Challenge: Experimental results show that the proposed model outperforms single-task baseline by 3% and multi-task (without instruction) baseline by 18% on an average.
Approach: They propose a unified model that can learn all 32 instruction tasks of the BoX without any task-specific modules.
Outcome: The proposed model outperforms single-task baseline by 3% and multi-task (without instruction) baseline by 18% on an average.

Similar Papers

Multi-Task Learning for Sequence Tagging: An Empirical Study (C18-1)

Copied to clipboard

Challenge: Existing work on "pairwise" MTL has been validated in sequence tagging but key issues remain about its effectiveness.
Approach: They propose three general multi-task learning approaches on 11 sequence tagging tasks.
Outcome: The proposed approaches improve on 11 sequence tagging tasks.
Bag-of-Words Transfer: Non-Contextual Techniques for Multi-Task Learning (D19-61)

Copied to clipboard

Challenge: Existing approaches to multi-task learning take advantage of transfer among tasks . generative reconstruction of the observations is not included in the standard framework .
Approach: They propose to use a syntactically-oblivious pooling encoder and pre-trained word embeddings to improve sentence-level representations.
Outcome: The proposed techniques yield similar performance on a universe of task combinations while reducing training time and model size.
A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods (2023.eacl-main)

Copied to clipboard

Challenge: Multi-task learning is a popular approach in natural language processing because of its commonalities and differences.
Approach: They propose to summarize recent advances in multi-task learning methods based on their task relatedness into two general multi-step training methods.
Outcome: The proposed methods summarize the tasks and discuss future directions.
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"
Toward Zero-Shot Instruction Following (2024.eacl-srw)

Copied to clipboard

Challenge: a novel approach to zero-shot cross-task generalization is proposed . prior work relied on demonstrations, but this approach could be overestimated .
Approach: They propose a "demonstration-driven instruction following" setting for zero-shot cross-task generalization . they propose to automatically find out critical sentences in a paragraph-style task definition .
Outcome: The proposed approach yields state-of-the-art performance on the Super-NaturalInstructions.
How does Multi-Task Training Affect Transformer In-Context Capabilities? Investigations with Function Classes (2024.naacl-short)

Copied to clipboard

Challenge: Multi-task learning (MTL) for generalist models is a promising direction that offers transfer learning potential.
Approach: They propose to combine multi-task learning (MTL) with in-context learning (ICL) to build models that can generalize to multiple tasks while being robust to out-of-distribution examples.
Outcome: The proposed training strategies enable models to learn difficult tasks while mixing in prior tasks, denoted as mixed curriculum.
CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP (2021.emnlp-main)

Copied to clipboard

Challenge: We study whether and how cross-task generalization ability can be acquired . we use CrossFit to standardize seen/unseen task partitions and evaluation protocols .
Approach: They propose a problem setup for studying cross-task generalization ability which standardizes seen/unseen task partitions and data access during different learning stages.
Outcome: The proposed model can be used to build few-shot learners across diverse tasks.
Large-scale Lifelong Learning of In-context Instructions and How to Tackle It (2023.acl-long)

Copied to clipboard

Challenge: In-context instruction learning is a method to improve the target PLM’s instance- and task-level generalization performance as it observes more tasks.
Approach: They propose to fine-tune a Pre-trained Language Model (PLM) on a set of tasks with in-context instructions and to extend this property to a scenario in which tasks are fed to the target PLM in a sequential manner.
Outcome: The proposed method achieves noticeable improvements in both types of generalization, nearly reaching the upper bound performance obtained through joint training.
Cross-Task Generalization via Natural Language Crowdsourcing Instructions (2022.acl-long)

Copied to clipboard

Challenge: Despite the success of supervised learning, models often struggle with generalization across tasks.
Approach: They propose to use crowdsourcing instructions to build a model that learns a new task by understanding the human-readable instructions that define it.
Outcome: The proposed model can learn from seen tasks and generalize to unseen tasks given its natural crowdsourcing instructions.
A Learnable Skill Combination Strategy for Multi-task Learning in Natural Language Understanding (2026.findings-acl)

Copied to clipboard

Challenge: a novel multi-task learning framework for domain-specific natural language understanding tasks addresses these limitations by combing multiple tasks into a single framework.
Approach: They propose a multi-task learning framework that decomposes the language model into modular skill components and employs a dynamic, learnable skill-combination mechanism to adaptively handle diverse tasks.
Outcome: The proposed framework surpasses conventional multi-task learning approaches in performance.

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