MétaCan
Menu
Back to cohort
Record W4362559515 · doi:10.3390/electronics12071692

SS-BERT: A Semantic Information Selecting Approach for Open-Domain Question Answering

2023· article· en· W4362559515 on OpenAlexaboutno aff
Xuan Fu, Jiangnan Du, Hai-Tao Zheng, Jianfeng Li, Cuiqin Hou, Qiyu Zhou, Hong‐Gee Kim

Bibliographic record

VenueElectronics · 2023
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsnot available
FundersNational Natural Science Foundation of China
KeywordsQuestion answeringComputer scienceOpen domainInformation retrievalLabrador RetrieverDomain (mathematical analysis)Precision and recallSelection (genetic algorithm)EncoderDual (grammatical number)Artificial intelligenceNatural language processingMathematicsMedicine

Abstract

fetched live from OpenAlex

Open-Domain Question Answering (Open-Domain QA) aims to answer any factoid questions from users. Recent progress in Open-Domain QA adopts the “retriever-reader” structure, which has proven effective. Retriever methods are mainly categorized as sparse retrievers and dense retrievers. In recent work, the dense retriever showed a stronger semantic interpretation than the sparse retriever. When training a dual-encoder dense retriever for document retrieval and reranking, there are two challenges: negative selection and a lack of training data. In this study, we make three major contributions to this topic: negative selection by query generation, data augmentation from negatives, and a passage evaluation method. We prove that the model performs better by focusing on false negatives and data augmentation in the Open-Domain QA passage rerank task. Our model outperforms other single dual-encoder rerankers over BERT-base and BM25 by 0.7 in MRR@10, achieving the highest Recall@50 and the max Recall@1000, which is restricted by the BM25 retrieval results.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.903
Threshold uncertainty score0.466

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.019
GPT teacher head0.275
Teacher spread0.255 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations3
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueElectronicsSame topicTopic ModelingFrench-language works237,207