Search Results for author:
Found 26 papers, 20 papers with code
Text-Based Reasoning About Vector Graphics
By casting an image to a text-based representation, we can leverage the power of language models to learn alignment from SVG to visual primitives and generalize to unseen question-answering tasks.
Event Detection from Social Media for Epidemic Prediction
In our work, we pioneer exploiting Event Detection (ED) for better preparedness and early warnings of any upcoming epidemic by developing a framework to extract and analyze epidemic-related events from social media posts.
TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction
In this work, we identify and address evaluation challenges, including inconsistency due to varying data assumptions or preprocessing steps, the insufficiency of current evaluation frameworks that may introduce dataset or data split bias, and the low reproducibility of some previous approaches.
Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer
In this paper, we propose a simple yet effective method, SALT, to improve the zero-shot cross-lingual transfer of the multilingual pretrained language models without the help of such external data.
Contextual Label Projection for Cross-Lingual Structured Prediction
Label projection, which involves obtaining translated labels and texts jointly, is essential for leveraging machine translation to facilitate cross-lingual transfer in structured prediction tasks.
ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation
Paraphrase generation is a long-standing task in natural language processing (NLP).
AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model
However, existing generation-based EAE models mostly focus on problem re-formulation and prompt design, without incorporating additional information that has been shown to be effective for classification-based models, such as the abstract meaning representation (AMR) of the input passages.
PIP: Parse-Instructed Prefix for Syntactically Controlled Paraphrase Generation
Existing fine-tuning methods for this task are costly as all the parameters of the model need to be updated during the training process.
Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis
Recent research has revealed that machine learning models have a tendency to leverage spurious correlations that exist in the training set but may not hold true in general circumstances.
Learning Easily Updated General Purpose Text Representations with Adaptable Task-Specific Prefixes
Fine-tuning a large pre-trained language model for each downstream task causes computational burdens in the inference time due to several times of forward passes.
Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations
In this paper, we demonstrate that leveraging Abstract Meaning Representations (AMR) can greatly improve the performance of unsupervised syntactically controlled paraphrase generation.
TAGPRIME: A Unified Framework for Relational Structure Extraction
In this work, we propose to take a unified view of all these tasks and introduce TAGPRIME to address relational structure extraction problems.
GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Roles
We utilize this ontology to further introduce GENEVA, a diverse generalizability benchmarking dataset comprising four test suites, aimed at evaluating models' ability to handle limited data and unseen event type generalization.
A Comparative Survey of Deep Active Learning
In this work, We construct a DAL toolkit, DeepAL+, by re-implementing 19 highly-cited DAL methods.
Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction
We present a study on leveraging multilingual pre-trained generative language models for zero-shot cross-lingual event argument extraction (EAE).
DeepAL: Deep Active Learning in Python
We present DeepAL, a Python library that implements several common strategies for active learning, with a particular emphasis on deep active learning.
DEGREE: A Data-Efficient Generation-Based Event Extraction Model
Given a passage and a manually designed prompt, DEGREE learns to summarize the events mentioned in the passage into a natural sentence that follows a predefined pattern.
Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training
Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer.
Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models
In this work, we present ParaBART, a semantic sentence embedding model that learns to disentangle semantics and syntax in sentence embeddings obtained by pre-trained language models.
Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs
We also demonstrate that the performance of SynPG is competitive or even better than supervised models when the unannotated data is large.
Generating Sports News from Live Commentary: A Chinese Dataset for Sports Game Summarization
To deeply study this task, we present SportsSum, a Chinese sports game summarization dataset which contains 5, 428 soccer games of live commentaries and the corresponding news articles.
Examining Gender Bias in Languages with Grammatical Gender
Recent studies have shown that word embeddings exhibit gender bias inherited from the training corpora.
JECL: Joint Embedding and Cluster Learning for Image-Text Pairs
We propose JECL, a method for clustering image-caption pairs by training parallel encoders with regularized clustering and alignment objectives, simultaneously learning both representations and cluster assignments.
Dynamic Principal Projection for Cost-Sensitive Online Multi-Label Classification
The foundation of CS-DPP is an online LSDR framework derived from a leading LSDR algorithm.
Cost-Sensitive Reference Pair Encoding for Multi-Label Learning
Label space expansion for multi-label classification (MLC) is a methodology that encodes the original label vectors to higher dimensional codes before training and decodes the predicted codes back to the label vectors during testing.
Cost-Sensitive Label Embedding for Multi-Label Classification
Furthermore, extensive experimental results demonstrate that CLEMS is significantly better than a wide spectrum of existing LE algorithms and state-of-the-art cost-sensitive algorithms across different cost functions.
