LSDSem 2017 Shared Task: The Story Cloze Test

Mostafazadeh, Nasrin; Roth, Michael; Louis, Annie; Chambers, Nathanael; Allen, James F.

doi:10.18653/v1/w17-0906

Cited by 124 publications

(129 citation statements)

References 10 publications

(20 reference statements)

Supporting

Mentioning

112

Contrasting

Order By: Relevance

“…We also notice the recent progress in RocStories (Mostafazadeh et al, 2017). Rather than inferring a possible ending generated from document, recent systems solve this task by discriminatively comparing two candidates.…”

Section: Related Workmentioning

confidence: 99%

Reasoning with Heterogeneous Knowledge for Commonsense Machine Comprehension

Lin¹,

Sun²,

Han³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Reasoning with commonsense knowledge is critical for natural language understanding.Traditional methods for commonsense machine comprehension mostly only focus on one specific kind of knowledge, neglecting the fact that commonsense reasoning requires simultaneously considering different kinds of commonsense knowledge. In this paper, we propose a multi-knowledge reasoning method, which can exploit heterogeneous knowledge for commonsense machine comprehension. Specifically, we first mine different kinds of knowledge (including event narrative knowledge, entity semantic knowledge and sentiment coherent knowledge) and encode them as inference rules with costs. Then we propose a multiknowledge reasoning model, which selects inference rules for a specific reasoning context using attention mechanism, and reasons by summarizing all valid inference rules. Experiments on RocStories show that our method outperforms traditional models significantly.

show abstract

Section: Related Workmentioning

confidence: 99%

Reasoning with Heterogeneous Knowledge for Commonsense Machine Comprehension

Lin¹,

Sun²,

Han³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…Based on these vector representations, it predicts the ending-option with the largest cosine similarity with the context. Msap: The task addressed in this paper was also a shared task for an EACL'17 workshop and this baseline (Schwartz et al, 2017) represents the best performance reported on its leaderboard (Mostafazadeh et al, 2017). It trains a logistic regression based on stylistic and languagemodel based features.…”

Section: Baselinesmentioning

confidence: 99%

Story Comprehension for Predicting What Happens Next

Chaturvedi¹,

Peng²,

Roth³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Automatic story comprehension is a fundamental challenge in Natural Language Understanding, and can enable computers to learn about social norms, human behavior and commonsense. In this paper, we present a story comprehension model that explores three distinct semantic aspects: (i) the sequence of events described in the story, (ii) its emotional trajectory, and (iii) its plot consistency. We judge the model's understanding of real-world stories by inquiring if, like humans, it can develop an expectation of what will happen next in a given story. Specifically, we use it to predict the correct ending of a given short story from possible alternatives. The model uses a hidden variable to weigh the semantic aspects in the context of the story. Our experiments demonstrate the potential of our approach to characterize these semantic aspects, and the strength of the hidden variable based approach. The model outperforms the stateof-the-art approaches and achieves best results on a publicly available dataset.

show abstract

“…To fine tune the model on short stories, we re-train FES-LM on the ROCStories dataset (Mostafazadeh et al, 2017) with the model trained on NYT as initialization. We use the train set of ROCStories, which contains around 100K short stories (each consists of five sentences) 5 .…”

Section: Dataset and Preprocessingmentioning

confidence: 99%

“…We then re-train the model on short commonsense stories (with the model trained on news as initialization). We perform story cloze test (Mostafazadeh et al, 2017), i.e. given a four-sentence story, choose the fifth sentence from two provided options.…”

Section: Introductionmentioning

confidence: 99%

A Joint Model for Semantic Sequences: Frames, Entities, Sentiments

Peng¹,

Chaturvedi²,

Roth³

2017

Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)

View full text Add to dashboard Cite

Understanding stories -sequences of events -is a crucial yet challenging natural language understanding task. These events typically carry multiple aspects of semantics including actions, entities and emotions. Not only does each individual aspect contribute to the meaning of the story, so does the interaction among these aspects. Building on this intuition, we propose to jointly model important aspects of semantic knowledge -frames, entities and sentiments -via a semantic language model. We achieve this by first representing these aspects' semantic units at an appropriate level of abstraction and then using the resulting vector representations for each semantic aspect to learn a joint representation via a neural language model. We show that the joint semantic language model is of high quality and can generate better semantic sequences than models that operate on the word level. We further demonstrate that our joint model can be applied to story cloze test and shallow discourse parsing tasks with improved performance and that each semantic aspect contributes to the model.

show abstract

LSDSem 2017 Shared Task: The Story Cloze Test

Cited by 124 publications

References 10 publications

Reasoning with Heterogeneous Knowledge for Commonsense Machine Comprehension

Reasoning with Heterogeneous Knowledge for Commonsense Machine Comprehension

Story Comprehension for Predicting What Happens Next

A Joint Model for Semantic Sequences: Frames, Entities, Sentiments

Contact Info

Product

Resources

About