Temporal Event Knowledge Acquisition via Identifying Narratives

Yao, Wenlin; Huang, Ruihong

doi:10.18653/v1/p18-1050

Cited by 17 publications

(13 citation statements)

References 26 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One might argue that the reason the sequence perturbations work better in terms of INC accuracy is that the events extracted from news do not necessarily follow the temporal order and therefore the perturbations will not create an issue. To show the effectiveness of our approach, we evaluated the performance of our models on the event sequences extracted from narratives coming from different domains: novels, blogs and news (Yao and Huang, 2018).…”

Section: Discussionmentioning

confidence: 99%

“…By considering the next event based on shuffled sequences of events, we encourage the model to treat the input more as a set of events rather than strictly as a discourse sequence. Surprisingly, despite our disruption of discourse order, experiments show how perturbations can improve event language modeling of text, particularly when evaluating the model on other domains which present events in different orders (e.g., novels or blogs present data in more of a "narrative" fashion than news datasets common in NLP (Yao and Huang, 2018)). Our experiments evaluate accuracy on the Inverse Narrative Cloze task on in-domain newswire, as well as out-domain novels and blogs 1 .…”

Section: Introductionmentioning

confidence: 93%

See 1 more Smart Citation

Don’t Let Discourse Confine Your Model: Sequence Perturbations for Improved Event Language Models

Koupaee¹,

Durrett²,

Chambers³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Event language models represent plausible sequences of events. Most existing approaches train autoregressive models on text, which successfully capture event co-occurrence but unfortunately constrain the model to follow the discourse order in which events are presented. Other domains may employ different discourse orders, and for many applications, we may care about different notions of ordering (e.g., temporal) or not care about ordering at all (e.g., when predicting related events in a schema). We propose a simple yet surprisingly effective strategy for improving event language models by perturbing event sequences so we can relax model dependence on text order. Despite generating completely synthetic event orderings, we show that this technique improves the performance of the event language models on both applications and outof-domain events data.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 93%

Don’t Let Discourse Confine Your Model: Sequence Perturbations for Improved Event Language Models

Koupaee¹,

Durrett²,

Chambers³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

show abstract

“…For event knowledge, we considered three major event relation types including temporal, causal and subevent. We obtained event temporal knowledge from a previous work (Yao and Huang, 2018) 10 and we retrieved the latter two types of event knowledge from Concept-Net 11 (Speer and Havasi, 2012), which is a widelyused commonsense knowledge base.…”

Section: Dataset and Preprocessingmentioning

confidence: 99%

A Regularization Approach for Incorporating Event Knowledge and Coreference Relations into Neural Discourse Parsing

Dai

Huang

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

View full text Add to dashboard Cite

We argue that external commonsense knowledge and linguistic constraints need to be incorporated into neural network models for mitigating data sparsity issues and further improving the performance of discourse parsing. Realizing that external knowledge and linguistic constraints may not always apply in understanding a particular context, we propose a regularization approach that tightly integrates these constraints with contexts for deriving word representations. Meanwhile, it balances attentions over contexts and constraints through adding a regularization term into the objective function. Experiments show that our knowledge regularization approach outperforms all previous systems on the benchmark dataset PDTB for discourse parsing.

show abstract

“…Gathering large-scale high-quality labeled data with temporal annotations is often expensive and requires specially designed annotation schemes (Pustejovsky et al, 2003a;Cassidy et al, 2014;Ning et al, 2018b;Zhao et al, 2021). Here, we instead turn to a narrative documents corpus, EventsNarratives (Yao and Huang, 2018) and design an automatic method to extract the training data we need. In these documents, discourse order is loosely assumed to reflect temporal order, so events extracted from this text can directly provide training data for our models.…”

Section: Introductionmentioning

confidence: 99%

Conditional Generation of Temporally-ordered Event Sequences

Lin¹,

Chambers²,

Durrett³

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Models of narrative schema knowledge have proven useful for a range of event-related tasks, but they typically do not capture the temporal relationships between events. We propose a single model that addresses both temporal ordering, sorting given events into the order they occurred, and event infilling, predicting new events which fit into an existing temporally-ordered sequence. We use a BARTbased conditional generation model that can capture both temporality and common event co-occurrence, meaning it can be flexibly applied to different tasks in this space. Our model is trained as a denoising autoencoder: we take temporally-ordered event sequences, shuffle them, delete some events, and then attempt to recover the original event sequence. This task teaches the model to make inferences given incomplete knowledge about the events in an underlying scenario. On the temporal ordering task, we show that our model is able to unscramble event sequences from existing datasets without access to explicitly labeled temporal training data, outperforming both a BERT-based pairwise model and a BERT-based pointer network. On event infilling, human evaluation shows that our model is able to generate events that fit better temporally into the input events when compared to GPT-2 story completion models.

show abstract

Temporal Event Knowledge Acquisition via Identifying Narratives

Cited by 17 publications

References 26 publications

Don’t Let Discourse Confine Your Model: Sequence Perturbations for Improved Event Language Models

Don’t Let Discourse Confine Your Model: Sequence Perturbations for Improved Event Language Models

A Regularization Approach for Incorporating Event Knowledge and Coreference Relations into Neural Discourse Parsing

Conditional Generation of Temporally-ordered Event Sequences

Contact Info

Product

Resources

About