Challenge: Existing work has treated procedures as shallow structures without modeling the parent-child relation.
Approach: They propose to construct an open-domain hierarchical knowledge-base (KB) of procedures based on wikiHow . they link steps in an article to other articles with similar goals, recursively building the KB .
Outcome: The proposed method significantly outperforms baselines according to automatic evaluation, human judgment, and application to downstream tasks such as instructional video retrieval.

Similar Papers

Benchmarking Hierarchical Script Knowledge (N19-1)

Copied to clipboard

Challenge: Understanding procedural language requires reasoning about hierarchical and temporal relations between events.
Approach: They propose a hierarchical script learning dataset and a cloze task to match video captions with missing procedural details.
Outcome: The proposed model matches video captions with missing procedural details to find out if they can understand the language.
Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation (2023.findings-acl)

Copied to clipboard

Challenge: Existing work assumes that events are sequentially arranged in a script, while this assumption leads to linear generation that is far from sufficient for comprehensively acquiring the representation about how events are organized towards a task goal.
Approach: They propose to extend goal-oriented Script Generation task from the perspective of cognitive theory by incorporating subgoals into hierarchical script generation.
Outcome: The proposed task is based on a new dataset and human evaluation metrics.
Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge Utilization (2024.emnlp-main)

Copied to clipboard

Challenge: Despite advances in large language models, how they use their knowledge for reasoning is not yet well understood.
Approach: They propose a method that deconstructs complex real-world questions into a graph . they quantify forward discrepancy, a discrepany in LLM performance on simpler sub-problems .
Outcome: The proposed method shows that smaller models exhibit more discrepancies than larger models . it also shows that guiding models from simpler to complex questions improves performance .
HyHTM: Hyperbolic Geometry-based Hierarchical Topic Model (2023.findings-acl)

Copied to clipboard

Challenge: Hierarchical Topic Models (HTMs) often produce hierarchies where lower-level topics are unrelated and not specific enough to their higher-level subjects.
Approach: They propose a Hyperbolic geometry-based Hierarchical Topic Model that incorporates hierarchical information from hyperbolic geometrics to explicitly model hierarchies in topic models.
Outcome: The proposed model is significantly faster and leaves a much smaller memory footprint than the best-performing baseline.
Structured Self-Supervised Pretraining for Commonsense Knowledge Graph Completion (2021.tacl-1)

Copied to clipboard

Challenge: Existing approaches focus on generating concepts that have direct and obvious relationships with existing concepts and lack an ability to generate unobvious concepts.
Approach: They propose a general graph-to-paths pretraining framework that leverages high-order structures in CKGs to capture high-level relationships between concepts.
Outcome: The proposed framework can capture high-order relationships between concepts in four special cases: long path, path-to-path, router, and graph-node-path.
A Web-scale system for scientific knowledge exploration (P18-4)

Copied to clipboard

Challenge: a system that organizes scientific knowledge into a hierarchical concept structure is needed to enable efficient exploration of Web-scale knowledge.
Approach: They propose a system that organizes scientific knowledge into a hierarchical concept structure . system allows researchers to identify hundreds of thousands of scientific concepts . it also allows researchers tagging scientific publications into millions of concepts based on text and graph structure based model .
Outcome: The proposed system builds the most comprehensive cross-domain scientific concept ontology published to date, with more than 200 thousand concepts and over one million relationships.
Tree-KG: An Expandable Knowledge Graph Construction Framework for Knowledge-intensive Domains (2025.acl-long)

Copied to clipboard

Challenge: Knowledge graphs are a useful tool for organizing complex data in knowledge-intensive domains.
Approach: They propose an expandable framework that combines structured domain texts with advanced semantic techniques to create a tree-like graph from textbooks.
Outcome: The proposed framework surpasses competing methods in the text-Annotated dataset with high scores on the Text-Annalytated data.
Constructing Procedural Graphs with Multiple Dependency Relations: A New Dataset and Baseline (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to structure procedural knowledge focus on representing descriptive knowledge but ignore another commonsense knowledge-Procedural Knowledge.
Approach: They propose to generate flow graphs from procedural documents by extracting sequential dependency between sentences and missing two important dependencies in procedural document.
Outcome: The proposed method can generate flow graphs from unstructured documents with syntactic information and discourse structures.
A hierarchical approach to vision-based language generation: from simple sentences to complex natural language (2020.coling-main)

Copied to clipboard

Challenge: Automating video to language translation is a challenging problem, but it is unclear what the neural network learns .
Approach: They propose a hierarchical approach to automatically describing videos in natural language . they propose generating video descriptions as sequences of simple sentences followed by a more complex and fluent description in natural languages.
Outcome: The proposed approach generates video descriptions as sequences of simple sentences, followed by a more complex and fluent description in natural language.
Scalable Construction and Reasoning of Massive Knowledge Bases (N18-6)

Copied to clipboard

Challenge: Existing knowledge mining systems assume abundant human annotations for training high quality machine learning models, which is impractical when trying to deploy IE systems to a broad range of domains, settings and languages.
Approach: They introduce how to extract structured facts from text corpora to construct knowledge bases.
Outcome: The proposed methods are weakly-supervised and domain-independent for knowledge base construction across various domains.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations