Papers by Guoqing Zheng

8 papers
A Conditional Generative Matching Model for Multi-lingual Reply Suggestion (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing models for multilingual RS are limited by capacity and data distribution skew . we propose Conditional Generative Matching models (CGM) to overcome these challenges .
Approach: They propose Conditional Generative Matching models to address multilingual RS challenges . they use expressive message conditional priors, mixture densities and latent alignment . results exceed ROUGE scores by 10% on average, and 16% for low resource languages .
Outcome: The proposed model exceeds baselines in relevance by 10% on average and 16% for low resource languages.
WALNUT: A Benchmark on Semi-weakly Supervised Learning for Natural Language Understanding (2022.naacl-main)

Copied to clipboard

Challenge: Existing studies on weak supervision for NLU focus on a specific task or simulate weak supervision signals from ground-truth labels.
Approach: They propose a benchmark to advocate and facilitate research on weak supervision for NLU . they use document-level and token-level prediction tasks as examples .
Outcome: The proposed benchmark advocates and facilitates research on weak supervision for NLU tasks.
Self-Training with Weak Supervision (2021.naacl-main)

Copied to clipboard

Challenge: State-of-the-art deep neural networks require large amounts of labeled training data that is expensive to obtain or not available for many tasks.
Approach: They propose a weak supervision framework that leverages all available data for a given task . they leverage task-specific unlabeled data through self-training with a model that predicts pseudo-labels for instances that may not be covered by weak rules .
Outcome: The proposed framework improves on state-of-the-art datasets on six benchmark tasks.
Boosting Natural Language Generation from Instructions with Meta-Learning (2022.emnlp-main)

Copied to clipboard

Challenge: Recent work shows that language models trained with multi-task instructional learning (MTIL) can solve diverse NLP tasks in zero-shot settings with improved performance compared to prompt tuning.
Approach: They propose to adapt meta-learning to MTIL in three directions: 1) Model Agnostic Meta Learning (MAML), 2) Hyper-Network adaptation to generate task specific parameters conditioned on instructions.
Outcome: The proposed approaches improve over strong baselines in zero-shot settings and are most impactful when the test tasks are strictly zero- shot and are "hard"
Axiomatic Preference Modeling for Longform Question Answering (2023.emnlp-main)

Copied to clipboard

Challenge: Recent advances in large language models have helped bridge the "alignment gap" between the responses of raw pretrained language models and responses that resonate more closely with human preferences.
Approach: They propose to use a axiomatic framework to generate a rich variety of preference signals to uphold these signals.
Outcome: The proposed model outperforms GPT-4 and ChatGPT in preference scoring.
Hybrid-RACA: Hybrid Retrieval-Augmented Composition Assistance for Real-time Text Prediction (2024.emnlp-industry)

Copied to clipboard

Challenge: Large language models (LLMs) enhanced with retrieval augmentation have shown great performance in many applications, but their computational overhead and additional retrieval step limit their effectiveness in real-time tasks.
Approach: They propose a system that combines a cloud-based LLM with a smaller client-side model through retrieval augmented memory to provide real-time text prediction.
Outcome: The proposed system can generate better responses from the cloud-based model while maintaining low latency.
A Dataset and Baselines for Multilingual Reply Suggestion (2021.acl-long)

Copied to clipboard

Challenge: Reply suggestion models help users process emails and chats faster.
Approach: They present a multilingual reply suggestion dataset with ten languages . they build a generation model and a retrieval model as baselines for MRS .
Outcome: The proposed model complements existing benchmarks for cross-lingual generalization . the model has different strengths in the English monolingual setting and requires different strategies to generalize across languages.
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning (2021.naacl-main)

Copied to clipboard

Challenge: Recent work shows that multilingual representations are disjointed across languages, bringing additional challenges for transfer onto extremely low-resource languages.
Approach: They propose a meta-learning based framework that learns to transform representations judiciously from auxiliary languages to a target one and brings their representation spaces closer for effective transfer.
Outcome: The proposed framework learns to transform representations from auxiliary languages to a target language and brings their representation spaces closer for effective transfer.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations