Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding

2022-10-26 · Md Mosharaf Hossain, Eduardo Blanco

Negation poses a challenge in many natural language understanding tasks. Inspired by the fact that understanding a negated statement often requires humans to infer affirmative interpretations, in this paper we show that doing so benefits models for three natural language understanding tasks. We present an automated procedure to collect pairs of sentences with negation and their affirmative interpretations, resulting in over 150,000 pairs. Experimental results show that leveraging these pairs helps (a) T5 generate affirmative interpretations from negations in a previous benchmark, and (b) a RoBERTa-based classifier solve the task of natural language inference. We also leverage our pairs to build a plug-and-play neural generator that given a negated statement generates an affirmative interpretation. Then, we incorporate the pretrained generator into a RoBERTa-based classifier for sentiment analysis and show that doing so improves the results. Crucially, our proposal does not require any manual effort.

📄 PDF Abstract BibTeX arXiv:2210.14486

Code (1)

mosharafhossain/large-afin-and-nlu 공식 구현 pytorch

Tasks

Natural Language Inference Natural Language UnderstandingNegationSentiment Analysis

Methods 이 논문이 사용한 방법론

Gated Linear Unit A Gated Linear Unit, or GLU computes: $$ \mathrm{GLU}(a, b) = a \otimes \sigma(b) $$ It is used in natural language processing architectures, for example the Gated CNN,…

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…

Multi-Head Attention 설명 없음

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Residual Connection 설명 없음

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Inverse Square Root Schedule Inverse Square Root is a learning rate schedule 1 / $\sqrt{\max\left(n, k\right)}$ where $n$ is the current training iteration and $k$ is the number of warm-up steps. This…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Paraphrasing in Affirmative Terms Improves Negation Understanding

2024-06-11 · MohammadHossein Rezaei, Eduardo Blanco

Negation is a common linguistic phenomenon. Yet language models face challenges with negation in many natural language understanding tasks such as question answering and natural language inference. In this paper, we expe…

Natural Language Inference Natural Language Understanding Negation Question Answering

A Question-Answer Driven Approach to Reveal Affirmative Interpretations from Verbal Negations

2022-05-23 · Findings (NAACL) 2022 7 · Md Mosharaf Hossain, Luke Holman, Anusha Kakileti, Tiffany Iris Kao 외

This paper explores a question-answer driven approach to reveal affirmative interpretations from verbal negations (i.e., when a negation cue grammatically modifies a verb). We create a new corpus consisting of 4,472 verb…

Natural Language Inference Negation

Predicting the Focus of Negation: Model and Error Analysis

2020-07-01 · ACL 2020 6 · Md Mosharaf Hossain, Kathleen Hamilton, Alexis Palmer, Eduardo Blanco

The focus of a negation is the set of tokens intended to be negated, and a key component for revealing affirmative alternatives to negated utterances. In this paper, we experiment with neural networks to predict the focu…

Negation

SpaceVLM: Sub-Space Modeling of Negation in Vision-Language Models

2025-11-15 · Sepehr Kazemi Ranjbar, Kumail Alhamoud, Marzyeh Ghassemi arxiv

Vision-Language Models (VLMs) struggle with negation. Given a prompt like "retrieve (or generate) a street scene without pedestrians," they often fail to respect the "not." Existing methods address this limitation by fin…

Interpreting Negation in GPT-2: Layer- and Head-Level Causal Analysis

2026-03-12 · Abdullah Al Mofael, Lisa M. Kuhn, Ghassan Alkadi, Kuo-Pao Yang arxiv

Negation remains a persistent challenge for modern language models, often causing reversed meanings or factual errors. In this work, we conduct a causal analysis of how GPT-2 Small internally processes such linguistic tr…