Browse SoTA > Reasoning > Common Sense Reasoning

Common Sense Reasoning

63 papers with code · Reasoning

Common sense reasoning tasks are intended to require the model to go beyond pattern recognition. Instead, the model should use "common sense" or world knowledge to make inferences.

Benchmarks

Greatest papers with code

A Simple Method for Commonsense Reasoning

7 Jun 2018tensorflow/models

Commonsense reasoning is a long-standing challenge for deep learning.

COMMON SENSE REASONING

Language Models are Unsupervised Multitask Learners

Preprint 2019 huggingface/transformers

Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.

 Ranked #1 on Language Modelling on enwik8 (using extra training data)

COMMON SENSE REASONING DATA-TO-TEXT GENERATION DOCUMENT SUMMARIZATION LANGUAGE MODELLING MACHINE TRANSLATION QUESTION ANSWERING READING COMPREHENSION

DKN: Deep Knowledge-Aware Network for News Recommendation

25 Jan 2018microsoft/recommenders

To solve the above problems, in this paper, we propose a deep knowledge-aware network (DKN) that incorporates knowledge graph representation into news recommendation.

CLICK-THROUGH RATE PREDICTION COMMON SENSE REASONING RECOMMENDATION SYSTEMS

A Neural Conversational Model

19 Jun 2015farizrahman4u/seq2seq

We find that this straightforward model can generate simple conversations given a large conversational training dataset.

COMMON SENSE REASONING NATURAL LANGUAGE UNDERSTANDING

Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models

ACL 2020 google-research/language

Recent models for unsupervised representation learning of text have employed a number of techniques to improve contextual word representations but have put little focus on discourse-level representations.

COMMON SENSE REASONING NATURAL LANGUAGE INFERENCE READING COMPREHENSION UNSUPERVISED REPRESENTATION LEARNING

Temporal Relational Reasoning in Videos

ECCV 2018 metalbubble/TRN-pytorch

Temporal relational reasoning, the ability to link meaningful transformations of objects or entities over time, is a fundamental property of intelligent species.

ACTION CLASSIFICATION ACTION RECOGNITION COMMON SENSE REASONING HUMAN-OBJECT INTERACTION DETECTION RELATIONAL REASONING

KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning

IJCNLP 2019 INK-USC/KagNet

Commonsense reasoning aims to empower machines with the human ability to make presumptions about ordinary situations in our daily life.

Ranked #3 on Common Sense Reasoning on CommonsenseQA (using extra training data)

COMMON SENSE REASONING KNOWLEDGE BASE QUESTION ANSWERING KNOWLEDGE GRAPHS NATURAL LANGUAGE INFERENCE