Library

Subject
Tags

107,780 matches · Natural Language Processing Techniques

#
001Wikidata and LiLa for Latin: Enabling Interoperability and Access to Inflected Forms and Corpus AttestationsOpenAlexPaperLindemann, David, Pellegrini, Matteo et al.Dec 5
002pal2invOpenAlexPaperANONYMOUS, ANONYMOUSNov 24
003pal2invOpenAlexPaperANONYMOUS, ANONYMOUSNov 23
004Multi-dimensional hierarchical temporal alignment for improved temporal commonsense reasoning in large language modelsOpenAlexPaperGe Yan, Hai-Tao Yu et al.Nov 1
005Corpus Approaches to Parallel ConcordancingOpenAlexPaperLaura M. Hartwell, Cécile Frérot et al.Oct 15
006Parallel Concordancing: a phraseological approach.OpenAlexPaperLaura M. Hartwell, Cécile Frérot et al.Oct 15
007A Framework for the Automation of Preference GrammarOpenAlexPaperC.U.C. Ugorji, Ginikachi Maduako et al.4 days ago
008Building a Transformer-Based Neural Machine Translation System for English–Kibajuni Translation: A Low-Resource Deep Learning Approach for Indigenous Language PreservationOpenAlexPaperAnwar H. Ahmed, Wahida M. Bana et al.4 days ago
009Hallucinations in Structured Extraction: A Case Study on Prompt-Based Semantic Role LabelingOpenAlexPaperIoannis Kazlaris, Konstantinos Diamantaras et al.4 days ago
010HyperToken: Script-Aware, Nukta-Preserving Tokenization for Low-Resource Indic LanguagesOpenAlexPaperPrashant ARYA4 days ago
011HyperToken: Script-Aware, Nukta-Preserving Tokenization for Low-Resource Indic LanguagesOpenAlexPaperPrashant ARYA4 days ago
012Introduction aux diagrammes HCP et à MakingHCPChartSkill (archived 2026-07-27)OpenAlexPaperGo Komura4 days ago
013Introduction aux diagrammes HCP et à MakingHCPChartSkill (archived 2026-07-27)OpenAlexPaperGo Komura4 days ago
014LuisCore — Recursive Cognition InfrastructureOpenAlexPaperLuisCore Project4 days ago
015LuisCore — Recursive Cognition InfrastructureOpenAlexPaperLuisCore Project4 days ago
016PAP_NER: A large-scale vietnamese administrative named entity recognition corpus and hybrid deep learning architectureOpenAlexPaperDinh-Dien La, Tien-Bang Tran et al.4 days ago
017Prompting Rules That Reduce Codex Mojibake Accidents on Windows (archived 2026-07-27)OpenAlexPaperGo Komura4 days ago
018Prompting Rules That Reduce Codex Mojibake Accidents on Windows (archived 2026-07-27)OpenAlexPaperGo Komura4 days ago
019The Genealogy of Large Language Models: From Auxiliary Tools in ASR to Foundational Transformers and Back AgainOpenAlexPaperJosé Luciano Maldonado4 days ago
020[Draft sections of Maidu grammar]OpenAlexPaperHans Jørgen Uldall4 days ago
021[Wintu vocabulary]OpenAlexPaperJohn Peabody Harrington4 days ago
022سحر لغة Ada ── لغة تعبر عن التصميم بالأنواع، وتدعم برمجيات تعمل لعقود (archived 2026-07-27)OpenAlexPaperGo Komura4 days ago
023سحر لغة Ada ── لغة تعبر عن التصميم بالأنواع، وتدعم برمجيات تعمل لعقود (archived 2026-07-27)OpenAlexPaperGo Komura4 days ago
024Ada言語の魅力 ── 型で設計を語り、数十年動き続けるソフトウェアを支える言語 (archived 2026-07-26)OpenAlexPaperGo Komura5 days ago
025Ada言語の魅力 ── 型で設計を語り、数十年動き続けるソフトウェアを支える言語 (archived 2026-07-26)OpenAlexPaperGo Komura5 days ago
026CDCE Predictions for AGI Architecture: Hyperon as a Test CaseOpenAlexPaperClark5 days ago
027CDCE Predictions for AGI Architecture: Hyperon as a Test CaseOpenAlexPaperClark5 days ago
028CDCE Predictions for AGI Architecture: Hyperon as a Test CaseOpenAlexPaperClark5 days ago
029Curriculum Learning and Data-Efficient Pretraining: A Technical NoteOpenAlexPaperDheiver Francisco Santos5 days ago
