Filters








1,106 Hits in 5.8 sec

A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories [article]

Nasrin Mostafazadeh, Nathanael Chambers, Xiaodong He, Devi Parikh, Dhruv Batra, Lucy Vanderwende, Pushmeet Kohli, James Allen
2016 arXiv   pre-print
This paper attempts to address this problem with a new framework for evaluating story understanding and script learning: the 'Story Cloze Test'.  ...  We discuss these implications for script and story learning, and offer suggestions for deeper language understanding.  ...  We thank William de Beaumont and Choh Man Teng for their work on TRIPS parser. We thank Alyson Grealish for her great help in the quality control of our corpus.  ... 
arXiv:1604.01696v1 fatcat:v6xeepq5xnfozenq64gulgj2oy

A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories

Nasrin Mostafazadeh, Nathanael Chambers, Xiaodong He, Devi Parikh, Dhruv Batra, Lucy Vanderwende, Pushmeet Kohli, James Allen
2016 Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
This paper attempts to address this problem with a new framework for evaluating story understanding and script learning: the 'Story Cloze Test'.  ...  We discuss these implications for script and story learning, and offer suggestions for deeper language understanding.  ...  We thank William de Beaumont and Choh Man Teng for their work on TRIPS parser. We thank Alyson Grealish for her great help in the quality control of our corpus.  ... 
doi:10.18653/v1/n16-1098 dblp:conf/naacl/MostafazadehCHP16 fatcat:22jse6esnnhu3ewzonnpzebcp4

Story Cloze Evaluator: Vector Space Representation Evaluation by Predicting What Happens Next

Nasrin Mostafazadeh, Lucy Vanderwende, Wen-tau Yih, Pushmeet Kohli, James Allen
2016 Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP  
We propose a novel framework, Story Cloze Evaluator, for evaluating vector representations which goes beyond textual similarity and captures the notion of predicting what should happen next given a context  ...  new framework for further investment of the representation learning community.  ...  This work was supported in part by Grant W911NF-15-1-0542 with the US Defense Advanced Research Projects Agency (DARPA), the Army Research Office (ARO) and the Office of Naval Research (ONR).  ... 
doi:10.18653/v1/w16-2505 dblp:conf/repeval/MostafazadehVYK16 fatcat:c5yxr25jqfbq7i2wkfiwtz6kou

Commonsense Reasoning in a Deeper Way: By Discovering Relations between Predicates

Wenguan Huang, Xudong Luo
2017 Proceedings of the 9th International Conference on Agents and Artificial Intelligence  
Then we construct a set of knowledge by extending the predicate set of ConceptNet, and apply information extraction technique to capture them from corpus.  ...  Finally, to evaluate our framework, we conduct experiments against a part of the Winograd Schema Challenge, which, its author claimed, is an alternative of Turing Test.  ...  ACKNOWLEDGMENTS This research was partially supported by the Bairen Plan of Sun Yat-sen University, the Natural Science Foundation of Guangdong Province, China (No. 2016A030313231) and the National Fund  ... 
doi:10.5220/0006120504070414 dblp:conf/icaart/HuangL17 fatcat:nt6vqvgvzzgvtgpgkkmcineczi

Automatic Story Generation: Challenges and Attempts [article]

Amal Alabdulkarim, Siyan Li, Xiangyu Peng
2021 arXiv   pre-print
The scope of this survey paper is to explore the challenges in automatic story generation. We hope to contribute in the following ways: 1.  ...  Explore how previous research in story generation addressed those challenges. 2. Discuss future research directions and new technologies that may aid more advancements. 3.  ...  Commonsense serves as a deep understanding of language.  ... 
arXiv:2102.12634v1 fatcat:b67pi4zy5fc4dp4edidecwo54a

Resource-Lean Modeling of Coherence in Commonsense Stories

Niko Schenk, Christian Chiarcos
2017 Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics  
We present a resource-lean neural recognizer for modeling coherence in commonsense stories.  ...  We evaluate our approach in the Story Cloze Test 1 demonstrating an absolute improvement in accuracy of 4.7% over state-of-the-art implementations.  ...  Acknowledgments We want to thank Philip Schulz for constructive feedback regarding the neural network setup and the two anonymous reviewers for their very helpful remarks and insightful comments. 7 We  ... 
doi:10.18653/v1/w17-0910 dblp:conf/eacl/SchenkC17 fatcat:eejqmmdssncrnalzs4w5n4qsvu

ConceptNet — A Practical Commonsense Reasoning Tool-Kit

H Liu, P Singh
2004 BT technology journal  
The knowledge base is a semantic network presently consisting of over 1.6 million assertions of commonsense knowledge encompassing the spatial, physical, social, temporal, and psychological aspects of  ...  ConceptNet is a freely available commonsense knowledge base and natural-language-processing tool-kit which supports many practical textual-reasoning tasks over real-world documents including topic-gisting  ...  000 users of the Open Mind Common Sense Web site for contributing their time and effort to our project.  ... 
doi:10.1023/b:bttj.0000047600.45421.6d fatcat:hokobaz4xbfuba2fabzm7uirfy

TellMeWhy: A Dataset for Answering Why-Questions in Narratives [article]

