홈 › Papers

PASH at TREC 2021 Deep Learning Track: Generative Enhanced Model for Multi-stage Ranking

2022-05-18 · Yixuan Qiao, Hao Chen, Jun Wang, Tuozhen Liu, Xianbin Ye, Xin Tang, Rui Fang, Peng Gao, Wenfeng Xie, Guotong Xie

This paper describes the PASH participation in TREC 2021 Deep Learning Track. In the recall stage, we adopt a scheme combining sparse and dense retrieval method. In the multi-stage ranking phase, point-wise and pair-wise ranking strategies are used one after another based on model continual pre-trained on general knowledge and document-level data. Compared to TREC 2020 Deep Learning Track, we have additionally introduced the generative model T5 to further enhance the performance.

📄 PDF Abstract BibTeX arXiv:2205.11245

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningGeneral Knowledge Retrieval

Methods 이 논문이 사용한 방법론

Gated Linear Unit A Gated Linear Unit, or GLU computes: $$ \mathrm{GLU}(a, b) = a \otimes \sigma(b) $$ It is used in natural language processing architectures, for example the Gated CNN,…

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Inverse Square Root Schedule Inverse Square Root is a learning rate schedule 1 / $\sqrt{\max\left(n, k\right)}$ where $n$ is the current training iteration and $k$ is the number of warm-up steps. This…

TREC CAsT 2019: The Conversational Assistance Track Overview

2020-03-30 · Jeffrey Dalton, Chenyan Xiong, Jamie Callan

The Conversational Assistance Track (CAsT) is a new track for TREC 2019 to facilitate Conversational Information Seeking (CIS) research and to create a large-scale reusable test collection for conversational search syste…

Conversational Search Learning-To-Rank Machine Reading Comprehension Reading Comprehension+2

New language resources for the Pashto language

2012-05-01 · LREC 2012 5 · Djamel Mostefa, Khalid Choukri, Sylvie Brunessaux, Karim Boudahmane

This paper reports on the development of new language resources for the Pashto language, a very low-resource language spoken in Afghanistan and Pakistan. In the scope of a multilingual data collection project, three larg…

Machine Translation Translation

Overview of the TREC 2023 Product Product Search Track

2023-11-14 · Daniel Campos, Surya Kallumadi, Corby Rosset, Cheng Xiang Zhai 외

This is the first year of the TREC Product search track. The focus this year was the creation of a reusable collection and evaluation of the impact of the use of metadata and multi-modal data on retrieval accuracy. This …

Retrieval

PashtoCorp: A 1.25-Billion-Word Corpus, Evaluation Suite, and Reproducible Pipeline for Low-Resource Language Development

2026-03-17 · Hanif Rahman arxiv

We present PashtoCorp, a 1.25-billion-word corpus for Pashto, a language spoken by 60 million people that remains severely underrepresented in NLP. The corpus is assembled from 39 sources spanning seven HuggingFace datas…

Reading Comprehension

Overview of the TREC 2025 RAGTIME Track

2026-02-10 · Dawn Lawrie, Sean MacAvaney, James Mayfield, Luca Soldaini 외 arxiv

The principal goal of the RAG TREC Instrument for Multilingual Evaluation (RAGTIME) track at TREC is to study report generation from multilingual source documents. The track has created a document collection containing A…

Information Retrieval