b
bvoris_

Siyuan Xu

@bvoris_

PDF to Text Document Conversion Searchable Offline Libraries

Cina
Cinese, Inglese
Alcune informazioni sono riportate in lingua inglese.
Chi sono
I turn document collections into searchable, offline libraries. I cleaned, de-duplicated and indexed a 5,080-article / 9.57-million-character corpus into a single offline HTML file that opens with a double-click - no server, no internet, no subscription. I also built a compliance-document search agent over 18 regulations (845 indexed clauses), evaluated with a self-built 28-case test set. Messy input is fine: scanned PDFs, OCR noise, mixed simplified/traditional Chinese, broken page headers. Automated pipeline + human verification, with a self-check report on every order.... Continua a leggere

Competenze

b
bvoris_
Siyuan Xu
offline • 
Tempo di risposta medio: 1 ora

Consulta i miei servizi

Automazioni
I will turn your pdfs and documents into a searchable offline library
A partire da75 USD / progettoMaggiori dettagli
copia incolla
I will convert chinese scanned PDF or image tables into clean excel data
A partire da25 USD / progettoMaggiori dettagli

Portfolio

Esperienza lavorativa

Self-Employed_/ Freelancer

Document & Corpus Engineer

Self-Employed / Freelancer • Lavoratore autonomo

Oct 2026 - Present • 0 mos

Built a searchable corpus of 5,080 articles / 9.57M characters from web pages and scanned PDFs: cleaning, article-level segmentation, duplicate removal, and BM25 search. Delivered as a single 27 MB offline HTML file. Fixed two data-integrity defects found in QA: truncated article titles, and a 40,000-character cumulative text offset.

Legal Document Handling

Law • Full time

Sep 2025 - Aug 2026 • 11 mos

Worked with terminology-dense, high-precision documents in a regulated environment. Detail available on request.