Two-Step Classification using Recasted Data for Low Resource Settings

Challenge:	Existing studies on NLP models focus on high resource languages like English, but there are only two datasets for Hindi.
Approach:	They propose a novel two-step classification method which uses textual-entailment predictions for classification task.
Outcome:	The proposed method improves classification performance by using a joint-objective for classification and textual entailment.

Similar Papers

Overview

Challenge

Approach

Outcome

Deep Learning for Natural Language Inference (N19-5)

Copied to clipboard

Samuel Bowman, Xiaodan Zhu

Reasoning

Challenge:	This tutorial discusses cutting-edge research on NLI, including recent advance on dataset development, cutting- edge deep learning models, and highlights from recent research on using NLI to understand capabilities and limits of deep learning for language understanding and reasoning.
Approach:	This tutorial discusses cutting-edge research on NLI, including recent advance on dataset development and cutting- edge deep learning models.
Outcome:	This tutorial discusses cutting-edge research on NLI, including recent advance on dataset development, cutting- edge deep learning models, and highlights from recent research on using NLI to understand capabilities and limits of deep learning model for language understanding and reasoning.

Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference (2022.findings-emnlp)

Copied to clipboard

Mobashir Sadat, Cornelia Caragea

Responsible & Trustworthy NLP

Challenge:	Semi-supervised learning (SSL) is a popular technique for reducing the reliance on human annotations for NLI tasks.
Approach:	They propose a way to incorporate unlabeled data into semi-supervised learning (SSL) using a conditional language model, they propose to generate hypotheses for unlabed sentences .
Outcome:	The proposed framework significantly improves the performance of four NLI datasets in low-resource settings.

MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing (2025.findings-naacl)

Copied to clipboard

Vlad Andrei Negru, Robert Vacareanu, Camelia Lemnaru, Mihai Surdeanu, Rodica Potolea

Textual Inference

Challenge:	Existing models fail to capture important semantic features of logic such as monotonicity and negation.
Approach:	They propose a modular step-by-step approach to natural language inference . they use a language model to generate edits to incrementally transform the premise into the hypothesis .
Outcome:	The proposed method outperforms baseline models in realistic cross-domain settings with improvements up to 12.6% (relative).

DocNLI: A Large-scale Dataset for Document-level Natural Language Inference (2021.findings-acl)

Copied to clipboard

Wenpeng Yin, Dragomir Radev, Caiming Xiong

Language Models

Challenge:	Existing studies focus on sentence-level inference, which limits its application in downstream NLP problems.
Approach:	They propose to construct a large-scale dataset for document-level NLI that can be used to study NLP problems.
Outcome:	The proposed model performs well on popular sentence-level benchmarks and generalizes well to out-of-domain NLP tasks that rely on inference at document granularity.

Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation (D18-1)

Copied to clipboard

Adam Poliak, Aparajita Haldar, Rachel Rudinger, J. Edward Hu, Ellie Pavlick, Aaron Steven White, Benjamin Van Durme

Representation Learning

Challenge:	a plethora of new natural language inference datasets has been created in recent years . however, these datasets do not provide clear insight into what type of reasoning or inference a model may be performing.
Approach:	They propose to recast 13 existing natural language inference datasets into a common structure.
Outcome:	The proposed datasets provide insight into how well a sentence representation captures distinct types of reasoning.

Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters (2022.findings-emnlp)

Copied to clipboard

Tal Schuster, Sihao Chen, Senaka Buthpitiya, Alex Fabrikant, Donald Metzler

Information Extraction & Text Mining

Challenge:	Recent advances in modeling and datasets demonstrate promising performance for NLI.
Approach:	They explore the direct zero-shot applicability of NLI models to real applications . they analyze the robustness of models to longer and out-of-domain inputs .
Outcome:	The proposed models are robust to longer and out-of-domain inputs and can perform on full documents.

Adversarial NLI: A New Benchmark for Natural Language Understanding (2020.acl-main)

Copied to clipboard

Yixin Nie, Adina Williams, Emily Dinan, Mohit Bansal, Jason Weston, Douwe Kiela

Robustness in NLP

Challenge:	a new large-scale NLI benchmark dataset is presented to test models on a variety of popular NLIs.
Approach:	They propose a large-scale NLI benchmark dataset that is iteratively compared with a human-and-model-in-the-loop procedure.
Outcome:	The proposed method can be applied in a never-ending learning scenario, becoming a moving target for NLU, rather than a static benchmark that will quickly saturate.

Towards Robustifying NLI Models Against Lexical Dataset Biases (2020.acl-main)

Copied to clipboard

Xiang Zhou, Mohit Bansal

Responsible & Trustworthy NLP

Challenge:	Recent studies show that deep learning models exploit dataset biases without deep understanding of the language semantics.
Approach:	They propose two methods to debiase models against lexical dataset biases . they use contradiction-word bias and word-overlapping bias as examples .
Outcome:	The proposed method removes label bias at embedding level, while the other uses a bag-of-words sub-model to capture features likely to exploit the bias.

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios (2021.naacl-main)

Copied to clipboard

Michael A. Hedderich, Lukas Lange, Heike Adel, Jannik Strötgen, Dietrich Klakow

Responsible & Trustworthy NLP

Challenge:	a growing body of work is focused on improving performance in low-resource settings . a goal of this study is to explain how these methods differ in their requirements .
Approach:	They propose to analyze data-lean scenarios across different dimensions of data availability to understand which approaches are effective in a specific low-resource setting.
Outcome:	The proposed methods enable learning when training data is sparse.

A Deep Generative Approach to Native Language Identification (2020.coling-main)

Copied to clipboard

Ehsan Lotfi, Ilia Markov, Walter Daelemans

Information Retrieval

Challenge:	Native language identification (NLI) is a multi-class classification task involving multiple features that capture the systematic fingerprints of the first language in the second language writing.
Approach:	They propose a deep generative language modelling approach to NLI that fine-tunes a GPT-2 model separately on texts written by the authors with the same L1 and assigns n-grams to an unseen text.
Outcome:	The proposed method outperforms traditional machine learning approaches and currently achieves the best results on the benchmark NLI datasets.