Search Results for author:
Found 96 papers, 21 papers with code
Unsupervised Domain Adaptation for Text Classification via Meta Self-Paced Learning
A shift in data distribution can have a significant impact on performance of a text classification model.
Learning Cross-lingual Representations for Event Coreference Resolution with Multi-view Alignment and Optimal Transport
We study a new problem of cross-lingual transfer learning for event coreference resolution (ECR) where models trained on data from a source language are adapted for evaluations in different target languages.
MECI: A Multilingual Dataset for Event Causality Identification
Our dataset thus enable a new research direction on cross-lingual transfer learning for ECI.
Event Detection: Gate Diversity and Syntactic Importance Scores for Graph Convolution Neural Networks
Recent studies on event detection (ED) have shown that the syntactic dependency graph can be employed in graph convolution neural networks (GCN) to achieve state-of-the-art performance.
Introducing a New Dataset for Event Detection in Cybersecurity Texts
Detecting cybersecurity events is necessary to keep us informed about the fast growing number of such events reported in text.
Hierarchical Graph Convolutional Networks for Jointly Resolving Cross-document Coreference of Entity and Event Mentions
Prior work has demonstrated the benefits of the predicate-argument information and document context for resolving the coreference of event mentions.
Improving Cross-Lingual Transfer for Event Argument Extraction with Language-Universal Sentence Structures
Previous work on CEAE has shown the cross-lingual benefits of universal dependency trees in capturing shared syntactic structures of sentences across languages.
Parameter-Efficient Domain Knowledge Integration from Multiple Sources for Biomedical Pre-trained Language Models
These knowledge adapters are pre-trained for individual domain knowledge sources and integrated via an attention-based knowledge controller to enrich PLMs.
Learning Prototype Representations Across Few-Shot Tasks for Event Detection
We address the sampling bias and outlier issues in few-shot learning for event detection, a subtask of information extraction.
Event Extraction in Video Transcripts
As such, the challenges of EE in informal and noisy texts are not adequately studied.
Keyphrase Prediction from Video Transcripts: New Dataset and Directions
To this end, this work studies new challenges of KP in transcripts of videos, an understudied domain for KP that involves informal texts and non-cohesive presentation styles.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Does It Happen? Multi-hop Path Structures for Event Factuality Prediction with Graph Transformer Networks
In this work, we show that the multi-hop paths between the words are also necessary to compute the sentence structures for EFP.
Fine-grained Temporal Relation Extraction with Ordered-Neuron LSTM and Graph Convolutional Networks
In this work, we propose to fill this gap by introducing novel methods to integrate the syntactic structures into the deep learning models for FineTempRel.
Crosslingual Transfer Learning for Relation and Event Extraction via Word Category and Class Alignments
To address this issue, we propose a novel crosslingual alignment method that leverages class information of REE tasks for representation learning.
Modeling Document-Level Context for Event Detection via Important Context Selection
To address this issue, we propose a novel method to model document-level context for ED that dynamically selects relevant sentences in the document for the event prediction of the target sentence.
GloCOM: A Short Text Neural Topic Model via Global Clustering Context
Uncovering hidden topics from short texts is challenging for traditional and neural models due to data sparsity, which limits word co-occurrence patterns, and label sparsity, stemming from incomplete reconstruction targets.
Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering
Retrieval-augmented generation (RAG) has emerged as a promising approach to enhance the performance of large language models (LLMs) in knowledge-intensive tasks such as those from medical domain.
Zero-shot Cross-lingual Transfer Learning with Multiple Source and Target Languages for Information Extraction: Language Selection and Adversarial Training
The majority of previous researches addressing multi-lingual IE are limited to zero-shot cross-lingual single-transfer (one-to-one) setting, with high-resource languages predominantly as source training data.
A Survey of Small Language Models
We propose a novel taxonomy for categorizing the methods used to optimize SLMs, including model compression, pruning, and quantization techniques.
Taipan: Efficient and Expressive State Space Language Models with Selective Attention
Efficient long-context language modeling remains a significant challenge in Natural Language Processing (NLP).
Lifelong Event Detection via Optimal Transport
Continual Event Detection (CED) poses a formidable challenge due to the catastrophic forgetting phenomenon, where learning new tasks (with new coming event types) hampers performance on previous ones.
