1 |
Cross-media Scientific Research Achievements Query based on Ranking Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Exploring Sub-skeleton Trajectories for Interpretable Recognition of Sign Language ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Cross-Lingual Query-Based Summarization of Crisis-Related Social Media: An Abstractive Approach Using Transformers ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Simplifying Multilingual News Clustering Through Projection From a Shared Space ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Towards Best Practices for Training Multilingual Dense Retrieval Models ...
|
|
|
|
Abstract:
Dense retrieval models using a transformer-based bi-encoder design have emerged as an active area of research. In this work, we focus on the task of monolingual retrieval in a variety of typologically diverse languages using one such design. Although recent work with multilingual transformers demonstrates that they exhibit strong cross-lingual generalization capabilities, there remain many open research questions, which we tackle here. Our study is organized as a "best practices" guide for training multilingual dense retrieval models, broken down into three main scenarios: where a multilingual transformer is available, but relevance judgments are not available in the language of interest; where both models and training data are available; and, where training data are available not but models. In considering these scenarios, we gain a better understanding of the role of multi-stage fine-tuning, the strength of cross-lingual transfer under various conditions, the usefulness of out-of-language data, and the ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Information Retrieval cs.IR
|
|
URL: https://arxiv.org/abs/2204.02363 https://dx.doi.org/10.48550/arxiv.2204.02363
|
|
BASE
|
|
Hide details
|
|
6 |
Addressing Issues of Cross-Linguality in Open-Retrieval Question Answering Systems For Emergent Domains ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
QALD-9-plus: A Multilingual Dataset for Question Answering over DBpedia and Wikidata Translated by Native Speakers ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Dataset ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
From Examples to Rules: Neural Guided Rule Synthesis for Information Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Offensive Language Detection in Under-resourced Algerian Dialectal Arabic Language ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Query Expansion and Entity Weighting for Query Reformulation Retrieval in Voice Assistant Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Improving Word Translation via Two-Stage Contrastive Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
nigam@COLIEE-22: Legal Case Retrieval and Entailment using Cascading of Lexical and Semantic-based models ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|