Search Results for author:
Found 6 papers, 4 papers with code
Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty
To address this, we propose a design for proactive T2I agents equipped with an interface to (1) actively ask clarification questions when uncertain, and (2) present their understanding of user intent as an understandable belief graph that a user can edit.
Efficient Pointwise-Pairwise Learning-to-Rank for News Recommendation
Extensive experiments show that our approach outperforms the state-of-the-art methods on the MIND and Adressa news recommendation datasets.
Beyond Aesthetics: Cultural Competence in Text-to-Image Models
CUBE consists of 1) CUBE-1K, a set of high-quality prompts that enable the evaluation of cultural awareness, and 2) CUBE-CSpace, a larger dataset of cultural artifacts that serves as grounding to evaluate cultural diversity.
CONTRASTE: Supervised Contrastive Pre-training With Aspect-based Prompts For Aspect Sentiment Triplet Extraction
We then (pre)train an encoder-decoder model by applying contrastive learning on the decoder-generated aspect-aware sentiment representations of the masked terms.
Ranked #3 on
Aspect Sentiment Triplet Extraction
on ASTE-Data-V2
Aspect Sentiment Triplet Extraction
Aspect Term Extraction and Sentiment Classification
+4
Targeted Extraction of Temporal Facts from Textual Resources for Improved Temporal Question Answering over Knowledge Bases
This allows us to spot those facts that failed to get retrieved from the KB and generate textual queries to extract them from the textual resources in an open-domain question answering fashion.
Knowledge Base Question Answering
Open-Domain Question Answering
+1
CABACE: Injecting Character Sequence Information and Domain Knowledge for Enhanced Acronym and Long-Form Extraction
Acronyms and long-forms are commonly found in research documents, more so in documents from scientific and legal domains.