Preserving Generalization of Language models in Few-shot Continual Relation Extraction
Few-shot Continual Relations Extraction (FCRE) is an emerging and dynamic area of study where models can sequentially integrate knowledge from new relations with limited labeled data while circumventing catastrophic forgetting and preserving prior knowledge from pre-trained backbones.
NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization
Recent advances in neural topic models have concentrated on two primary directions: the integration of the inference network (encoder) with a pre-trained language model (PLM) and the modeling of the relationship between words and topics in the generative model (decoder).
Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective
Activation Editing, which involves directly editting the internal representations of large language models (LLMs) to alter their behaviors and achieve desired properties, has emerged as a promising area of research.
ULLME: A Unified Framework for Large Language Model Embeddings with Generation-Augmented Learning
This is due to their causal attention mechanism and the misalignment between their pre-training objectives and the text ranking tasks.
Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language Models
We introduce an approach to identifying speaker names in dialogue transcripts, a crucial task for enhancing content accessibility and searchability in digital media archives.
LongLaMP: A Benchmark for Personalized Long-form Text Generation
In this work, we demonstrate the importance of user-specific personalization for long-text generation tasks and develop the Long-text Language Model Personalization (LongLaMP) Benchmark.
ToVo: Toxicity Taxonomy via Voting
To address these issues, we propose a dataset creation mechanism that integrates voting and chain-of-thought processes, producing a high-quality open-source dataset for toxic content detection.
Realistic Evaluation of Toxicity in Large Language Models
Large language models (LLMs) have become integral to our professional workflows and daily lives.
BKEE: Pioneering Event Extraction in the Vietnamese Language
Event Extraction (EE) is a fundamental task in information extraction, aimed at identifying events and their associated arguments within textual data.
CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages
However, when it comes to training datasets for these LLMs, especially the recent state-of-the-art models, they are often not fully disclosed.
Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback
Okapi introduces instruction and response-ranked data in 26 diverse languages to facilitate the experiments and development of future multilingual LLM research.
Boosting Punctuation Restoration with Data Generation and Reinforcement Learning
Punctuation restoration is an important task in automatic speech recognition (ASR) which aim to restore the syntactic structure of generated ASR texts to improve readability.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Question-Context Alignment and Answer-Context Dependencies for Effective Answer Sentence Selection
In this paper, we propose to improve the candidate scoring by explicitly incorporating the dependencies between question-context and answer-context into the final representation of a candidate.
ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning
The answer to this question requires a thorough evaluation of ChatGPT over multiple tasks with diverse languages and large datasets (i. e., beyond reported anecdotes), which is still missing or limited in current research.
Textual Data Augmentation for Patient Outcomes Prediction
Deep learning models have demonstrated superior performance in various healthcare applications.
MINION: a Large-Scale and Diverse Dataset for Multilingual Event Detection
Event Detection (ED) is the task of identifying and classifying trigger words of event mentions in text.
MEE: A Novel Multilingual Event Extraction Dataset
Event Extraction (EE) is one of the fundamental tasks in Information Extraction (IE) that aims to recognize event mentions and their arguments (i. e., participants) from text.
Improving Keyphrase Extraction with Data Augmentation and Information Filtering
Keyphrase extraction is one of the essential tasks for document understanding in NLP.
Tutorial Recommendation for Livestream Videos using Discourse-Level Consistency and Ontology-Based Filtering
In order to alleviate this issue, one solution is to link the streaming videos with the relevant tutorial available for the tools used in the streaming video.
Symlink: A New Dataset for Scientific Symbol-Description Linking
Mathematical symbols and descriptions appear in various forms across document section boundaries without explicit markup.
SemEval 2022 Task 12: Symlink- Linking Mathematical Symbols to their Descriptions
Given the increasing number of livestreaming videos, automatic speech recognition and post-processing for livestreaming video transcripts are crucial for efficient data management as well as knowledge mining.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
MACRONYM: A Large-Scale Dataset for Multilingual and Multi-Domain Acronym Extraction
Acronym extraction is the task of identifying acronyms and their expanded forms in texts that is necessary for various NLP applications.
