Challenge: Existing approaches to search result clustering use multiple views and visual and textual views.
Approach: They propose to use multi-view learning to learn search results from web-snippets . they propose to obtain a single consensus partitioning after consulting two views .
Outcome: The proposed approach on a benchmark dataset shows that visual and text-based views can achieve better clustering.

Similar Papers

Exploring the Value of Multi-View Learning for Session-Aware Query Representation (2022.findings-naacl)

Copied to clipboard

Challenge: Existing approaches to learn distributed query representations only consider user’s query reformulations or system’s rankings . previous studies show that user’ s query behavior and knowledge change depending on the system’ 'results' and intertwine and affect each other during the completion of a search task.
Approach: They propose to use multi-view learning methods to align query embeddings with document ranking representations using transformers.
Outcome: The proposed approach can capture search intent semantics and can reflect user's query behavior and knowledge.
Improving Hierarchical Text Clustering with LLM-guided Multi-view Cluster Representation (2024.emnlp-industry)

Copied to clipboard

Challenge: a multi-stage approach to hierarchical clustering of interaction drivers in contact centers is proposed . silhouette score and human preference score are improved by 36.7% for top-level clusters compared to standard agglomerative clustering .
Approach: They propose a multi-stage approach that introduces different perspectives or views to improve the quality of hierarchical clustering of interaction drivers in a contact center.
Outcome: The proposed approach improves the quality of generated clusters on public datasets with minimal query time compared to the current state-of-the-art approaches.
Dialog Intent Induction with Deep Multi-View Clustering (D19-1)

Copied to clipboard

Challenge: Existing work assumes that dialog intents are expressed in query utterances and captured in the rest of the dialog.
Approach: They propose a dialog intent induction task and propose alternating-view k-means for clustering . they split a conversation into two independent views and exploit multi-view clustering techniques .
Outcome: The proposed approach can induce better dialog intent clusters than state-of-the-art clustering methods.
Multi-View Document Representation Learning for Open-Domain Dense Retrieval (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for dense retrieval are hard to match with multiple views.
Approach: They propose a multi-view document representation learning framework to generate multiple embeddings through viewers to represent documents and enforce them to align with different queries.
Outcome: The proposed method outperforms recent works and achieves state-of-the-art results.
Improving Multi-view Document Clustering: Leveraging Multi-structure Processor and Hybrid Ensemble Clustering Module (2024.lrec-main)

Copied to clipboard

Challenge: Experimental results show that DMsECN outperforms existing models for document clustering .
Approach: They propose a multi-view document clustering model with a processor and hybrid module . they demonstrate that DMsECN outperforms existing models by creating a consensus structure from multiple clustering structures.
Outcome: The proposed model outperforms existing models on four multi-view document clustering datasets.
Syntactic Multi-view Learning for Open Information Extraction (2022.emnlp-main)

Copied to clipboard

Challenge: Open Information Extraction (OpenIE) aims to generate structured tuples from unstructured open-domain text.
Approach: They propose to model constituency and dependency trees into word-level graphs and combine them with sentential semantic representations to extract relational tuples.
Outcome: The proposed model integrates constituency and dependency trees into word-level graphs and enables neural OpenIE to learn from syntactic structures.
Style-Aware Contrastive Learning for Multi-Style Image Captioning (2023.findings-eacl)

Copied to clipboard

Challenge: Existing multi-style image captioning methods focus on visual content and style . existing methods overlook the relationship between linguistic style and visual content.
Approach: They propose a style-aware visual encoder with contrastive learning to mine potential visual content relevant to style and a triplet contrast objective to distinguish whether the image, style and caption matched.
Outcome: The proposed method achieves state-of-the-art performance and an extensive analysis to verify its effectiveness.
Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances (2024.acl-long)

Copied to clipboard

Challenge: Existing methods for semantics discovery focus on text, video, and audio, failing to leverage the rich multimodal information in the real world.
Approach: They propose a method to construct augmentation views for multimodal data and use them to perform pre-training to establish well-initialized representations for subsequent clustering.
Outcome: The proposed method improves on benchmark multimodal intent and dialogue act datasets by 2-6% over state-of-the-art methods.
Proposition-Level Clustering for Multi-Document Summarization (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods focused on clustering sentences to indicate information saliency and avoid redundancy.
Approach: They propose to group together sub-sentential propositions to generate a representative sentence for each cluster via text fusion.
Outcome: The proposed method improves over the previous state-of-the-art method in the DUC 2004 and TAC 2011 datasets, both in automatic ROUGE scores and human preference.
VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search (2025.emnlp-main)

Copied to clipboard

Challenge: Existing vision-language models struggle with reasoning-focused tasks due to the lack of high-quality training data.
Approach: They propose a new approach that leverages search engines to create a multimodal multimodal dataset . they use a set of 30,000 seed images to extract HTML data from 700K unique URLs .
Outcome: The proposed model achieves the best known performance on MMMU-Pro (40.7), MathVerse (42.6), and DynaMath (55.7).

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