paper-with-me

Papers

CEDR: Contextualized Embeddings for Document Ranking

2019-04-15 · Sean MacAvaney, Andrew Yates, Arman Cohan, Nazli Goharian

Although considerable attention has been given to neural ranking architectures recently, far less attention has been paid to the term representations that are used as input to these models. In this work, we investigate how two pretrained contextualized language models (ELMo and BERT) can be utilized for ad-hoc document ranking. Through experiments on TREC benchmarks, we find that several existing neural ranking architectures can benefit from the additional context provided by contextualized language models. Furthermore, we propose a joint approach that incorporates BERT's classification vector into existing neural models and show that it outperforms state-of-the-art ad-hoc ranking baselines. We call this joint approach CEDR (Contextualized Embeddings for Document Ranking). We also address practical challenges in using these models for ranking, including the maximum input length imposed by BERT and runtime performance impacts of contextualized language models.

📄 PDF Abstract BibTeX arXiv:1904.07094

Code (7)

Georgetown-IR-Lab/cedr 공식 구현 pytorch
Georgetown-IR-Lab/contextualized-reps-for-ranking 공식 구현 pytorch
Crysitna/CEDR_tpu pytorch
Georgetown-IR-Lab/curricula-neural-ir
TikaToka/CapstoneSpring pytorch
crystina-z/CEDR_tpu pytorch
ssun32/clirmatrix_cedr pytorch

Tasks

Ad-Hoc Information RetrievalDocument RankingGeneral Classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
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…
Adam 설명 없음

Similar Papers 제목 키워드 기반

RepBERT: Contextualized Text Embeddings for First-Stage Retrieval

2020-06-28 · Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Min Zhang 외

Although exact term match between queries and documents is the dominant method to perform first-stage retrieval, we propose a different approach, called RepBERT, to represent documents and queries with fixed-length conte…

Passage RankingRetrieval

Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits

2021-02-12 · Leonid Boytsov, Zico Kolter

We study the utility of the lexical translation model (IBM Model 1) for English text retrieval, in particular, its neural variants that are trained end-to-end. We use the neural Model1 as an aggregator layer applied to c…

CPUDocument RankingInformation RetrievalRetrieval+2

Topic Aware Contextualized Embeddings for High Quality Phrase Extraction

2022-01-17 · Venktesh V, Mukesh Mohania, Vikram Goyal

Keyphrase extraction from a given document is the task of automatically extracting salient phrases that best describe the document. This paper proposes a novel unsupervised graph-based ranking method to extract high-qual…

Keyphrase ExtractionVocal Bursts Intensity Prediction

CEQE: Contextualized Embeddings for Query Expansion

2021-03-09 · Shahrzad Naseri, Jeffrey Dalton, Andrew Yates, James Allan

In this work we leverage recent advances in context-sensitive language models to improve the task of query expansion. Contextualized word representation models, such as ELMo and BERT, are rapidly replacing static embeddi…

RerankingRe-RankingRetrieval

CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling

2023-05-16 · Zheng Fang, Yulan He, Rob Procter

Most existing topic models rely on bag-of-words (BOW) representation, which limits their ability to capture word order information and leads to challenges with out-of-vocabulary (OOV) words in new documents. Contextualiz…

Document ClassificationLanguage ModellingNatural Language UnderstandingNER+3