030Curriculum Learning and Data-Efficient Pretraining: A Technical NoteOpenAlexPaperDheiver Francisco Santos5 days ago
031LuisCore — Recursive Cognition InfrastructureOpenAlexPaperLuisCore Project5 days ago
032Measure before you rewrite: ablation-driven redesign of LLM-facing RDF schema documentation in TogoMCPOpenAlexPaperAkira R. Kinjo, Yasunori Yamamoto5 days ago
033Model Merging for Capability Composition: A Technical NoteOpenAlexPaperDheiver Francisco Santos5 days ago
034Model Merging for Capability Composition: A Technical NoteOpenAlexPaperDheiver Francisco Santos5 days ago
035Parameter-Efficient Fine-Tuning: LoRA, QLoRA, and DoRAOpenAlexPaperDheiver Francisco Santos5 days ago
036Parameter-Efficient Fine-Tuning: LoRA, QLoRA, and DoRAOpenAlexPaperDheiver Francisco Santos5 days ago
037Reinforcement Learning with Verifiable Rewards (RLVR) and GRPO for ReasoningOpenAlexPaperDheiver Francisco Santos5 days ago
038Reinforcement Learning with Verifiable Rewards (RLVR) and GRPO for ReasoningOpenAlexPaperDheiver Francisco Santos5 days ago
039SPARKによる形式検証入門 ── Adaの契約から数学的証明へ (archived 2026-07-26)OpenAlexPaperGo Komura5 days ago
040SPARKによる形式検証入門 ── Adaの契約から数学的証明へ (archived 2026-07-26)OpenAlexPaperGo Komura5 days ago
041Synthetic Data Generation and Self-Improvement: A Technical NoteOpenAlexPaperDheiver Francisco Santos5 days ago
042Synthetic Data Generation and Self-Improvement: A Technical NoteOpenAlexPaperDheiver Francisco Santos5 days ago
043Transactional Shifted-Fibonacci Normalization: A Decreasing Potential, Local Parallel Scheduling, and a Counter-Native BridgeOpenAlexPaperMarco Oppido5 days ago
044Routing Through Refusal—A Routing-Integrity Reanalysis of SORRY-Bench: Contextual Contamination, Rater Feasibility, and the Engineerability of Safety-Routing FailureOpenAlexPaperE. Katz6 days ago
045Routing Through Refusal—A Routing-Integrity Reanalysis of SORRY-Bench: Contextual Contamination, Rater Feasibility, and the Engineerability of Safety-Routing FailureOpenAlexPaperE. Katz6 days ago
046Word Order as Definiteness Cues in Polish-English NMT: towards a construal grammar.OpenAlexPaperLucia E. Donatelli, P.K. (Pawel) Oczkowski6 days ago
047A survey of gender bias mitigation in neural machine translationOpenAlexPaperNeha Gajakos, Christopher Staff et al.7 days ago
048AI-Based Technique for Language: Breaking Communication BarriersOpenAlexPaperRajaboina Rashwitha, Mrs. D. Srilatha et al.7 days ago
049Agents ingesting contracts, invoices and filings need nested JSON matching a caller-supplied schema, but 2026 extraction benchmarks report frontier models achieving five-percent field-level pass rates on complex nested documents, because repeated arrays must be row-aligned and an absent field is indistinguishable from an invented one. A naive single prompt with schema-constrained decoding guarantees syntactically valid JSON, not correct JSON: it silently fabricates plausible values for missing fields and emits no per-field trust signal, so callers ingest hallucinations. Evaluate a vision-language extractor combining page-level retrieval, per-field self-consistency across repeated re-reads and layout crops, logprob-and-agreement confidence fusion, mandatory source-span grounding with page and bounding-box coordinates, an explicit not_present sentinel, and arithmetic cross-checks on totals. Measure field-level precision, recall and F1, hallucination rate on deliberately absent fields, span-grounding accuracy and risk-coverage AUROC of the confidence, against a hand-labeled gold set of nested documents with