Papers with hierarchical representations

7 papers
Hierarchical Representation-based Dynamic Reasoning Network for Biomedical Question Answering (2022.coling-1)

Copied to clipboard

Challenge: Existing models of biomedical question answering are limited in their ability to predict answers . a new model improves the performance of existing models, but the code will be released after the paper is published.
Approach: They propose a hierarchical representation-based dynamic reasoning network to solve biomedical problems.
Outcome: The proposed model significantly improves on three mainstream biomedical datasets . the code will be released after the paper is published .
Image Embedding Sampling Method for Diverse Captioning (2025.emnlp-main)

Copied to clipboard

Challenge: Currently, large-scale captioning models are less accessible for resource-constrained applications such as mobile devices and assistive technologies.
Approach: They propose a training-free framework that enhances caption diversity and informativeness by explicitly attending to distinct image regions using a comparably small VLM as the backbone.
Outcome: The proposed framework achieves comparable performance to larger models on MSCOCO, Flickr30k, and Nocaps test datasets while maintaining strong image-caption relevancy and semantic integrity with the human-annotated captions.
Story Trees: Representing Documents using Topological Persistence (2022.lrec-1)

Copied to clipboard

Challenge: Topological data analysis (TDA) focuses on the inherent shape of (spatial) data.
Approach: They propose to use topological data analysis to represent document structure as story trees . story trees are hierarchical representations created from semantic vector representations of sentences .
Outcome: The proposed methods can be used to extract summary summaries from news stories using story trees.
Growing Through Experience: Scaling Episodic Grounding in Language Models (2025.acl-long)

Copied to clipboard

Challenge: Language models (LMs) require effective episodic grounding to perform well at physical planning tasks due to their limited ability to learn from and apply past experiences.
Approach: They propose a weak-to-strong episodic learning framework that integrates episodic memory into hierarchical representations and pre-trained knowledge to unlock larger LMs' potential for grounding.
Outcome: The proposed framework outperforms top proprietary LMs by 3.45% across diverse planning and question-answering tasks.
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering (2020.acl-main)

Copied to clipboard

Challenge: Existing approaches to embedding in multiparty dialogues are poor for span-based question answering (QA)
Approach: They propose a novel approach to transformers that learns hierarchical representations in multiparty dialogue.
Outcome: The proposed model improves on the FriendsQA dataset by 3.8% and 1.4% over the two state-of-the-art models.
Conversational Semantic Parsing for Dialog State Tracking (2020.emnlp-main)

Copied to clipboard

Challenge: Language understanding for task-based dialog systems is often termed "dialog state tracking" (DST) whereas semantic parsing is the task of converting a single-turn utterance to a graphstructured meaning representation, DST is more complex.
Approach: They propose a framework for dialog state tracking that incorporates semantic compositionality, cross-domain knowledge sharing and co-reference.
Outcome: The proposed framework improves on state-of-the-art approaches for dialog state tracking (DST) it incorporates semantic compositionality, cross-domain knowledge sharing and co-reference.
Recurrent Neural Networks with Mixed Hierarchical Structures and EM Algorithm for Natural Language Processing (2022.lrec-1)

Copied to clipboard

Challenge: A variety of hierarchical RNN models have been proposed to incorporate hierarchically-based hierarchic information in modeling languages in the literature.
Approach: They propose a latent indicator layer approach to identify and learn hierarchical information and develop an EM algorithm to handle the latent indicators layer in training.
Outcome: The proposed approach outperforms other RNN-based models in document classification tasks.

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