# Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start

arXiv: https://arxiv.org/abs/2010.02584 · HTML: https://mlsanity.com/paper/2010.02584/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2020.

## Built on by (most cited first, 30 of 44)

- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks](https://mlsanity.com/paper/2106.04489/) (2021)
- [UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models](https://mlsanity.com/paper/2201.05966/) (2022)
- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP](https://mlsanity.com/paper/2104.08835/) (2021)
- [Entailment as Few-Shot Learner](https://mlsanity.com/paper/2104.14690/) (2021)
- [Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2108.13161/) (2021)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.03659/) (2021)
- [Improving In-Context Few-Shot Learning via Self-Supervised Training](https://mlsanity.com/paper/2205.01703/) (2022)
- [Discrete and Soft Prompting for Multilingual Models](https://mlsanity.com/paper/2109.03630/) (2021)
- [Can NLI Models Verify QA Systems' Predictions?](https://mlsanity.com/paper/2104.08731/) (2021)
- [Paradigm Shift in Natural Language Processing](https://mlsanity.com/paper/2109.12575/) (2021)
- [Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks](https://mlsanity.com/paper/2309.13256/) (2023)
- [Summarization as Indirect Supervision for Relation Extraction](https://mlsanity.com/paper/2205.09837/) (2022)
- [Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System](https://mlsanity.com/paper/2104.11882/) (2021)
- [Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning](https://mlsanity.com/paper/2205.01376/) (2022)
- [Ontology-enhanced Prompt-tuning for Few-shot Learning](https://mlsanity.com/paper/2201.11332/) (2022)
- [Building Efficient Universal Classifiers with Natural Language Inference](https://mlsanity.com/paper/2312.17543/) (2023)
- [Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference](https://mlsanity.com/paper/2202.06167/) (2022)
- [Few-Shot Learning with Siamese Networks and Label Tuning](https://mlsanity.com/paper/2203.14655/) (2022)
- [PART: Pre-trained Authorship Representation Transformer](https://mlsanity.com/paper/2209.15373/) (2022)
- [Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?](https://mlsanity.com/paper/2212.10784/) (2022)
- [Active Few-Shot Learning with FASL](https://mlsanity.com/paper/2204.09347/) (2022)
- [Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP](https://mlsanity.com/paper/2111.01322/) (2021)
- [CLUES: Few-Shot Learning Evaluation in Natural Language Understanding](https://mlsanity.com/paper/2111.02570/) (2021)
- [LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Framework](https://mlsanity.com/paper/2112.07522/) (2021)
- [Few-shot Multimodal Sentiment Analysis based on Multimodal Probabilistic Fusion Prompts](https://mlsanity.com/paper/2211.06607/) (2022)
- [What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories](https://mlsanity.com/paper/2302.03353/) (2023)
- [Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding](https://mlsanity.com/paper/2306.11066/) (2023)

## Abstract (arXiv)

A standard way to address different NLP problems is by first constructing a problem-specific dataset, then building a model to fit this dataset. To build the ultimate artificial intelligence, we desire a single machine that can handle diverse new problems, for which task-specific annotations are limited. We bring up textual entailment as a unified solver for such NLP problems. However, current research of textual entailment has not spilled much ink on the following questions: (i) How well does a pretrained textual entailment system generalize across domains with only a handful of domain-specific examples? and (ii) When is it worth transforming an NLP task into textual entailment? We argue that the transforming is unnecessary if we can obtain rich annotations for this task. Textual entailment really matters particularly when the target NLP task has insufficient annotations. Universal NLP can be probably achieved through different routines. In this work, we introduce Universal Few-shot textual Entailment (UFO-Entail). We demonstrate that this framework enables a pretrained entailment model to work well on new entailment domains in a few-shot setting, and show its effectiveness as a unified solver for several downstream NLP tasks such as question answering and coreference resolution when the end-task annotations are limited. Code: https://github.com/salesforce/UniversalFewShotNLP