A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
Filters
Incorporating Connections Beyond Knowledge Embeddings: A Plug-and-Play Module to Enhance Commonsense Reasoning in Machine Reading Comprehension
[article]
2021
arXiv
pre-print
In this paper, we propose a Plug-and-play module to IncorporatE Connection information for commonsEnse Reasoning (PIECER). ...
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. ...
In this paper, we propose a Plug-and-play module to IncorporatE Connection information for commonsEnse Reasoning (PIECER). ...
arXiv:2103.14443v1
fatcat:cnmfvwdfe5e4pb5hgwldjrn3dq
A Survey of Knowledge-Enhanced Text Generation
[article]
2022
arXiv
pre-print
In this survey, we present a comprehensive review of the research on knowledge enhanced text generation over the past five years. ...
To address this issue, researchers have considered incorporating various forms of knowledge beyond the input text into the generation models. ...
Why a Survey of Knowledge-enhanced Text Generation? Incorporating knowledge in NLG beyond input text is seen as a promising direction in both academia and industry. ...
arXiv:2010.04389v3
fatcat:vzdtlz4j65g2va7gwkbmzyxkhq
A Roadmap for Big Model
[article]
2022
arXiv
pre-print
, Commonsense Reasoning, Reliability&Security, Governance, Evaluation, Machine Translation, Text Generation, Dialogue and Protein Research. ...
In each topic, we summarize clearly the current studies and propose some future research directions. At the end of this paper, we conclude the further development of BMs in a more general view. ...
In the rest, we mainly discuss machine reading comprehension and open domain question answering. Machine Reading Comprehension. ...
arXiv:2203.14101v4
fatcat:rdikzudoezak5b36cf6hhne5u4
A Survey of Knowledge Enhanced Pre-trained Models
[article]
2022
arXiv
pre-print
In this survey, we provide a comprehensive overview of KEPTMs in NLP and CV. We first introduce the progress of pre-trained models and knowledge representation learning. ...
Pre-trained models with knowledge injection, which we call knowledge enhanced pre-trained models (KEPTMs), possess deep understanding and logical reasoning and introduce interpretability. ...
Beyond that, they also provide comprehensive relational information [20] , [21] and/or explicit rules [22] for models to enhance the reasoning of pre-trained language models. ...
arXiv:2110.00269v3
fatcat:b2g3ezuplvftfp7zlehvogd44m
Pretrained Language Models for Text Generation: A Survey
[article]
2022
arXiv
pre-print
Text Generation aims to produce plausible and readable text in a human language from input data. ...
This comprehensive survey is intended to help researchers interested in text generation problems to learn the core concepts, the main techniques and the latest developments in this area based on PLMs. ...
[66] and Mao et al. [134] utilized commonsense knowledge base to fine-tune PLMs to generate reasonable stories. ...
arXiv:2201.05273v4
fatcat:pnffabspsnbhvo44gbaorhxc3a
SceneMaker: Intelligent Multimodal Visualisation of Natural Language Scripts
[chapter]
2010
Lecture Notes in Computer Science
SceneMaker's architecture with a language and text analysis module, a reasoning and decision making module based on cognitive, emotional information and a multimedia module for multimodal visualisation ...
The main objective of this work is to demonstrate how a scene and actor behaviour changes, when emotional states are taken into account, e.g. walking down a street in a happy versus a sad state. ...
The knowledge bases in CONFUCIUS will be extended by ConceptNet Singh, 2004) and Open Mind Common Sense (OMCS, 2009) for practical commonsense reasoning about context and Opinmind (2008) to analyse ...
doi:10.1007/978-3-642-17080-5_17
fatcat:w23elmcseja3lfycqehk5awdju
A 20-Year Community Roadmap for Artificial Intelligence Research in the US
[article]
2019
arXiv
pre-print
Future AI systems will rightfully be expected to reason effectively about the world in which they (and people) operate, handling complex tasks and responsibilities effectively and ethically, engaging in ...
The deployment of AI systems has not only created a trillion-dollar industry that is projected to quadruple in three years, but has also exposed the need to make AI systems fair, explainable, trustworthy ...
In order to do this, AI systems will have to incorporate complex ethical and commonsense reasoning capabilities that are needed to reliably and flexibly exhibit ethical behavior in a wide variety of interaction ...
arXiv:1908.02624v1
fatcat:jza6i2tzufgeracsou77qukbu4
Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
2021
The Journal of Artificial Intelligence Research
This success can be partly attributed to the advancements made in the sub-fields of AI such as machine learning, computer vision, and natural language processing. ...
