
Experiments on three data sets verify the effectiveness of our model and show that it outperforms state-of-the-art social recommendation methods.
TransOMCS: From Linguistic Graphs to Commonsense Knowledge
Commonsense knowledge acquisition is a key problem for artificial intelligence.
On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification
Implicit discourse relation classification is one of the most difficult parts in shallow discourse parsing as the relation prediction without explicit connectives requires the language understanding at both the text span level and the sentence level.
A Chinese Corpus for Fine-grained Entity Typing
In this paper, we introduce a corpus for Chinese fine-grained entity typing that contains 4, 800 mentions manually labeled through crowdsourcing.
Fisher Deep Domain Adaptation
Though the learned representations are separable in the source domain, they usually have a large variance and samples with different class labels tend to overlap in the target domain, which yields suboptimal adaptation performance.
On the Role of Conceptualization in Commonsense Knowledge Graph Construction
Commonsense knowledge graphs (CKGs) like Atomic and ASER are substantially different from conventional KGs as they consist of much larger number of nodes formed by loosely-structured text, which, though, enables them to handle highly diverse queries in natural language related to commonsense, leads to unique challenges for automatic KG construction methods.
Exploiting Semantic Relations for Fine-grained Entity Typing
We find that, in some cases, existing neural fine-grained entity typing models may ignore the semantic information in the context that is important for typing.
Vertex-reinforced Random Walk for Network Embedding
In this paper, we study the fundamental problem of random walk for network embedding.
Multiplex Word Embeddings for Selectional Preference Acquisition
Therefore, in this paper, we propose a multiplex word embedding model, which can be easily extended according to various relations among words.
Neural Subgraph Isomorphism Counting
In this paper, we study a new graph learning problem: learning to count subgraph isomorphisms.
RWNE: A Scalable Random-Walk-Based Network Embedding Framework with Personalized Higher-Order Proximity Preserved
However, despite the success of current random-walk-based methods, most of them are usually not expressive enough to preserve the personalized higher-order proximity and lack a straightforward objective to theoretically articulate what and how network proximity is preserved.
Improving Fine-grained Entity Typing with Entity Linking
Fine-grained entity typing is a challenging problem since it usually involves a relatively large tag set and may require to understand the context of the entity mention.
HeteSpaceyWalk: A Heterogeneous Spacey Random Walk for Heterogeneous Information Network Embedding
Heterogeneous information network (HIN) embedding has gained increasing interests recently.
What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues
To tackle this challenge, in this paper, we formally define the task of visual-aware pronoun coreference resolution (PCR) and introduce VisPro, a large-scale dialogue PCR dataset, to investigate whether and how the visual information can help resolve pronouns in dialogues.
Multilingual and Multi-Aspect Hate Speech Analysis
Current research on hate speech analysis is typically oriented towards monolingual and single classification tasks.
Motif Enhanced Recommendation over Heterogeneous Information Network
In this paper, we propose to use motifs to capture higher-order relations among nodes of same type in a HIN and develop the motif-enhanced meta-path (MEMP) to combine motif-based higher-order relations with edge-based first-order relations.
Hyper-Path-Based Representation Learning for Hyper-Networks
Then a carefully designed algorithm, Hyper-gram, utilizes these random walks to capture both pairwise relationships and tuplewise relationships in the whole hyper-networks.
Knowledge-aware Pronoun Coreference Resolution
Resolving pronoun coreference requires knowledge support, especially for particular domains (e. g., medicine).
Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision
Lack of labeled training data is a major bottleneck for neural network based aspect and opinion term extraction on product reviews.
Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks
In this paper, we design an event meta-schema to characterize the semantic relatedness of social events and build an event-based heterogeneous information network (HIN) integrating information from external knowledge base, and propose a novel Pair-wise Popularity Graph Convolutional Network (PP-GCN) based fine-grained social event categorization model.
Beyond Personalization: Social Content Recommendation for Creator Equality and Consumer Satisfaction
An effective content recommendation in modern social media platforms should benefit both creators to bring genuine benefits to them and consumers to help them get really interesting content.
Incorporating Context and External Knowledge for Pronoun Coreference Resolution
Linking pronominal expressions to the correct references requires, in many cases, better analysis of the contextual information and external knowledge.
SP-10K: A Large-scale Evaluation Set for Selectional Preference Acquisition
Selectional Preference (SP) is a commonly observed language phenomenon and proved to be useful in many natural language processing tasks.
ASER: A Large-scale Eventuality Knowledge Graph
Understanding human's language requires complex world knowledge.
Relation Discovery with Out-of-Relation Knowledge Base as Supervision
In this paper, we study the problem of how to use out-of-relation knowledge bases to supervise the discovery of unseen relations, where out-of-relation means that relations to discover from the text corpus and those in knowledge bases are not overlapped.
A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification
These word pairs can be extracted by using dependency parsers and simple rules.
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.
Efficient Path Prediction for Semi-Supervised and Weakly Supervised Hierarchical Text Classification
Hierarchical text classification has many real-world applications.
MetaGAN: An Adversarial Approach to Few-Shot Learning
In this paper, we propose a conceptually simple and general framework called MetaGAN for few-shot learning problems.
Entity Linking within a Social Media Platform: A Case Study on Yelp
In this paper, we study a new entity linking problem where both the entity mentions and the target entities are within a same social media platform.
Side Information Fusion for Recommender Systems over Heterogeneous Information Network
Collaborative filtering (CF) has been one of the most important and popular recommendation methods, which aims at predicting users' preferences (ratings) based on their past behaviors.
Understanding Hidden Memories of Recurrent Neural Networks
We propose a technique to explain the function of individual hidden state units based on their expected response to input texts.
Document-Level Multi-Aspect Sentiment Classification as Machine Comprehension
Document-level multi-aspect sentiment classification is an important task for customer relation management.
Joint Embeddings of Chinese Words, Characters, and Fine-grained Subcharacter Components
Word embeddings have attracted much attention recently.
NNEMBs at SemEval-2017 Task 4: Neural Twitter Sentiment Classification: a Simple Ensemble Method with Different Embeddings
In this paper, we propose a simple and effective ensemble method to further boost the performances of neural models.
Subjective Knowledge Acquisition and Enrichment Powered By Crowdsourcing
In our work, we propose a system, called crowdsourced subjective knowledge acquisition (CoSKA), for subjective knowledge acquisition powered by crowdsourcing and existing KBs.
Machine Learning with World Knowledge: The Position and Survey
In this paper, we will discuss how to use the existing general-purpose world knowledge to enhance machine learning processes, by enriching the features or reducing the labeling work.
Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
Despite the successes in capturing continuous distributions, the application of generative adversarial networks (GANs) to discrete settings, like natural language tasks, is rather restricted.
Cross-lingual Dataless Classification for Languages with Small Wikipedia Presence
We use a word-level dictionary to convert documents in a SWL to a large-Wikipedia language (LWLs), and then perform CLDDC based on the LWL's Wikipedia.
World Knowledge as Indirect Supervision for Document Clustering
We provide three ways to specify the world knowledge to domains by resolving the ambiguity of the entities and their types, and represent the data with world knowledge as a heterogeneous information network.
Tracking Idea Flows between Social Groups
To facilitate users in analyzing the flow, we present a method to model the flow behaviors that aims at identifying the lead-lag relationships between word clusters of different user groups.