injected omissions, beating a naive base-model prompt, constrained-decoding-only extraction, and a commercial OCR pipeline. Deliver as the prototype a minimal runnable Python MCP server (stdio) exposing the priced AI tool extract_schema_with_abstention that invokes a language or ML model to produce its output, with a typed input/output schema, an x402-style pay-per-call metering stub that records a per-call price in USDT and emits a settlement receipt, and one smoke test that exercises the tool end to end.OpenAlexPaperDogukan Ali Gundogan7 days ago
050Agents ingesting contracts, invoices and filings need nested JSON matching a caller-supplied schema, but 2026 extraction benchmarks report frontier models achieving five-percent field-level pass rates on complex nested documents, because repeated arrays must be row-aligned and an absent field is indistinguishable from an invented one. A naive single prompt with schema-constrained decoding guarantees syntactically valid JSON, not correct JSON: it silently fabricates plausible values for missing fields and emits no per-field trust signal, so callers ingest hallucinations. Evaluate a vision-language extractor combining page-level retrieval, per-field self-consistency across repeated re-reads and layout crops, logprob-and-agreement confidence fusion, mandatory source-span grounding with page and bounding-box coordinates, an explicit not_present sentinel, and arithmetic cross-checks on totals. Measure field-level precision, recall and F1, hallucination rate on deliberately absent fields, span-grounding accuracy and risk-coverage AUROC of the confidence, against a hand-labeled gold set of nested documents with injected omissions, beating a naive base-model prompt, constrained-decoding-only extraction, and a commercial OCR pipeline. Deliver as the prototype a minimal runnable Python MCP server (stdio) exposing the priced AI tool extract_schema_with_abstention that invokes a language or ML model to produce its output, with a typed input/output schema, an x402-style pay-per-call metering stub that records a per-call price in USDT and emits a settlement receipt, and one smoke test that exercises the tool end to end.OpenAlexPaperDogukan Ali Gundogan7 days ago
051Averroes-Q: Training a 32-Billion Parameter Bilingual Arabic-English LLM on a Single Apple M2 Ultra WorkstationOpenAlexPaperYahya Saqban7 days ago
052Averroes-Q: Training a 32-Billion Parameter Bilingual Arabic-English LLM on a Single Apple M2 Ultra WorkstationOpenAlexPaperYahya Saqban7 days ago
053Enhancing Chinese-to-English legal translation by generative artificial intelligence: a corpus-informed prompt engineering approachOpenAlexPaperYingyi Zhuang, Q Y Liu7 days ago
054Explorations in the distributional semantics of Mandarin two-character compoundsOpenAlexPaperTian Shen, Harald Baayen7 days ago
055Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and ProspectsOpenAlexPaperYuheng Cheng, Ceyao Zhang et al.7 days ago
056HNC Grand Unified v4 Fixed Leckey 2026OpenAlexPaperGary Leckey7 days ago
057HNC Grand Unified v4 Fixed Leckey 2026OpenAlexPaperGary Leckey7 days ago
058Hayula Gateway: A Unified OpenAI-Compatible API Layer for Multi-Model Local InferenceOpenAlexPaperYahya Saqban7 days ago
059Hayula Gateway: A Unified OpenAI-Compatible API Layer for Multi-Model Local InferenceOpenAlexPaperYahya Saqban7 days ago
060I/o for LLM inference: a survey of storage and memory bottlenecksOpenAlexPaperRajarshi Chowdhury7 days ago

Showing 60 of 107,780 documents · scroll for more