Papers with Textual Inference

30 papers
Natural Language Inference with Mixed Effects (2020.starsem-1)

Copied to clipboard

Challenge: aggregating raw annotations to a single label is problematic due to disagreement among annotators.
Approach: They propose a generic method that allows one to skip the aggregation step and train on the raw annotations directly without subjecting the model to unwanted noise.
Outcome: The proposed method improves performance over models that do not incorporate such effects.
Compositional Semantics and Inference System for Temporal Order based on Japanese CCG (2022.acl-srw)

Copied to clipboard

Challenge: a system for temporal order in Japanese has not been developed for linguistic inference involving temporal expressions.
Approach: They propose a Japanese NLI system that considers temporal order in Japanese . they use axioms for temporal relations and automated theorem provers to perform inference involving temporal orders.
Outcome: The proposed system outperforms logic-based systems and current deep learning models on Japanese datasets.
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.
PerspectroScope: A Window to the World of Diverse Perspectives (P19-3)

Copied to clipboard

Challenge: PerspectroScope is a web-based system that lets users query a discussion-worthy natural language claim .
Approach: They propose a web-based system which lets users query a discussion-worthy natural language claim and extract and visualize various perspectives in support or against the claim.
Outcome: The proposed system lets users query a discussion-worthy natural language claim and extract and visualize various perspectives in support or against the claim.
Logical Inferences with Comparatives and Generalized Quantifiers (2020.acl-srw)

Copied to clipboard

Challenge: Comparative constructions pose a challenge in Natural Language Inference (NLI) Comparatives interact with quantifiers, numerals, and lexical antonyms, but a logical inference system for comparatives has not been developed for the task.
Approach: They propose a compositional semantics system that maps comparative constructions to semantic representations via combinatory categorial grammar parsers and integrates it with an automated theorem proving system.
Outcome: The proposed system outperforms previous logic-based systems and deep learning models on three NLI datasets.
PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are prone to factually inconsistent statements, known as hallucinations.
Approach: They propose to train a specialized model that detects inconsistencies over text prefixes to improve generation faithfulness by 5-14 F1 points.
Outcome: The proposed model outperforms baseline models by 5-14 F1 points in prefix-level entailment.
A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference (N18-1)

Copied to clipboard

Challenge: et al., 1996, show that many of the most actively studied problems in NLP depend in large part on natural language understanding (NLU).
Approach: They propose a dataset for machine learning that uses ten different genres of English to evaluate sentences for their meanings.
Outcome: The multi-genre natural language inference corpus is one of the largest available for natural language understanding.
Scoring Lexical Entailment with a Supervised Directional Similarity Network (P18-2)

Copied to clipboard

Challenge: Existing word embeddings that use supervision only improve the embeddable word embeds of words with annotated lexical relations.
Approach: They propose a supervised directional similarity network for learning task-specific transformation functions on top of general-purpose word embeddings.
Outcome: The proposed model outperforms existing models on the HyperLex dataset on a directional graded lexical entailment task by 25%.
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.
Structured Alignment Networks for Matching Sentences (D18-1)

Copied to clipboard

Challenge: Many tasks in natural language processing involve comparing two sentences to compute some notion of relevance, entailment, or similarity.
Approach: They propose a model of structured alignments between sentences to compare two sentences by matching their latent structures.
Outcome: The proposed model is differentiable and trained only on the matching objective.
Lessons from Natural Language Inference in the Clinical Domain (D18-1)

Copied to clipboard

Challenge: State of the art models with deep neural networks lack generalization capabilities in specialized domains where training data is limited.
Approach: They propose a dataset annotated by doctors performing a natural language inference task grounded in the medical history of patients.
Outcome: The proposed model outperforms existing models in the clinical domain by incorporating domain knowledge from external data and lexical sources.
Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference (P19-1)

Copied to clipboard

Challenge: Recent advances on abstractive summarization have led to fluent summaries, but factual errors in generated summary still severely limit their use in practice.
Approach: They evaluate summaries produced by state-of-the-art models via crowdsourcing and show that factual errors occur frequently.
Outcome: The proposed models can detect errors and reduce them by reranking alternative summaries.
Harry Potter and the Action Prediction Challenge from Natural Language (N19-1)

Copied to clipboard

Challenge: Using textual descriptions of scenes, we explore the challenge of action prediction from textual description.
Approach: They propose a testbed to approximate whether text inference can be used to predict upcoming actions from textual descriptions of scenes.
Outcome: The proposed model performs best for frequent actions and large scene descriptions, but logistic regression fails on infrequent actions.
A Simple Three-Step Approach for the Automatic Detection of Exaggerated Statements in Health Science News (2021.eacl-main)

Copied to clipboard

Challenge: Exaggerations in health news can have tremendous adverse effects on the lifestyle of the common masses who feed themselves mostly on such news instead of the source scientific publication.
Approach: They propose a three-step approach that extracts relation phrases from a scientific paper and then classifies the strength of the relationship phrase extracted.
Outcome: The proposed approach outperforms baseline models that compare state-of-the-art embedding of the statement pairs through a binary classifier or recast the problem as a textual entailment task.
Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance? (2021.eacl-main)

Copied to clipboard

Challenge: Neural models have established state-of-the-art performance on several NLP benchmarks, but little is understood about the mechanisms by which they operate.
Approach: They examine the probing paradigm through a set of controlled synthetic tasks and show that pretrained word embeddings play a considerable role in encoding these properties rather than the training task itself.
Outcome: The proposed model can encode linguistic properties above chance-level even when distributed in the data as random noise, reversing the interpretation of absolute claims on probing tasks.
SDOH-NLI: a Dataset for Inferring Social Determinants of Health from Clinical Notes (2023.findings-emnlp)

