Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing最新文献

Commonsense about Human Senses: Labeled Data Collection Processes 关于人类感官的常识:标记数据收集过程

Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing Pub Date : 2019-11-01 DOI: 10.18653/v1/D19-6005

Ndapandula Nakashole

引用次数: 0

How Pre-trained Word Representations Capture Commonsense Physical Comparisons 预训练词表征如何捕获常识性物理比较

Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing Pub Date : 2019-11-01 DOI: 10.18653/v1/D19-6016

Pranav Goel

引用次数: 6

Diversity-aware Event Prediction based on a Conditional Variational Autoencoder with Reconstruction 基于重构条件变分自编码器的分集感知事件预测

Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/D19-6014

Hirokazu Kiyomaru, Kazumasa Omura, Yugo Murawaki, Daisuke Kawahara, S. Kurohashi

{"title":"Diversity-aware Event Prediction based on a Conditional Variational Autoencoder with Reconstruction","authors":"Hirokazu Kiyomaru, Kazumasa Omura, Yugo Murawaki, Daisuke Kawahara, S. Kurohashi","doi":"10.18653/v1/D19-6014","DOIUrl":"https://doi.org/10.18653/v1/D19-6014","url":null,"abstract":"Typical event sequences are an important class of commonsense knowledge. Formalizing the task as the generation of a next event conditioned on a current event, previous work in event prediction employs sequence-to-sequence (seq2seq) models. However, what can happen after a given event is usually diverse, a fact that can hardly be captured by deterministic models. In this paper, we propose to incorporate a conditional variational autoencoder (CVAE) into seq2seq for its ability to represent diverse next events as a probabilistic distribution. We further extend the CVAE-based seq2seq with a reconstruction mechanism to prevent the model from concentrating on highly typical events. To facilitate fair and systematic evaluation of the diversity-aware models, we also extend existing evaluation datasets by tying each current event to multiple next events. Experiments show that the CVAE-based models drastically outperform deterministic models in terms of precision and that the reconstruction mechanism improves the recall of CVAE-based models without sacrificing precision.","PeriodicalId":192716,"journal":{"name":"Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128931143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

Understanding Commonsense Inference Aptitude of Deep Contextual Representations 理解深度语境表征的常识推理能力

Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/d19-6001

Jeff Da, Jungo Kasai

引用次数: 33

IIT-KGP at COIN 2019: Using pre-trained Language Models for modeling Machine Comprehension IIT-KGP在COIN 2019:使用预训练的语言模型建模机器理解

Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/D19-6009

Prakhar Sharma, Sumegh Roychowdhury

引用次数: 1

Pingan Smart Health and SJTU at COIN - Shared Task: utilizing Pre-trained Language Models and Common-sense Knowledge in Machine Reading Tasks 平安智能健康与上海交通大学COIN -共享任务:在机器阅读任务中利用预训练的语言模型和常识知识

Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/D19-6011

Xiepeng Li, Zhexi Zhang, Wei Zhu, Zheng Li, Yuan Ni, Peng Gao, Junchi Yan, G. Xie

{"title":"Pingan Smart Health and SJTU at COIN - Shared Task: utilizing Pre-trained Language Models and Common-sense Knowledge in Machine Reading Tasks","authors":"Xiepeng Li, Zhexi Zhang, Wei Zhu, Zheng Li, Yuan Ni, Peng Gao, Junchi Yan, G. Xie","doi":"10.18653/v1/D19-6011","DOIUrl":"https://doi.org/10.18653/v1/D19-6011","url":null,"abstract":"To solve the shared tasks of COIN: COmmonsense INference in Natural Language Processing) Workshop in , we need explore the impact of knowledge representation in modeling commonsense knowledge to boost performance of machine reading comprehension beyond simple text matching. There are two approaches to represent knowledge in the low-dimensional space. The first is to leverage large-scale unsupervised text corpus to train fixed or contextual language representations. The second approach is to explicitly express knowledge into a knowledge graph (KG), and then fit a model to represent the facts in the KG. We have experimented both (a) improving the fine-tuning of pre-trained language models on a task with a small dataset size, by leveraging datasets of similar tasks; and (b) incorporating the distributional representations of a KG onto the representations of pre-trained language models, via simply concatenation or multi-head attention. We find out that: (a) for task 1, first fine-tuning on larger datasets like RACE (Lai et al., 2017) and SWAG (Zellersetal.,2018), and then fine-tuning on the target task improve the performance significantly; (b) for task 2, we find out the incorporating a KG of commonsense knowledge, WordNet (Miller, 1995) into the Bert model (Devlin et al., 2018) is helpful, however, it will hurts the performace of XLNET (Yangetal.,2019), a more powerful pre-trained model. Our approaches achieve the state-of-the-art results on both shared task’s official test data, outperforming all the other submissions.","PeriodicalId":192716,"journal":{"name":"Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130974220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

BLCU-NLP at COIN-Shared Task1: Stagewise Fine-tuning BERT for Commonsense Inference in Everyday Narrations 硬币共享任务1的blu - nlp:日常叙述中常识推理的阶段性微调BERT

Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/D19-6012

Chunhua Liu, Shike Wang, Bohan Li, Dong Yu

引用次数: 3

Jeff Da at COIN - Shared Task Jeff Da在COIN -共享任务

Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/V1/D19-6010

Jeff Da

引用次数: 1

Commonsense Inference in Natural Language Processing (COIN) - Shared Task Report 自然语言处理(COIN)中的常识推理-共享任务报告

Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/D19-6007

Simon Ostermann, Sheng Zhang, Michael Roth, Peter Clark

引用次数: 5

KARNA at COIN Shared Task 1: Bidirectional Encoder Representations from Transformers with relational knowledge for machine comprehension with common sense KARNA在COIN共享任务1:双向编码器表示从变压器与关系知识与常识的机器理解

Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/D19-6008

Yash Jain, Chinmay Singh

引用次数: 3