Search Results for author:
Found 10 papers, 9 papers with code
Domain Generalization for Text Classification with Memory-Based Supervised Contrastive Learning
While there is much research on cross-domain text classification, most existing approaches focus on one-to-one or many-to-one domain adaptation.
SeaLLMs -- Large Language Models for Southeast Asia
Despite the remarkable achievements of large language models (LLMs) in various tasks, there remains a linguistic bias that favors high-resource languages, such as English, often at the expense of low-resource and regional languages.
Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning
Therefore, it is crucial for LLMs to understand the concept of temporal knowledge.
Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data
We conducted experiments on document-level and biomedical relation extraction datasets, and the results showed that our proposed self-training framework consistently outperforms existing competitive methods on the Re-DocRED and ChemDisgene datasets when the training data are incompletely annotated.
Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models
In this paper, we introduce a comprehensive probing dataset \tempreason to evaluate the temporal reasoning capability of large language models.
Unlocking Temporal Question Answering for Large Language Models with Tailor-Made Reasoning Logic
The temporal aspect is a significant dimension of our reality.
Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction
We analyze the causes and effects of the overwhelming false negative problem in the DocRED dataset.
Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation
Our model consistently outperforms strong baselines and its performance exceeds the previous SOTA by 1. 36 F1 and 1. 46 Ign_F1 score on the DocRED leaderboard.
Ranked #2 on
Relation Extraction
on DocRED
Document-level Relation Extraction
Knowledge Distillation
+2
On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation
It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a downstream task.
Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training
To improve the robustness of self-training, in this paper we present class-aware feature self-distillation (CFd) to learn discriminative features from PrLMs, in which PrLM features are self-distilled into a feature adaptation module and the features from the same class are more tightly clustered.
