paper-with-me

Papers

Extracting Commonsense Properties from Embeddings with Limited Human Guidance

2018-07-01 · ACL 2018 7 · Yiben Yang, Larry Birnbaum, Ji-Ping Wang, Doug Downey

Intelligent systems require common sense, but automatically extracting this knowledge from text can be difficult. We propose and assess methods for extracting one type of commonsense knowledge, object-property comparisons, from pre-trained embeddings. In experiments, we show that our approach exceeds the accuracy of previous work but requires substantially less hand-annotated knowledge. Further, we show that an active learning approach that synthesizes common-sense queries can boost accuracy.

📄 PDF Abstract BibTeX

Code (1)

yangyiben/PCE 공식 구현 pytorch

Tasks

Active LearningCommon Sense ReasoningZero-Shot Learning

Similar Papers 제목 키워드 기반

Modelling Commonsense Commonalities with Multi-Facet Concept Embeddings

2024-03-25 · Hanane Kteich, Na Li, Usashi Chatterjee, Zied Bouraoui 외

Concept embeddings offer a practical and efficient mechanism for injecting commonsense knowledge into downstream tasks. Their core purpose is often not to predict the commonsense properties of concepts themselves, but ra…

Entity Typing

Incorporating Connections Beyond Knowledge Embeddings: A Plug-and-Play Module to Enhance Commonsense Reasoning in Machine Reading Comprehension

2021-03-26 · Damai Dai, Hua Zheng, Zhifang Sui, Baobao Chang

Conventional Machine Reading Comprehension (MRC) has been well-addressed by pattern matching, but the ability of commonsense reasoning remains a gap between humans and machines. Previous methods tackle this problem by en…

Knowledge Graph EmbeddingsKnowledge GraphsMachine Reading ComprehensionReading Comprehension

Commonsense Knowledge Transfer for Pre-trained Language Models

2023-06-04 · Wangchunshu Zhou, Ronan Le Bras, Yejin Choi

Despite serving as the foundation models for a wide range of NLP benchmarks, pre-trained language models have shown limited capabilities of acquiring implicit commonsense knowledge from self-supervision alone, compared t…

Language ModelingLanguage ModellingRelation PredictionTransfer Learning

Commonsense Knowledge Transfer for Pre-trained Language Models

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Despite serving as the foundation models for a wide range of NLP benchmarks, pre-trained language models have shown limited capabilities of acquiring implicit commonsense knowledge from self-supervision alone, compared t…

Language ModelingLanguage ModellingRelation PredictionTransfer Learning

Generating Commonsense Explanation by Extracting Bridge Concepts from Reasoning Paths

2020-09-24 · Asian Chapter of the Association for Computational Linguistics 2020 · Haozhe Ji, Pei Ke, Shaohan Huang, Furu Wei 외

Commonsense explanation generation aims to empower the machine's sense-making capability by generating plausible explanations to statements against commonsense. While this task is easy to human, the machine still struggl…

Explanation Generation