Analogous Process Structure Induction for Sub-event Sequence Prediction

Zhang, Hongming; Chen, Muhao; Wang, Haoyu; Song, Yangqiu; Roth, Dan

doi:10.18653/v1/2020.emnlp-main.119

Cited by 31 publications

(25 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike the previous works [49,50], we do not distinguish activities (or processes), states, and events. Instead, we use dependency patterns to represent all the eventualities that can be activities, states, and events and also discourse relations [30] such as COMPARISON.Contrast and CONTINGENCY.Cause as the relation types between eventualities based on the following two design principles.…”

Section: Design Principlesmentioning

confidence: 99%

ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities

Zhang¹,

Liu²,

Pan³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Commonsense knowledge acquisition and reasoning have long been a core artificial intelligence problem. However, in the past, there has been a lack of scalable methods to collect commonsense knowledge. In this paper, we propose to develop principles for collecting commonsense knowledge based on selectional preference, which is a common phenomenon in human languages that has been shown to be related to semantics. We generalize the definition of selectional preference from one-hop linguistic syntactic relations to higher-order relations over linguistic graphs. Unlike previous commonsense knowledge definition (e.g., ConceptNet), the selectional preference (SP) knowledge only relies on statistical distribution over linguistic graphs, which can be efficiently and accurately acquired from the unlabeled corpus with modern tools, rather than human-defined relations. As a result, acquiring SP knowledge is a much more salable way of acquiring commonsense knowledge. Following this principle, we develop a large-scale eventuality (a linguistic term covering activity, state, and event)-based knowledge graph ASER, where each eventuality is represented as a dependency graph, and the relation between them is a discourse relation defined in shallow discourse parsing. The higher-order selectional preference over collected linguistic graphs reflects various kinds of commonsense knowledge. For example, dogs are more likely to bark than cats as the eventuality "dog barks" appears 14,998 times in ASER while "cat barks" only appears 6 times. "Be hungry" is more likely to be the reason rather than result of "eat food" as the edge "be hungry", Cause, "eat food" appears in ASER while "eat food", Cause, "be hungry" does not. Moreover, motivated by the observation that humans understand events by abstracting the observed events to a higher level and can thus transferring their knowledge to new events, we propose a conceptualization module on top of the collected knowledge to significantly boost the coverage of ASER. In total, ASER contains 438 million eventualities and 648 million edges between eventualities. After conceptualization with Probase, a selectional preference based concept-instance relational knowledge base, our concept graph contains 15 million conceptualized eventualities and 224 million edges between them. Detailed analysis is provided to demonstrate its quality. All the collected data, APIs, and tools that can help convert collected SP knowledge into the format of ConceptNet are available at https://github.com/HKUST-KnowComp/ASER.

show abstract

Section: Design Principlesmentioning

confidence: 99%

ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities

Zhang¹,

Liu²,

Pan³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Previous work on schema induction has focused solely on textual resources through statistical methods [1,3,4,11,36] and neural approaches [1,23,24,30,43,44,49,59]. While [57] employ multimodal resources to extract procedural knowledge, the output is an implicit vector representation, unlike our work's explicit and interpretable schema.…”

Section: Related Workmentioning

confidence: 99%

Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrieval

Yang¹,

Kim²,

Panagopoulou³

et al. 2021

Preprint

View full text Add to dashboard Cite

Schemata are structured representations of complex tasks that can aid artificial intelligence by allowing models to break down complex tasks into intermediate steps. We propose a novel system that induces schemata from web videos and generalizes them to capture unseen tasks with the goal of improving video retrieval performance. Our system proceeds in three major phases: (1) Given a task with related videos, we construct an initial schema for a task using a joint videotext model to match video segments with text representing steps from wikiHow; (2) We generalize schemata to unseen tasks by leveraging language models to edit the text within existing schemata. Through generalization, we can allow our schemata to cover a more extensive range of tasks with a small amount of learning data; (3) We conduct zero-shot instructional video retrieval with the unseen task names as the queries. Our schema-guided approach outperforms existing methods for video retrieval, and we demonstrate that the schemata induced by our system are better than those generated by other models.

show abstract

“…Pattern-Based Approaches. Taxonomies from experts (e.g., WordNet (Miller, 1995)) have proved effective in various reasoning applications (Song et al, 2011;Zhang et al, 2020). Meanwhile, Hearst patterns (Hearst, 1992) make large corpora a good resource of explicit is-a pairs, resulting in automatically built hypernymy knowledge bases (Wu et al, 2012;Seitner et al, 2016) of large scales.…”

Section: Related Workmentioning

confidence: 99%

When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models

Yu¹,

Han²,

Wang³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

View full text Add to dashboard Cite

We address hypernymy detection, i.e., whether an is-a relationship exists between words (x, y), with the help of large textual corpora. Most conventional approaches to this task have been categorized to be either pattern-based or distributional. Recent studies suggest that pattern-based ones are superior, if large-scale Hearst pairs are extracted and fed, with the sparsity of unseen (x, y) pairs relieved. However, they become invalid in some specific sparsity cases, where x or y is not involved in any pattern. For the first time, this paper quantifies the non-negligible existence of those specific cases. We also demonstrate that distributional methods are ideal to make up for patternbased ones in such cases. We devise a complementary framework, under which a patternbased and a distributional model collaborate seamlessly in cases which they each prefer. On several benchmark datasets, our framework achieves competitive improvements and the case study shows its better interpretability.

show abstract

Analogous Process Structure Induction for Sub-event Sequence Prediction

Cited by 31 publications

References 21 publications

ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities

ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities

Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrieval

When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models

Contact Info

Product

Resources

About