Yangqiu Song

Efficient Path Prediction for Semi-Supervised and Weakly Supervised Hierarchical Text Classification

2019

Hierarchical text classification has many real-world applications. However, labeling a large number of documents is costly. In practice, we can use semi-supervised learning or weakly supervised learning (e.g., dataless classification) to reduce the labeling cost. …

Understanding Hidden Memories of Recurrent Neural Networks

2017

Recurrent neural networks (RNNs) have been successfully applied to various natural language processing (NLP) tasks and achieved better results than conventional methods. However, the lack of understanding of the mechanisms behind their effectiveness limits further …

Exploiting Semantic Relations for Fine-grained Entity Typing

2020 · Rare & Special e-Zone (The Hong Kong University of Science and Technology)

Fine-grained entity typing results can serve as important information for entities while constructing knowledge bases. It is a challenging task due to the use of large tag sets and the requirement of understanding the context. …

Analogous Process Structure Induction for Sub-event Sequence Prediction

2020 · arXiv (Cornell University)

Computational and cognitive studies of event understanding suggest that identifying, comprehending, and predicting events depend on having structured representations of a sequence of events and on conceptualizing (abstracting) its components into (soft) event categories. Thus, …

Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model

2021

Hongliang Dai, Yangqiu Song, Haixun Wang. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs

2021 · arXiv (Cornell University)

Complex Query Answering (CQA) is an important reasoning task on knowledge graphs. Current CQA learning models have been shown to be able to generalize from atomic operators to more complex formulas, which can be regarded …

Knowledge Graph Reasoning over Entities and Numerical Values

2023

A complex logic query in a knowledge graph refers to a query expressed in logic form that conveys a complex meaning, such as where did the Canadian Turing award winner graduate from? Knowledge graph reasoning-based …

AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph

2023 · arXiv (Cornell University)

Cognitive research indicates that abstraction ability is essential in human intelligence, which remains under-explored in language models. In this paper, we present AbsPyramid, a unified entailment graph of 221K textual descriptions of abstraction knowledge. While …

AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation

2024 · arXiv (Cornell University)

Abstraction ability is crucial in human intelligence, which can also benefit various tasks in NLP study. Existing work shows that LLMs are deficient in abstract ability, and how to improve it remains unexplored. In this …

CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning

2024

Weiqi Wang, Tianqing Fang, Chunyang Li, Haochen Shi, Wenxuan Ding, Baixuan Xu, Zhaowei Wang, Jiaxin Bai, Xin Liu, Cheng Jiayang, Chunkit Chan, Yangqiu Song. Proceedings of the 62nd Annual Meeting of the Association for Computational …

KBQA

2017 · Proceedings of the VLDB Endowment

Question answering (QA) has become a popular way for humans to access billion-scale knowledge bases. Unlike web search, QA over a knowledge base gives out accurate and concise results, provided that natural language questions can …

Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks

2017

Heterogeneous Information Network (HIN) is a natural and general representation of data in modern large commercial recommender systems which involve heterogeneous types of data. HIN based recommenders face two problems: how to represent the high-level …

Joint Embeddings of Chinese Words, Characters, and Fine-grained Subcharacter Components

2017

Word embeddings have attracted much attention recently. Different from alphabetic writing systems, Chinese characters are often composed of subcharacter components which are also semantically informative. In this work, we propose an approach to jointly embed …