Much of the growth in these fields has been made possible with deep learning, a sub-area of machine learning that uses artificial neural networks. ...
We extend our special thanks to Matthew Kuhn and Stephanie Lund for painstakingly proofing the whole manuscript. ...
doi:10.1613/jair.1.11688
fatcat:kvfdrg3bwrh35fns4z67adqp6i
Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
[article]
2020
arXiv
pre-print
This success can be partly attributed to the advancements made in the sub-fields of AI such as Machine Learning (ML), Computer Vision (CV), and Natural Language Processing (NLP). ...
The largest of the growths in these fields has been made possible with deep learning, a sub-area of machine learning, which uses the principles of artificial neural networks. ...
We extend our special thanks to Matthew Kuhn and Stephanie Lund for painstakingly proofing the whole manuscript. ...
arXiv:1907.09358v2
fatcat:4fyf6kscy5dfbewll3zs7yzsuq
World Knowledge Representation
[chapter]
2020
Representation Learning for Natural Language Processing
With the well-structured united knowledge representation, KGs are widely used in a variety of applications to enhance their system performance. ...
World knowledge representation aims to represent entities and relations in the knowledge graph in low-dimensional semantic space, which have been widely used in large knowledge-driven tasks. ...
KALM Pre-trained language models can do many tasks without supervised training data, like reading comprehension, summarization, and translation [60] . ...
doi:10.1007/978-981-15-5573-2_7
fatcat:nzn3gdsjozh4jfzqu6ux345uci
Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey
[article]
2022
arXiv
pre-print
The reasons for this are manifold and range from time and cost constraints to ethical considerations. ...
The existence of representative datasets is a prerequisite of many successful artificial intelligence and machine learning models. ...
A neural-symbolic reasoning engine could employ world knowledge or common sense knowledge to make sense of the scenery of a perception module or a combination of such modules. ...
arXiv:2205.04712v1
fatcat:u2bgxr2ctnfdjcdbruzrtjwot4
The Roles and Modes of Human Interactions with Automated Machine Learning Systems
[article]
2022
arXiv
pre-print
This discussion necessarily reviews projected developmental pathways for AutoML, such as the incorporation of reasoning, although the focus remains on how and why HCI may occur in such a framework rather ...
As automated machine learning (AutoML) systems continue to progress in both sophistication and performance, it becomes important to understand the 'how' and 'why' of human-computer interaction (HCI) within ...
To anchor such a scenario, modern theories for incorporating 'reasoning' in ML systems are surveyed and debated. ...
arXiv:2205.04139v1
fatcat:kfo3oybsjvfs5gjyt2j3dbaali
Advances and challenges in conversational recommender systems: A survey
2021
AI Open
We hope this survey can help to identify and address challenges in CRSs and inspire future research. ...
A B S T R A C T Recommender systems exploit interaction history to estimate user preference, having been heavily used in a wide range of industry applications. ...
Acknowledgments This work is supported by the National Natural Science Foundation of China (61972372, U19A2079) and the National Key Research and Development Program of China (2020YFB1406703, 2020AAA0106000 ...
doi:10.1016/j.aiopen.2021.06.002
fatcat:4r26fmsuvjcyla5wycb2ax62ha
The cognitive functions of language
2002
Behavioral and Brain Sciences
The overall goal of the paper is to review a wide variety of accounts of the cognitive function of natural language, integrating a number of different kinds of evidence and theoretical consideration in ...
This paper explores a variety of different versions of the thesis that natural language is involved in human thinking. ...
role to play in normal human cognition (in thinking and reasoning). ...
doi:10.1017/s0140525x02000122
fatcat:c7gskqw2qjb5bg53j7pzzmpyay
Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases
[article]
2021
arXiv
pre-print
Equipping machines with comprehensive knowledge of the world's entities and their relationships has been a long-standing goal of AI. ...
This machine knowledge can be harnessed to semantically interpret textual phrases in news, social media and web tables, and contributes to question answering, natural language processing and data analytics ...
It is a great pleasure and honor to have such wonderful colleagues in our research community. ...
arXiv:2009.11564v2
fatcat:vh2lqfmhhbcwpf6dcsej3hhvgy
« Previous
Showing results 1 — 15 out of 132 results