Yan Song

Side-scan sonar image segmentation using Kernel-based Extreme Learning Machine

2017

Autonomous Underwater Vehicles (AUVs) are important platform for oceanographic survey. AUVs have been widely applied to many fields, such as the ocean research, oil and gas exploitation, mineral resources investigation, fishing and military. People can …

Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network

2019 · arXiv (Cornell University)

Previous cross-lingual knowledge graph (KG) alignment studies rely on entity embeddings derived only from monolingual KG structural information, which may fail at matching entities that have different facts in two KGs. In this paper, we …

Coordinated Reasoning for Cross-Lingual Knowledge Graph Alignment

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

Existing entity alignment methods mainly vary on the choices of encoding the knowledge graph, but they typically use the same decoding method, which independently chooses the local optimal match for each source entity. This decoding …

Improving Relation Extraction through Syntax-induced Pre-training with Dependency Masking

2022 · Findings of the Association for Computational Linguistics: ACL 2022

Relation extraction (RE) is an important natural language processing task that predicts the relation between two given entities, where a good understanding of the contextual information is essential to achieve an outstanding model performance. Among …

Meta Representation Learning Method for Robust Speaker Verification in Unseen Domains

2024

This paper presents a meta representation learning method for robust speaker verification (SV) in unseen domains. It is known that the existing embedding learning based SV systems may suffer from domain mismatch issues. To address …

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

2024 · arXiv (Cornell University)

In this technical report, we introduce OpenR, an open-source framework designed to integrate key components for enhancing the reasoning capabilities of large language models (LLMs). OpenR unifies data acquisition, reinforcement learning training (both online and …

Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model

2025 · arXiv (Cornell University)

Existing approaches for Large language model (LLM) detoxification generally rely on training on large-scale non-toxic or human-annotated preference data, designing prompts to instruct the LLM to generate safe content, or modifying the model parameters to …

Directional Skip-Gram: Explicitly Distinguishing Left and Right Context for Word Embeddings

2018

Yan Song, Shuming Shi, Jing Li, Haisong Zhang. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). 2018.

ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations

2020

The pre-training of text encoders normally processes text as a sequence of tokens corresponding to small text units, such as word pieces in English and characters in Chinese. It omits information carried by larger text …