FAMIE: A Fast Active Learning Framework for Multilingual Information Extraction
FAMIE is designed to address a fundamental problem in existing AL frameworks where annotators need to wait for a long time between annotation batches due to the time-consuming nature of model training and data selection at each AL iteration.
Predicting Patient Readmission Risk from Medical Text via Knowledge Graph Enhanced Multiview Graph Convolution
Unplanned intensive care unit (ICU) readmission rate is an important metric for evaluating the quality of hospital care.
Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey
Large, pre-trained transformer-based language models such as BERT have drastically changed the Natural Language Processing (NLP) field.
DPR at SemEval-2021 Task 8: Dynamic Path Reasoning for Measurement Relation Extraction
To this end, in this paper, we propose a novel model for the task of measurement relation extraction (MRE) whose goal is to recognize the relation between measured entities, quantities, and conditions mentioned in a document.
Unleash GPT-2 Power for Event Detection
To prevent the noises inevitable in automatically generated data from hampering training process, we propose to exploit a teacher-student architecture in which the teacher is supposed to learn anchor knowledge from the original data.
Exploiting Document Structures and Cluster Consistencies for Event Coreference Resolution
In addition, consistency constraints between golden and predicted clusters of event mentions have not been considered to improve representation learning in prior deep learning models for ECR.
Dictionary-Guided Scene Text Recognition
Language prior plays an important role in the way humans perceive and recognize text in the wild.
Graph Convolutional Networks for Event Causality Identification with Rich Document-level Structures
Although deep learning models have recently shown state-of-the-art performance for ECI, they are limited to the intra-sentence setting where event mention pairs are presented in the same sentences.
Fine-Grained Event Trigger Detection
Most of the previous work on Event Detection (ED) has only considered the datasets with a small number of event types (i. e., up to 38 types).
Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks
Existing works on information extraction (IE) have mainly solved the four main tasks separately (entity mention recognition, relation extraction, event trigger detection, and argument extraction), thus failing to benefit from inter-dependencies between tasks.
MadDog: A Web-based System for Acronym Identification and Disambiguation
However, none of the existing works provide a unified solution capable of processing acronyms in various domains and to be publicly available.
Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing
Finally, we create a demo video for Trankit at: https://youtu. be/q0KGP3zGjGc.
Ranked #1 on
Sentence segmentation
on UD2.5 test
Acronym Identification and Disambiguation Shared Tasks for Scientific Document Understanding
To push forward research in this direction, we have organized two shared task for acronym identification and acronym disambiguation in scientific documents, named AI@SDU and AD@SDU, respectively.
Exploiting Node Content for Multiview Graph Convolutional Network and Adversarial Regularization
Network representation learning (NRL) is crucial in the area of graph learning.
Structural and Functional Decomposition for Personality Image Captioning in a Communication Game
Personality image captioning (PIC) aims to describe an image with a natural language caption given a personality trait.
The Dots Have Their Values: Exploiting the Node-Edge Connections in Graph-based Neural Models for Document-level Relation Extraction
However, this model does not capture the representations for the nodes in the graphs, thus preventing it from effectively encoding the specific and relevant information of the nodes for DRE.
Document-level Relation Extraction
Representation Learning
+1
What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation
The proposed model outperforms the state-of-the-art models on the new AD dataset, providing a strong baseline for future research on this dataset.
Event Detection: Gate Diversity and Syntactic Importance Scoresfor Graph Convolution Neural Networks
Recent studies on event detection (ED) haveshown that the syntactic dependency graph canbe employed in graph convolution neural net-works (GCN) to achieve state-of-the-art per-formance.
Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning
In this work, we propose to incorporate the syntactic structures of the sentences into the deep learning models for TOWE, leveraging the syntax-based opinion possibility scores and the syntactic connections between the words.
Aspect-Based Sentiment Analysis
Aspect-oriented Opinion Extraction
+2
Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation
In addition, we propose a mechanism to obtain the importance scores for each word in the sentences based on the dependency trees that are then injected into the model to improve the representation vectors for ABSA.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction
The goal of Event Argument Extraction (EAE) is to find the role of each entity mention for a given event trigger word.
