Annotation Artifacts in Natural Language Inference Data (N18-2)

Copied to clipboard

Challenge: Large-scale datasets for natural language inference are created by crowdsourcing annotations . authors show that success of natural language models to date has been overestimated .
Approach: They propose a method for crowdsourcing annotations to generate 3 new sentences based on a sentence (premise) they show that a simple text categorization model can correctly classify the hypothesis alone in about 67% of SNLI and 53% of MultiNLI .
Outcome: The proposed model can classify the hypothesis alone in 67% of SNLI and 53% of MultiNLI datasets.

Similar Papers

Biases in Large Language Model-Elicited Text: A Case Study in Natural Language Inference (2025.coling-main)

Copied to clipboard

Challenge: Creating NLP datasets with Large Language Models (LLMs) is an attractive alternative to relying on crowd-source workers.
Approach: They recreate a portion of the Stanford Natural Language Inference corpus using GPT-4, Llama-2 70b for Chat, and Mistral 7b Instruct.
Outcome: The proposed model can be used to generate NLP datasets with stereotypical biases and annotation artifacts.
MedNLI Is Not Immune: Natural Language Inference Artifacts in the Clinical Domain (2021.acl-short)

Copied to clipboard

Challenge: a large number of crowdworker-constructed datasets have been used to conduct natural language inference (NLI) on unstructured, domainspecific texts such as patient notes, pathology reports, and scientific papers.
Approach: They investigate whether MedNLI contains lexical and syntactic annotation artifacts associated with annotation process that allow hypothesis-only classifiers to achieve better-than-random performance.
Outcome: The proposed model outperforms a majority-class baseline model on a physician-annotated dataset with premises extracted from clinical notes.
Evaluating BERT for natural language inference: A case study on the CommitmentBank (D19-1)

Copied to clipboard

Challenge: Natural language inference datasets can identify premise-hypothesis relationship without observing premise . recasting of the CommitmentBank for NLI creates hypotheses that stand in entailment/contradiction/neutral relationship with premise.
Approach: They propose to recast the CommitmentBank for NLI to stand in certain relationships with the premise . hypotheses are complements of clause-embedding verbs in each premise, rethinking the CommittedBank .
Outcome: The proposed model performs well on the CommitmentBank with 85% F1 . however, the model does not capture the full complexity of pragmatic reasoning, authors say .
Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets (D19-1)

Copied to clipboard

Challenge: Having only a few workers generate the majority of dataset examples raises concerns about data diversity .
Approach: They perform a series of experiments to investigate annotator biases in recent NLU datasets . they find that models are able to recognize the most productive annotators .
Outcome: The results show that models can recognize the most productive annotators and do not generalize well to examples from annotator that did not contribute to the training set.
Don’t Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference (P19-1)

Copied to clipboard

Challenge: Natural Language Inference (NLI) datasets often contain hypothesis-only biases . authors propose probabilistic methods to build models that are more robust to such artifacts - a new study shows .
Approach: They propose probabilistic methods to build models that are more robust to biases . authors train on datasets containing biase .
Outcome: The proposed methods can make NLI models more robust to dataset-specific artifacts . the methods transfer better than a baseline architecture in 9 out of 12 NLI datasets compared with baseline architectures based on the proposed methods .
DocNLI: A Large-scale Dataset for Document-level Natural Language Inference (2021.findings-acl)

Copied to clipboard

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.
New Protocols and Negative Results for Textual Entailment Data Collection (2020.emnlp-main)

Copied to clipboard

Challenge: Natural language inference data has proven useful in benchmarking and as pretraining data for tasks requiring language understanding.
Approach: They propose four alternative protocols to improve annotation quality and diversity . they use 8.5k-example training sets to compare different protocols .
Outcome: The proposed protocols improve the ease of training and quality of the examples.
Asking Crowdworkers to Write Entailment Examples: The Best of Bad Options (2020.aacl-main)

Copied to clipboard

Challenge: Large-scale natural language inference datasets are available for non-expert crowdsourcing.
Approach: They propose to use crowdworker writing to create candidate pairs for annotation . they find crowdworkers writing is the best known protocol for entailment data .
Outcome: The proposed protocol outperforms the baseline protocol in evaluations of generalization and transfer learning.
Baselines and Test Data for Cross-Lingual Inference (L18-1)

Copied to clipboard

Challenge: Recent research on textual entailment is limited to English, but it is expanding to other languages.
Approach: They propose to extend the research in SNLI-style natural language inference toward multilingual evaluation by using cross-lingual word embeddings and machine translation.
Outcome: The proposed system scores an average accuracy of just over 75%, but it is not perfect.
SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference (D18-1)

Copied to clipboard

Challenge: a new dataset presents a task of grounded commonsense inference, unifying natural language inference and commonsensical reasoning.
Approach: They propose a procedure that constructs a de-biased dataset by iteratively training stylistic classifiers and using them to filter the data.
Outcome: The proposed procedure oversamples a de-biased dataset using state-of-the-art language models . human models struggle on the proposed procedure, indicating significant opportunities for future research.

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