paper-with-me

홈 › Papers

MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity

2019-10-19 · SCiL 2020 1 · Hai Hu, Qi Chen, Kyle Richardson, Atreyee Mukherjee, Lawrence S. Moss, Sandra Kuebler

We present a new logic-based inference engine for natural language inference (NLI) called MonaLog, which is based on natural logic and the monotonicity calculus. In contrast to existing logic-based approaches, our system is intentionally designed to be as lightweight as possible, and operates using a small set of well-known (surface-level) monotonicity facts about quantifiers, lexical items and tokenlevel polarity information. Despite its simplicity, we find our approach to be competitive with other logic-based NLI models on the SICK benchmark. We also use MonaLog in combination with the current state-of-the-art model BERT in a variety of settings, including for compositional data augmentation. We show that MonaLog is capable of generating large amounts of high-quality training data for BERT, improving its accuracy on SICK.

📄 PDF Abstract BibTeX arXiv:1910.08772

Code (1)

huhailinguist/ccg2mono 공식 구현

Tasks

Data AugmentationNatural Language Inference

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
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 &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Lightweight Language-driven Grasp Detection using Conditional Consistency Model

2024-07-25 · Nghia Nguyen, Minh Nhat Vu, Baoru Huang, An Vuong 외

Language-driven grasp detection is a fundamental yet challenging task in robotics with various industrial applications. In this work, we present a new approach for language-driven grasp detection that leverages the conce…

Denoising

Bonafide at LegalLens 2024 Shared Task: Using Lightweight DeBERTa Based Encoder For Legal Violation Detection and Resolution

2024-10-30 · Shikha Bordia

In this work, we present two systems -- Named Entity Resolution (NER) and Natural Language Inference (NLI) -- for detecting legal violations within unstructured textual data and for associating these violations with pote…

Entity ResolutionNatural Language InferenceNER

FMI_SU_Yotkova_Kastreva at SemEval-2026 Task 13: Lightweight Detection of LLM-Generated Code via Stylometric Signals

2026-05-05 · Elitsa Yotkova, Violeta Kastreva, Dimitar Dimitrov, Ivan Koychev 외 arxiv

SemEval-2026 Task 13 investigates machine-generated code detection across multiple programming languages and application scenarios, asking participating systems to generalize to unseen languages and domains. This paper d…

Binary Classification

LightFusionRec: Lightweight Transformers-Based Cross-Domain Recommendation Model

2024-10-21 · Vansh Kharidia, Dhruvi Paprunia, Prashasti Kanikar

This paper presents LightFusionRec, a novel lightweight cross-domain recommendation system that integrates DistilBERT for textual feature extraction and FastText for genre embedding. Important issues in recommendation sy…

Computational EfficiencymodelRecommendation Systems

InferLite: Simple Universal Sentence Representations from Natural Language Inference Data

2018-10-01 · EMNLP 2018 10 · Jamie Kiros, William Chan

Natural language inference has been shown to be an effective supervised task for learning generic sentence embeddings. In order to better understand the components that lead to effective representations, we propose a lig…

GPUNatural Language InferencePositionSentence+2