Exploiting the Syntax-Model Consistency for Neural Relation Extraction
In order to overcome these issues, we propose a novel deep learning model for RE that uses the dependency trees to extract the syntax-based importance scores for the words, serving as a tree representation to introduce syntactic information into the models with greater generalization.
Extensively Matching for Few-shot Learning Event Detection
In this work, weformulate event detection as a few-shot learn-ing problem to enable to extend event detec-tion to new event types.
Exploiting the Matching Information in the Support Set for Few Shot Event Classification
The existing event classification (EC) work primarily focuseson the traditional supervised learning setting in which models are unableto extract event mentions of new/unseen event types.
Improving Slot Filling by Utilizing Contextual Information
To address this issue, in this paper, we propose a novel method to incorporate the contextual information in two different levels, i. e., representation level and task-specific (i. e., label) level.
Ranked #6 on
Slot Filling
on SNIPS
A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency
In this work, we propose a novel model for DE that simultaneously performs the two tasks in a single framework to benefit from their inter-dependencies.
On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning
Deep learning models have achieved state-of-the-art performances on many relation extraction datasets.
Extending Event Detection to New Types with Learning from Keywords
We introduce a novel feature-based attention mechanism for convolutional neural networks for event detection in the new formulation.
Language-independent Cross-lingual Contextual Representations
Contextual representation models like BERT have achieved state-of-the-art performance on a diverse range of NLP tasks.
Improving Cross-Domain Performance for Relation Extraction via Dependency Prediction and Information Flow Control
The current deep learning models for relation extraction has mainly exploited this dependency information by guiding their computation along the structures of the dependency trees.
Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures
In this work, we introduce a novel graph-based neural network for EFP that can integrate the semantic and syntactic information more effectively.
Employing the Correspondence of Relations and Connectives to Identify Implicit Discourse Relations via Label Embeddings
It has been shown that implicit connectives can be exploited to improve the performance of the models for implicit discourse relation recognition (IDRR).
One for All: Neural Joint Modeling of Entities and Events
The previous work for event extraction has mainly focused on the predictions for event triggers and argument roles, treating entity mentions as being provided by human annotators.
Systematic Generalization: What Is Required and Can It Be Learned?
Numerous models for grounded language understanding have been recently proposed, including (i) generic models that can be easily adapted to any given task and (ii) intuitively appealing modular models that require background knowledge to be instantiated.
A Case Study on Learning a Unified Encoder of Relations
Typical relation extraction models are trained on a single corpus annotated with a pre-defined relation schema.
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts.
Similar but not the Same: Word Sense Disambiguation Improves Event Detection via Neural Representation Matching
Event detection (ED) and word sense disambiguation (WSD) are two similar tasks in that they both involve identifying the classes (i. e. event types or word senses) of some word in a given sentence.
Who is Killed by Police: Introducing Supervised Attention for Hierarchical LSTMs
The early work in this field \cite{keith2017identifying} proposed a distant supervision framework based on Expectation Maximization (EM) to deal with the multiple appearances of the names in documents.
A Deep Learning Model with Hierarchical LSTMs and Supervised Attention for Anti-Phishing
Anti-phishing aims to detect phishing content/documents in a pool of textual data.
Domain Adaptation for Relation Extraction with Domain Adversarial Neural Network
Our method is a joint model consisting of a CNN-based relation classifier and a domain-adversarial classifier.
Joint Learning of Local and Global Features for Entity Linking via Neural Networks
Previous studies have highlighted the necessity for entity linking systems to capture the local entity-mention similarities and the global topical coherence.
Toward Mention Detection Robustness with Recurrent Neural Networks
One of the key challenges in natural language processing (NLP) is to yield good performance across application domains and languages.
Combining Neural Networks and Log-linear Models to Improve Relation Extraction
The last decade has witnessed the success of the traditional feature-based method on exploiting the discrete structures such as words or lexical patterns to extract relations from text.
Ranked #1 on
Relation Extraction
on ACE 2005
(Cross Sentence metric)
Relation Extraction: Perspective from Convolutional Neural Networks
Ranked #1 on
Relation Extraction
on ACE 2005
(Cross Sentence metric)
