Search Results for author: Mingyang Song

Found 12 papers, 6 papers with code

Counting-Stars: A Simple, Efficient, and Reasonable Strategy for Evaluating Long-Context Large Language Models

1 code implementation18 Mar 2024 Mingyang Song, Mao Zheng, Xuan Luo

While recent research endeavors have concentrated on developing Large Language Models (LLMs) with robust long-context capabilities, due to the lack of appropriate evaluation strategies, relatively little is known about how well the long-context capability and performance of leading LLMs (e. g., GPT-4 Turbo and Kimi Chat).

Large Language Models as Zero-Shot Keyphrase Extractors: A Preliminary Empirical Study

1 code implementation23 Dec 2023 Mingyang Song, Xuelian Geng, Songfang Yao, Shilong Lu, Yi Feng, Liping Jing

Zero-shot keyphrase extraction aims to build a keyphrase extractor without training by human-annotated data, which is challenging due to the limited human intervention involved.

Keyphrase Extraction Language Modelling +1

Revitalizing Legacy Video Content: Deinterlacing with Bidirectional Information Propagation

no code implementations30 Oct 2023 Zhaowei Gao, Mingyang Song, Christopher Schroers, Yang Zhang

Our proposed method supports bidirectional spatio-temporal information propagation across multiple scales to leverage information in both space and time.

Recognizable Information Bottleneck

1 code implementation28 Apr 2023 Yilin Lyu, Xin Liu, Mingyang Song, Xinyue Wang, Yaxin Peng, Tieyong Zeng, Liping Jing

The recent PAC-Bayes IB uses information complexity instead of information compression to establish a connection with the mutual information generalization bound.

A Generative Model for Digital Camera Noise Synthesis

no code implementations16 Mar 2023 Mingyang Song, Yang Zhang, Tunç O. Aydın, Elham Amin Mansour, Christopher Schroers

To this end, we propose an effective generative model which utilizes clean features as guidance followed by noise injections into the network.

Hyperbolic Relevance Matching for Neural Keyphrase Extraction

1 code implementation NAACL 2022 Mingyang Song, Yi Feng, Liping Jing

Meanwhile, considering the hierarchical structure hidden in the document, HyperMatch embeds both phrases and documents in the same hyperbolic space via a hyperbolic phrase encoder and a hyperbolic document encoder.

Information Retrieval Keyphrase Extraction +2

Topic-Aware Encoding for Extractive Summarization

no code implementations17 Dec 2021 Mingyang Song, Liping Jing

Specifically, a neural topic model is added in the neural-based sentence-level representation learning to adequately consider the central topic information for capturing the critical content in the original document.

Document Summarization Extractive Summarization +2

Reinforcing Semantic-Symmetry for Document Summarization

no code implementations14 Dec 2021 Mingyang Song, Liping Jing

Among them, the extractor identifies the salient sentences from the input document, and the abstractor generates a summary from the salient sentences.

Document Summarization reinforcement-learning +3

Reinforced Abstractive Summarization with Adaptive Length Controlling

no code implementations14 Dec 2021 Mingyang Song, Yi Feng, Liping Jing

Document summarization, as a fundamental task in natural language generation, aims to generate a short and coherent summary for a given document.

Abstractive Text Summarization Document Summarization +3

Importance Estimation from Multiple Perspectives for Keyphrase Extraction

no code implementations EMNLP 2021 Mingyang Song, Liping Jing, Lin Xiao

Keyphrase extraction is a fundamental task in Natural Language Processing, which usually contains two main parts: candidate keyphrase extraction and keyphrase importance estimation.

Chunking Keyphrase Extraction +1

Does Head Label Help for Long-Tailed Multi-Label Text Classification

1 code implementation24 Jan 2021 Lin Xiao, Xiangliang Zhang, Liping Jing, Chi Huang, Mingyang Song

To address the challenge of insufficient training data on tail label classification, we propose a Head-to-Tail Network (HTTN) to transfer the meta-knowledge from the data-rich head labels to data-poor tail labels.

General Classification Multi Label Text Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.