21 |
Curlie Dataset - Language-agnostic Website Embedding and Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
22 |
Curlie Dataset - Language-agnostic Website Embedding and Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
23 |
Curlie Dataset - Language-agnostic Website Embedding and Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
24 |
Curlie Dataset - Language-agnostic Website Embedding and Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
25 |
From Examples to Rules: Neural Guided Rule Synthesis for Information Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
26 |
Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
27 |
Offensive Language Detection in Under-resourced Algerian Dialectal Arabic Language ...
|
|
|
|
BASE
|
|
Show details
|
|
29 |
Query Expansion and Entity Weighting for Query Reformulation Retrieval in Voice Assistant Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
30 |
LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback ...
|
|
|
|
BASE
|
|
Show details
|
|
31 |
Finding Inverse Document Frequency Information in BERT ...
|
|
|
|
Abstract:
For many decades, BM25 and its variants have been the dominant document retrieval approach, where their two underlying features are Term Frequency (TF) and Inverse Document Frequency (IDF). The traditional approach, however, is being rapidly replaced by Neural Ranking Models (NRMs) that can exploit semantic features. In this work, we consider BERT-based NRMs and study if IDF information is present in the NRMs. This simple question is interesting because IDF has been indispensable for the traditional lexical matching, but global features like IDF are not explicitly learned by neural language models including BERT. We adopt linear probing as the main analysis tool because typical BERT based NRMs utilize linear or inner-product based score aggregators. We analyze input embeddings, representations of all BERT layers, and the self-attention weights of CLS. By studying MS-MARCO dataset with three BERT-based models, we show that all of them contain information that is strongly dependent on IDF. ... : 5 pages ...
|
|
Keyword:
FOS Computer and information sciences; H.3.3; Information Retrieval cs.IR
|
|
URL: https://arxiv.org/abs/2202.12191 https://dx.doi.org/10.48550/arxiv.2202.12191
|
|
BASE
|
|
Hide details
|
|
32 |
Improving Word Translation via Two-Stage Contrastive Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
33 |
nigam@COLIEE-22: Legal Case Retrieval and Entailment using Cascading of Lexical and Semantic-based models ...
|
|
|
|
BASE
|
|
Show details
|
|
34 |
Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models ...
|
|
|
|
BASE
|
|
Show details
|
|
35 |
Dual Skipping Guidance for Document Retrieval with Learned Sparse Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
36 |
Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reduction ...
|
|
|
|
BASE
|
|
Show details
|
|
37 |
Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models ...
|
|
|
|
BASE
|
|
Show details
|
|
38 |
TURNER: The Uncertainty-based Retrieval Framework for Chinese NER ...
|
|
|
|
BASE
|
|
Show details
|
|
39 |
LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
40 |
A Deep Learning Approach for Repairing Missing Activity Labels in Event Logs for Process Mining ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|