Story Cloze Task: UW NLP System

This paper describes University of Washington NLP’s submission for the Linking Models of Lexical, Sentential and Discourse-level Semantics (LSDSem 2017) shared task—the Story Cloze Task. Our system is a linear classifier with a variety of features, including both the scores of a neural language model and style features. We report 75.2% accuracy on the task. A further discussion of our results can be found in Schwartz et al. (2017).

• Publication year

  2017

• Venue

  LSDSem@EACL

• Publication date

  2017-04-01

• Fields of study

  Linguistics, Computer Science, Psychology

• Identifiers
  DOI 10.18653/v1/W17-0907
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task

  2017cited by this paper
• Enhancing the LexVec Distributed Word Representation Model Using Positional Contexts and External Memory

  2016cited by this paper
• A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories

  2016influential reference
• ConceptNet 5.5: An Open Multilingual Graph of General Knowledge

  2016cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Authorship Attribution of Micro-Messages

  2013cited by this paper
• Stylometric Analysis of Scientific Articles

  2012cited by this paper
• Gender identity and lexical variation in social media

  2012cited by this paper
• Cross-domain Feature Selection for Language Identification

  2011cited by this paper
• Age Prediction in Blogs: A Study of Style, Content, and Online Behavior in Pre- and Post-Social Media Generations

  2011cited by this paper
• Author Age Prediction from Text using Linear Regression

  2011cited by this paper
• ICWSM - A Great Catchy Name: Semi-Supervised Recognition of Sarcastic Sentences in Online Product Reviews

  2010cited by this paper
• Recurrent neural network based language model

  2010cited by this paper
• A survey of modern authorship attribution methods

  2009cited by this paper
• Using Classifier Features for Studying the Effect of Native Language on the Choice of Written Second Language Words

  2007cited by this paper
• Effects of Age and Gender on Blogging

  2006cited by this paper
• Determining an author's native language by mining a text for errors

  2005cited by this paper
• Gender, genre, and writing style in formal written texts

  2003cited by this paper
• Long Short-Term Memory

  1997influential reference

• Text Quality-Based Pruning for Efficient Training of Language Models

  2024cites this paper
• Crafting Narrative Closures: Zero-Shot Learning with SSM Mamba for Short Story Ending Generation

  2024cites this paper
• A Historical Survey of Advances in Transformer Architectures

  2024cites this paper
• Cloze Evaluation for Deeper Understanding of Commonsense Stories in Indonesian

  2022cites this paper
• A Survey of Parameters Associated with the Quality of Benchmarks in NLP

  2022cites this paper
• MRCLens: an MRC Dataset Bias Detection Toolkit

  2022cites this paper
• Designing an Automatic Story Evaluation Metric

  2022influential citation
• TransBERT

  2021influential citation
• AESOP: Abstract Encoding of Stories, Objects, and Pictures

  2021cites this paper
• It’s not Rocket Science: Interpreting Figurative Language in Narratives

  2021cites this paper
• Posthoc Verification and the Fallibility of the Ground Truth

  2021cites this paper
• Story Ending Generation with Multi-Level Graph Convolutional Networks over Dependency Trees

  2021cites this paper
• Incorporating sentimental trend into gated mechanism based transformer network for story ending generation

  2021cites this paper
• Learning a Word-Level Language Model with Sentence-Level Noise Contrastive Estimation for Contextual Sentence Probability Estimation

  2021cites this paper
• Enhancing Pre-trained Language Models by Self-supervised Learning for Story Cloze Test

  2020cites this paper
• ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning

  2020cites this paper
• DTC: Transfer learning for commonsense machine comprehension

  2020cites this paper
• Multimodal Story Generation on Plural Images

  2020cites this paper
• Assessment of Word-Level Neural Language Models for Sentence Completion

  2020cites this paper
• Toward Better Storylines with Sentence-Level Language Models

  2020influential citation
• Story Completion with Explicit Modeling of Commonsense Knowledge

  2020cites this paper
• Knowledge Science, Engineering and Management: 13th International Conference, KSEM 2020, Hangzhou, China, August 28–30, 2020, Proceedings, Part II

  2020cites this paper
• Simple but effective techniques to reduce dataset biases

  2019cites this paper
• Story Ending Prediction by Transferable BERT

  2019cites this paper
• Chatting about data

  2019cites this paper
• logical reasoning type - Explain or Resolve

  2019cites this paper
• Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects

  2019cites this paper
• Incorporating Relation Knowledge into Commonsense Reading Comprehension with Multi-task Learning

  2019cites this paper
• CCHAN: An End to End Model for Cross Domain Sentiment Classification

  2019cites this paper
• Don’t Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference

  2019cites this paper
• Language Models are Unsupervised Multitask Learners

  2019cites this paper
• On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference

  2019cites this paper
• Story Ending Selection by Finding Hints From Pairwise Candidate Endings

  2019cites this paper
• Simple but effective techniques to reduce biases

  2019cites this paper
• Story Understanding with External Knowledge Based Attention

  2018cites this paper
• A Simple and Effective Approach to the Story Cloze Test

  2018influential citation
• Blindfold Baselines for Embodied QA

  2018cites this paper
• Incorporating Structured Commonsense Knowledge in Story Completion

  2018influential citation
• What Makes Reading Comprehension Questions Easier?

  2018cites this paper
• Tackling the Story Ending Biases in The Story Cloze Test

  2018influential citation
• Hypothesis Only Baselines in Natural Language Inference

  2018cites this paper
• LSDSem 2017 Shared Task: The Story Cloze Test

  2017cites this paper
• Story Comprehension for Predicting What Happens Next

  2017influential citation
• Reasoning with Heterogeneous Knowledge for Commonsense Machine Comprehension

  2017cites this paper
• Modelling Protagonist Goals and Desires in First-Person Narrative

  2017cites this paper
• The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task

  2017cites this paper
• Pay Attention to the Ending:Strong Neural Baselines for the ROC Story Cloze Task

  2017influential citation
• Scholarship, Research, and Creative Work at Bryn Mawr College Scholarship, Research, and Creative Work at Bryn Mawr College

  year unknowncites this paper