Sean Ren

Cross-lingual Continual Learning

ACL

Jul 2023

The longstanding goal of multi-lingual learning has been to develop a universal cross-lingual model that can withstand the changes in multi-lingual data distributions. There has been a large amount of work to adapt such multi-lingual models to unseen target languages. However, the majority of work in this direction focuses on the standard one-hop transfer learning pipeline from source to target languages, whereas in realistic scenarios, new languages can be incorporated at any time in a sequential manner. In this paper, we present a principled Cross-lingual Continual Learning (CCL) evaluation paradigm, where we analyze different categories of approaches used to continually adapt to emerging data from different languages. We provide insights

N

X-METRA-ADA: Cross-lingual Meta-Transfer learning Adaptation to Natural Language Understanding and Question Answering

NAACL

Jun 2021

Multilingual models, such as M-BERT and XLM-R, have gained increasing popularity, due to their zero-shot cross-lingual transfer learning capabilities. However, their generalization ability is still inconsistent for typologically diverse languages and across different benchmarks. Recently, meta-learning has garnered attention as a promising technique for enhancing transfer learning under low-resource scenarios: particularly for cross-lingual transfer in Natural Language Understanding (NLU). In this work, we propose X-METRA-ADA, a cross-lingual MEta-TRAnsfer learning ADAptation approach for NLU. Our approach adapts MAML, an optimization-based meta-learning approach, to learn to adapt to new languages. We extensively evaluate our framework on

A

Learning Contextualized Knowledge Structures for Commonsense Reasoning

Accepted at The ACL

Oct 2020

Recently, neural-symbolic models have achieved noteworthy success in leveraging knowledge graphs (KGs) for commonsense reasoning tasks, like question answering (QA). However, fact sparsity, inherent in human-annotated KGs, can hinder such models from retrieving task-relevant knowledge. To address these issues, we propose Hybrid Graph Network (HGN), a neural-symbolic model that reasons over both extracted (human-labeled) and generated facts within the same learned graph structure. Given a KG subgraph of extracted facts, HGN is jointly trained to generate complementary facts, encode relational information in the resulting "hybrid" subgraph, and filter out task-irrelevant facts. We demonstrate HGN's ability to produce contextually pertinent su

W

Comparative Document Analysis for Large Text Corpora

WSDM

Jan 2016

E

AFET: Automatic Fine-Grained Entity Typing by Hierarchical Partial-Label Embedding

EMNLP

Jan 2016

W

Personalized Entity Recommendation in Heterogeneous Information Networks

WSDM

W

Heterogeneous Graph-Based Intent Learning With Queries, Web Pages and Wikipedia Concepts

WSDM

W

Representing Documents via Latent Keyphrase Inference

Www

S

ClusType: Effective Entity Recognition and Typing by Relation Phrase-Based Clustering

SIGKDD

P

HeteRec: Entity Recommendation in Heterogeneous Information Networks with Implicit User Feedback

Proc of ACM Int Conf Series on Recommendation Systems RecSys Hong Kong Oct

W

Synonym Discovery for Structured Entities on Heterogeneous Graphs

Www

P

Personalized Entity Recommendation in Heterogeneous Information Networks with Implicit User Feedback

Proc Int Conf on Web Search and Data Mining WSDM

n

Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding

nd ACM SIGKDD Conference on Knowledge Discovery and Data MiningKDD

S

Mining Quality Phrases from Massive Text Corpora

SIGMOD

Jialu and I contributed to this paper equally.

About

Detail

Timeline

Résumé