Search Results for author:
Found 56 papers, 19 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.
Semi-supervised New Event Type Induction and Event Detection
We design a Semi-Supervised Vector Quantized Variational Autoencoder framework to automatically learn a discrete latent type representation for each seen and unseen type and optimize them using seen type event annotations.
Towards Automatic Curation of Antibiotic Resistance Genes via Statement Extraction from Scientific Papers: A Benchmark Dataset and Models
Antibiotic resistance has become a growing worldwide concern as new resistance mechanisms are emerging and spreading globally, and thus detecting and collecting the cause – Antibiotic Resistance Genes (ARGs), have been more critical than ever.
Teamwork Is Not Always Good: An Empirical Study of Classifier Drift in Class-incremental Information Extraction
Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes.
RE$^2$: Region-Aware Relation Extraction from Visually Rich Documents
Current research in form understanding predominantly relies on large pre-trained language models, necessitating extensive data for pre-training.
AMELI: Enhancing Multimodal Entity Linking with Fine-Grained Attributes
We propose attribute-aware multimodal entity linking, where the input is a mention described with a text and image, and the goal is to predict the corresponding target entity from a multimodal knowledge base (KB) where each entity is also described with a text description, a visual image and a set of attributes and values.
Iteratively Improving Biomedical Entity Linking and Event Extraction via Hard Expectation-Maximization
To solve these challenges, we propose joint biomedical entity linking and event extraction by regarding the event structures and entity references in knowledge bases as latent variables and updating the two task-specific models in a hard Expectation-Maximization (EM) fashion: (1) predicting the missing variables for each partially annotated dataset based on the current two task-specific models, and (2) updating the parameters of each model on the corresponding pseudo completed dataset.
The Art of SOCRATIC QUESTIONING: Zero-shot Multimodal Reasoning with Recursive Thinking and Self-Questioning
Socratic Questioning is driven by a Self-Questioning module that employs a large-scale language model to propose sub-problems related to the original problem as intermediate steps and Socratic Questioning recursively backtracks and answers the sub-problems until reaches the original problem.
Understand the Dynamic World: An End-to-End Knowledge Informed Framework for Open Domain Entity State Tracking
Open domain entity state tracking aims to predict reasonable state changes of entities (i. e., [attribute] of [entity] was [before_state] and [after_state] afterwards) given the action descriptions.
Rationalization for Explainable NLP: A Survey
Recent improvements in natural language generation have made rationalization an attractive technique because it is intuitive, human-comprehensible, and accessible to non-technical users.
ExClaim: Explainable Neural Claim Verification Using Rationalization
We introduce a novel claim verification approach, namely: ExClaim, that attempts to provide an explainable claim verification system with foundational evidence.
MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning
We take OFA as the base pre-trained model for multimodal instruction tuning, and to improve its performance, we explore multiple transfer learning strategies to leverage the large-scale Natural Instructions dataset.
MOCHA: A Multi-Task Training Approach for Coherent Text Generation from Cognitive Perspective
Teaching neural models to generate narrative coherent texts is a critical problem.
Multimedia Generative Script Learning for Task Planning
Therefore, we propose a new task, Multimedia Generative Script Learning, to generate subsequent steps by tracking historical states in both text and vision modalities, as well as presenting the first benchmark containing 2, 338 tasks and 31, 496 steps with descriptive images.
Contrastive Learning
Multimedia Generative Script Learning
+2
End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models
We propose the end-to-end multimodal fact-checking and explanation generation, where the input is a claim and a large collection of web sources, including articles, images, videos, and tweets, and the goal is to assess the truthfulness of the claim by retrieving relevant evidence and predicting a truthfulness label (i. e., support, refute and not enough information), and generate a rationalization statement to explain the reasoning and ruling process.
Improve Event Extraction via Self-Training with Gradient Guidance
Data scarcity and imbalance have been the main factors that hinder the progress of event extraction (EE).
Probing Script Knowledge from Pre-Trained Models
Script knowledge is critical for humans to understand the broad daily tasks and routine activities in the world.
Identifying and Measuring Token-Level Sentiment Bias in Pre-trained Language Models with Prompts
Due to the superior performance, large-scale pre-trained language models (PLMs) have been widely adopted in many aspects of human society.
Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection
Lifelong event detection aims to incrementally update a model with new event types and data while retaining the capability on previously learned old types.
The Art of Prompting: Event Detection based on Type Specific Prompts
We compare various forms of prompts to represent event types and develop a unified framework to incorporate the event type specific prompts for supervised, few-shot, and zero-shot event detection.
Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation
Furthermore, we propose a Federated learning paradigm with privacy-preserving Relation embedding aggregation (FedR) to tackle the privacy issue in FedE.
PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation
Despite recent progress of pre-trained language models on generating fluent text, existing methods still suffer from incoherence problems in long-form text generation tasks that require proper content control and planning to form a coherent high-level logical flow.
Efficient Long Sequence Encoding via Synchronization
Pre-trained Transformer models have achieved successes in a wide range of NLP tasks, but are inefficient when dealing with long input sequences.
