paper-with-me

홈 › Papers

Socialformer: Social Network Inspired Long Document Modeling for Document Ranking

2022-02-22 · Yujia Zhou, Zhicheng Dou, Huaying Yuan, Zhengyi Ma

Utilizing pre-trained language models has achieved great success for neural document ranking. Limited by the computational and memory requirements, long document modeling becomes a critical issue. Recent works propose to modify the full attention matrix in Transformer by designing sparse attention patterns. However, most of them only focus on local connections of terms within a fixed-size window. How to build suitable remote connections between terms to better model document representation remains underexplored. In this paper, we propose the model Socialformer, which introduces the characteristics of social networks into designing sparse attention patterns for long document modeling in document ranking. Specifically, we consider several attention patterns to construct a graph like social networks. Endowed with the characteristic of social networks, most pairs of nodes in such a graph can reach with a short path while ensuring the sparsity. To facilitate efficient calculation, we segment the graph into multiple subgraphs to simulate friend circles in social scenarios. Experimental results confirm the effectiveness of our model on long document modeling.

📄 PDF Abstract BibTeX arXiv:2202.10870

Code (1)

smallporridge/socialformer 공식 구현 pytorch

Tasks

Document Ranking

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
Adam 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

SocialFormer: Social Interaction Modeling with Edge-enhanced Heterogeneous Graph Transformers for Trajectory Prediction

2024-05-06 · Zixu Wang, Zhigang Sun, Juergen Luettin, Lavdim Halilaj

Accurate trajectory prediction is crucial for ensuring safe and efficient autonomous driving. However, most existing methods overlook complex interactions between traffic participants that often govern their future traje…

Autonomous DrivingGraph Neural NetworkPredictionTrajectory Prediction

Improving Topic Relevance Model by Mix-structured Summarization and LLM-based Data Augmentation

2024-04-03 · Yizhu Liu, Ran Tao, Shengyu Guo, Yifan Yang

Topic relevance between query and document is a very important part of social search, which can evaluate the degree of matching between document and user's requirement. In most social search scenarios such as Dianping, m…

Data AugmentationLanguage ModelingLanguage ModellingLarge Language Model

Computer-Assisted Text Analysis for Social Science: Topic Models and Beyond

2018-03-29 · Ryan Wesslen

Topic models are a family of statistical-based algorithms to summarize, explore and index large collections of text documents. After a decade of research led by computer scientists, topic models have spread to social sci…

Causal InferenceTopic Models

Human Language Modeling

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Natural language is generated by people, yet traditional language modeling views words or documents as if generated independently. Here, we propose human language modeling (HuLM), a hierarchical extension to the languag…

Language ModelingLanguage Modelling

Human Language Modeling

2022-05-10 · Findings (ACL) 2022 5 · Nikita Soni, Matthew Matero, Niranjan Balasubramanian, H. Andrew Schwartz

Natural language is generated by people, yet traditional language modeling views words or documents as if generated independently. Here, we propose human language modeling (HuLM), a hierarchical extension to the language…

Age EstimationLanguage ModelingLanguage ModellingSentiment Analysis+2