Papers by Siyu Tao

6 papers
ContextBLIP: Doubly Contextual Alignment for Contrastive Image Retrieval from Linguistically Complex Descriptions (2024.findings-acl)

Copied to clipboard

Challenge: Existing approaches to image retrieval from contextual descriptions (IRCD) lag behind human performance in IRCD.
Approach: They propose a method that relies on a doubly contextual alignment scheme for challenging IRCD.
Outcome: The proposed method can yield comparable results with GPT-4V, despite fewer parameters.
Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning (D19-1)

Copied to clipboard

Challenge: Existing studies on video captioning focus on the association relationships between multiple modalities.
Approach: They propose a video captioning model with high-order cross-modal attention (HOCA) they propose low-rank HOCA which adopts tensor decomposition to reduce the space requirement .
Outcome: The proposed model captures cross-modal interaction of different modalities and reduces space requirement.
Dual Low-Rank Multimodal Fusion (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing tensor-based fusion methods make poor use of fine-grained temporal dynamics of multimodal sequential features.
Approach: They propose a novel multimodal fusion method called Fine-Grained Temporal Low-Rank Multimodal Fusion that uses low-rank tensor approximation along dual dimensions of input features.
Outcome: The proposed method outperforms the state-of-the-art tensor-based methods with a similar computational complexity.
Synonym Knowledge Enhanced Reader for Chinese Idiom Reading Comprehension (2020.coling-main)

Copied to clipboard

Challenge: Experimental results show that our model achieves state-of-the-art performance for Chinese idiom comprehension.
Approach: They propose a model that can mitigate the inconsistency between literal and literal meanings by incorporating the synonym knowledge enhanced reader into the model.
Outcome: The proposed model achieves state-of-the-art on a Chinese idiom reading comprehension dataset.
More frequent verbs are associated with more diverse valency frames: Efficient principles at the lexicon-grammar interface (2024.acl-long)

Copied to clipboard

Challenge: Existing evidence has focused on word-internal properties, such as Zipf's observation that more frequent words are optimized in form to minimize communicative cost.
Approach: They propose to examine the hypothesis that efficient lexicon organization is also reflected in valency, or the combinations and orders of additional words and phrases a verb selects for in a sentence.
Outcome: The proposed hypothesis is consistent with communicative efficiency principles.
ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use (2025.acl-long)

Copied to clipboard

Challenge: Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models.
Approach: They propose a dataset that provides rigorous evaluation of multi-hop tool use.
Outcome: The proposed model achieves 49.04% accuracy across five model families.

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