What Makes the Story Forward? Inferring Commonsense Explanations as Prompts for Future Event Generation
To alleviate the knowledge forgetting issue, we design two modules, Im and Gm, for each type of knowledge, which are combined via prompt tuning.
MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding
Specifically, the task involves multi-hop questions that require reasoning over image-caption pairs to identify the grounded visual object being referred to and then predicting a span from the news body text to answer the question.
Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding
Event extraction is typically modeled as a multi-class classification problem where event types and argument roles are treated as atomic symbols.
How Knowledge Graph and Attention Help? A Qualitative Analysis into Bag-level Relation Extraction
In this paper, we contribute a dataset and propose a paradigm to quantitatively evaluate the effect of attention and KG on bag-level relation extraction (RE).
How Knowledge Graph and Attention Help? A Quantitative Analysis into Bag-level Relation Extraction
In this paper, we contribute a dataset and propose a paradigm to quantitatively evaluate the effect of attention and KG on bag-level relation extraction (RE).
Extracting Temporal Event Relation with Syntax-guided Graph Transformer
Extracting temporal relations (e. g., before, after, and simultaneous) among events is crucial to natural language understanding.
Membership Inference Attacks on Knowledge Graphs
Membership inference attacks (MIAs) infer whether a specific data record is used for target model training.
The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction
We introduce a new concept of Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations.
Global Attention for Name Tagging
Many name tagging approaches use local contextual information with much success, but fail when the local context is ambiguous or limited.
ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
To assist human review process, we build a novel ReviewRobot to automatically assign a review score and write comments for multiple categories such as novelty and meaningful comparison.
Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning
In this paper, we introduce Cosmos QA, a large-scale dataset of 35, 600 problems that require commonsense-based reading comprehension, formulated as multiple-choice questions.
Biomedical Event Extraction based on Knowledge-driven Tree-LSTM
Event extraction for the biomedical domain is more challenging than that in the general news domain since it requires broader acquisition of domain-specific knowledge and deeper understanding of complex contexts.
Cross-lingual Multi-Level Adversarial Transfer to Enhance Low-Resource Name Tagging
We focus on improving name tagging for low-resource languages using annotations from related languages.
PaperRobot: Incremental Draft Generation of Scientific Ideas
We present a PaperRobot who performs as an automatic research assistant by (1) conducting deep understanding of a large collection of human-written papers in a target domain and constructing comprehensive background knowledge graphs (KGs); (2) creating new ideas by predicting links from the background KGs, by combining graph attention and contextual text attention; (3) incrementally writing some key elements of a new paper based on memory-attention networks: from the input title along with predicted related entities to generate a paper abstract, from the abstract to generate conclusion and future work, and finally from future work to generate a title for a follow-on paper.
Genre Separation Network with Adversarial Training for Cross-genre Relation Extraction
Relation Extraction suffers from dramatical performance decrease when training a model on one genre and directly applying it to a new genre, due to the distinct feature distributions.
Describing a Knowledge Base
We aim to automatically generate natural language descriptions about an input structured knowledge base (KB).
Chengyu Cloze Test
We present a neural recommendation model for Chengyu, which is a special type of Chinese idiom.
Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension
The new dataset, ProPara, is the first to contain natural (rather than machine-generated) text about a changing world along with a full annotation of entity states (location and existence) during those changes (81k datapoints).
Ranked #4 on
Procedural Text Understanding
on ProPara
Paper Abstract Writing through Editing Mechanism
We present a paper abstract writing system based on an attentive neural sequence-to-sequence model that can take a title as input and automatically generate an abstract.
Ranked #1 on
Paper generation
on ACL Title and Abstract Dataset
Multi-lingual Common Semantic Space Construction via Cluster-consistent Word Embedding
We construct a multilingual common semantic space based on distributional semantics, where words from multiple languages are projected into a shared space to enable knowledge and resource transfer across languages.
Entity-aware Image Caption Generation
Current image captioning approaches generate descriptions which lack specific information, such as named entities that are involved in the images.
Open Relation Extraction and Grounding
Previous open Relation Extraction (open RE) approaches mainly rely on linguistic patterns and constraints to extract important relational triples from large-scale corpora.
Learning Phrase Embeddings from Paraphrases with GRUs
Learning phrase representations has been widely explored in many Natural Language Processing (NLP) tasks (e. g., Sentiment Analysis, Machine Translation) and has shown promising improvements.
Zero-Shot Transfer Learning for Event Extraction
Most previous event extraction studies have relied heavily on features derived from annotated event mentions, thus cannot be applied to new event types without annotation effort.
Improving Slot Filling Performance with Attentive Neural Networks on Dependency Structures
Slot Filling (SF) aims to extract the values of certain types of attributes (or slots, such as person:cities\_of\_residence) for a given entity from a large collection of source documents.
Bridge Text and Knowledge by Learning Multi-Prototype Entity Mention Embedding
Integrating text and knowledge into a unified semantic space has attracted significant research interests recently.
Building a Fine-Grained Entity Typing System Overnight for a New X (X = Language, Domain, Genre)
Recent research has shown great progress on fine-grained entity typing.