Yash Kumar Lal, Nathanael Chambers, Raymond Mooney, Niranjan Balasubramanian
2021 arXiv   pre-print
Given the limitations of automated evaluation for this task, we also present a systematized human evaluation interface for this dataset.  ...  They are especially worse on questions whose answers are external to the narrative, thus providing a challenge for future QA and narrative understanding research.  ...  The authors would like to thank the anonymous reviewers and the area chair for their feedback on this work.  ... 
arXiv:2106.06132v1 fatcat:b7at2swm4jdhfb2gv2g3icx5ga

Social Commonsense Reasoning with Multi-Head Knowledge Attention [article]

Debjit Paul, Anette Frank
2020 arXiv   pre-print
Social Commonsense Reasoning requires understanding of text, knowledge about social events and their pragmatic implications, as well as commonsense reasoning skills.  ...  In this work we propose a novel multi-head knowledge attention model that encodes semi-structured commonsense inference rules and learns to incorporate them in a transformer-based reasoning cell.  ...  We thank our annotators for their valuable annotations. We also thank NVIDIA Corporation for donating GPUs used in this research.  ... 
arXiv:2010.05587v1 fatcat:g3rb54etq5ao5jsibfskvax54e

Story-oriented Image Selection and Placement [article]

Sreyasi Nag Chowdhury, Simon Razniewski, Gerhard Weikum
2019 arXiv   pre-print
In this paper we present a system that automates the process of selecting relevant images for a story and placing them at contextual paragraphs within the story for a multimodal narration.  ...  The selection of images from a collection - either author's personal photo album, or web repositories - and their meticulous placement within a text, builds a succinct multimodal commentary for digital  ...  Although user knowledge may provide some cues towards such abstract relationships, a deeper understanding of semantic coherence is desired.  ... 
arXiv:1909.00692v1 fatcat:vfpyju273faolohkfwmlvxueeu

Commonsense on the Go

H Lieberman, A Faaborg, J Espinosa, T Stocky
2004 BT technology journal  
We address these opportunities and challenges by giving portable devices commonsense knowledge -a large collection of simple facts about people and everyday life.  ...  We have leveraged the knowledge of human existence contained in ConceptNet to create three intelligent mobile applications -a dynamic phrasebook for tourists [6], a match making agent for searching your  ...  Acknowledgments The authors would like to thank Push Singh and Hugo Liu for their helpful feedback and for breaking new ground with Open Mind Common Sense and ConceptNet.  ... 
doi:10.1023/b:bttj.0000047602.54693.3d fatcat:2rrbtor7prf3ldkrdqde3n45pe

LSDSem 2017 Shared Task: The Story Cloze Test

Nasrin Mostafazadeh, Michael Roth, Annie Louis, Nathanael Chambers, James Allen
2017 Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics  
The LSDSem'17 shared task is the Story Cloze Test, a new evaluation for story understanding and script learning.  ...  This test provides a system with a four-sentence story and two possible endings, and the system must choose the correct ending to the story.  ...  We thank Alyson Grealish and Ahmed Hassan Awadallah for their help in the quality control of ROCStories corpus.  ... 
doi:10.18653/v1/w17-0906 dblp:conf/eacl/MostafazadehRLC17 fatcat:nwetyrkdlbaxfcm6raycx3vjla

A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets [article]

Changchang Zeng, Shaobo Li, Qin Li, Jie Hu, Jianjun Hu
2020 arXiv   pre-print
This shows the need for improving existing datasets, evaluation metrics, and models to move current MRC models toward "real" understanding.  ...  To address the current lack of comprehensive survey of existing MRC tasks, evaluation metrics, and datasets, herein, (1) we analyze 57 MRC tasks and datasets and propose a more precise classification method  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
arXiv:2006.11880v2 fatcat:auup4gvsuzf4dkjb2n6nzyfl3m

Recognizing expressions of commonsense psychology in English Text

Andrew Gordon, Abe Kazemzadeh, Anish Nair, Milena Petrova
2003 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - ACL '03  
In this paper, we describe our efforts to create a robust, large-scale lexical-semantic resource for the recognition and classification of expressions of commonsense psychology in English Text.  ...  We achieve high levels of precision and recall by hand-authoring sets of local grammars for commonsense psychology concepts, and show that this approach can achieve classification performance greater than  ...  Army Research Institute for the Behavioral and Social Sciences under ARO contract number DAAD 19-99-D-0046.  ... 
doi:10.3115/1075096.1075123 dblp:conf/acl/GordonKNP03 fatcat:bomlpnp24jgf5gil4kgqwarp7i

A Survey on Machine Reading Comprehension—Tasks, Evaluation Metrics and Benchmark Datasets

Changchang Zeng, Shaobo Li, Qin Li, Jie Hu, Jianjun Hu
2020 Applied Sciences  
This shows the need for improving existing datasets, evaluation metrics, and models to move current MRC models toward "real" understanding.  ...  To address the current lack of comprehensive survey of existing MRC tasks, evaluation metrics, and datasets, herein, (1) we analyze 57 MRC tasks and datasets and propose a more precise classification method  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app10217640 fatcat:e6rioqqdnbdqpimpxzvowhgv7a
« Previous Showing results 1 — 15 out of 1,106 results