Copied to clipboard

Challenge: Social and behavioral determinants of health (SDOH) play a significant role in shaping health outcomes, and extracting these determinant from clinical notes is a first step to help healthcare providers systematically identify opportunities to provide appropriate care and address disparities.
Approach: They propose a dataset that extracts social and behavioral determinants from clinical notes and uses them to form a natural language inference task.
Outcome: The proposed dataset is based on publicly available notes and is more challenging than standard NLI benchmarks.
Evaluating Factuality in Generation with Dependency-level Entailment (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing text generation models produce text that is factually inconsistent with information in the input.
Approach: They propose a new formulation of entailment that decomposes it at the level of dependency arcs.
Outcome: The proposed model can identify factual errors better than sentence-level methods and question generation methods while localizing the erroneous parts of the generation.
ViNLI: A Vietnamese Corpus for Studies on Open-Domain Natural Language Inference (2022.coling-1)

Copied to clipboard

Challenge: a large-scale corpus is needed for studies on natural language inference (NLI) for Vietnamese, which can be considered a low-resource language.
Approach: They propose a corpus for evaluating Vietnamese natural language inference models . they use a human-annotated corpus extracted from more than 800 online news articles .
Outcome: The ViNLI corpus is created and evaluated with a strict process of quality control . the best system performance is still far from human performance (a 14.20% gap in accuracy).
MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing (2025.findings-naacl)

Copied to clipboard

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).
Does Putting a Linguist in the Loop Improve NLU Data Collection? (2021.findings-emnlp)

Copied to clipboard

Challenge: Many datasets for training and evaluating natural language understanding (NLU) models contain systematic artifacts that are identified only after data collection is complete.
Approach: They propose to have linguists identify artifacts and gaps in the data and communicate with non-expert crowdworkers to adjust task instructions and incentives.
Outcome: The proposed protocol does not increase accuracy on out-of-domain test sets, and adds a chatroom does not.
Conditional Natural Language Inference (2023.findings-emnlp)

Copied to clipboard

Challenge: False positive: widely-used feature-attribution explanation models are not suitable for finding conditions when sentences are long and are written independently.
Approach: They propose a task of conditional natural language inference to explain sentence pairs that provide contradictory (different) information for different conditions.
Outcome: The proposed model outperforms the full cross-encoder and other baselines in extracting conditions while maintaining comparable accuracy.
Posing Fair Generalization Tasks for Natural Language Inference (D19-1)

Copied to clipboard

Challenge: Existing evaluation methods for deep learning semantics rely on naturalistic corpora, but they often fail to support the kind of generalization we are asking for.
Approach: They define and motivate a formal notion of fairness for evaluations of deep learning models for semantics . they then apply it to natural language inference by constructing challenging but provably fair artificial datasets based on the results .
Outcome: The proposed evaluations show that standard neural models fail to generalize in the required ways and even these models do not solve the task perfectly.
Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic (2024.emnlp-main)

Copied to clipboard

Challenge: Recent language models allow structured reasoning with text, but lack of a clear protocol for discerning entailment causes noisy datasets and limited performance gains.
Approach: They propose a consistent approach to annotating decompositional entailment and evaluate its impact on LLM-based textual inference.
Outcome: The proposed approach has higher internal consistency than prior decompositional entailment datasets and significantly improves proof quality and accuracy.
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.
Word Attribute Prediction Enhanced by Lexical Entailment Tasks (2020.lrec-1)

Copied to clipboard

Challenge: a semantic attribute is associated with a designated dimension in attribute-based vector representations . semantic attributes are created by psychological experimental settings involving human annotators . a conceptual attribute of a concept dictates a specific semantic aspect of the concept .
Approach: They propose a two-stage neural network architecture that fine-tunes attribute representations by employing supervised entailment tasks.
Outcome: The proposed method improves performance of semantic/visual similarity/relatedness evaluation tasks.
An Analysis of Natural Language Inference Benchmarks through the Lens of Negation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks for natural language inference ignore negations and can make inferences that are difficult to make.
Approach: They propose a new benchmark for natural language inference in which negation plays a critical role.
Outcome: The proposed benchmarks show that negation plays a critical role in inference judgments.
Uncertain Natural Language Inference (2020.acl-main)

Copied to clipboard

Challenge: Existing categorical bin assignments for NLI are not effective for entailment inference.
Approach: They propose a refinement of Natural Language Inference that targets direct prediction of subjective probability assessments.
Outcome: The proposed model can be used in pre-training and correlates well with humans.
New Datasets for Automatic Detection of Textual Entailment and of Contradictions between Sentences in French (2024.lrec-main)

Copied to clipboard

Challenge: DACCORD is a dataset for automatic detection of contradictions between sentences . it is the first dataset exclusively dedicated to this task .
Approach: They introduce DACCORD, a dataset in French for automatic detection of contradictions between sentences.
Outcome: The proposed datasets are more challenging than existing datasets for the mainstream task in French.
Uncovering Agendas: A Novel French & English Dataset for Agenda Detection on Social Media (2024.lrec-main)

Copied to clipboard

Challenge: a social media analysis of online influence campaigns can reveal the sources of agenda setting . annotated data is limited or nonexistent, but there are methods to detect agenda control .
Approach: They propose a method for detecting instances of agenda control through social media . they use a modest corpus of tweets centered on the 2022 french presidential election .
Outcome: The proposed method overcomes the requirement for large annotated training dataset.
Entailed Between the Lines: Incorporating Implication into NLI (2025.acl-long)

Copied to clipboard

Challenge: True Emotions, social cues, insults, and a myriad of other messages are conveyed implicitly, often even more so than explicitly.
Approach: They propose a dataset to help LLMs understand implied entailment .
Outcome: The proposed dataset enables LLMs to understand implied entailment and can generalize this understanding across datasets and domains.

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