Tagged articles
machine reading comprehension
13 articles · Page 1 of 1
The X-STA algorithm, introduced by Alibaba Cloud’s PAI and researchers from South China University of Technology, leverages gradient‑decomposed knowledge sharing, teacher‑guided attention, and multi‑level alignment to enhance cross‑lingual machine reading comprehension, achieving state‑of‑the‑art results on three multilingual MRC benchmarks.
X-STAcross-lingualknowledge transfer
0 likes · 7 min read

This article reviews the evolution of machine question answering, from early feature‑engineered systems to modern large‑language‑model‑driven retrieval‑augmented generation, outlines Baidu Search’s current Retriever‑Reader architecture, discusses challenges such as semantic complexity, latency and answer quality, and presents solutions including hierarchical DocMRC modeling, multi‑teacher knowledge distillation, and instruction decomposition for efficient, high‑quality answers.
BaiduRetrieval-Augmented Generationknowledge distillation
0 likes · 18 min read

KECP, a Knowledge‑Enhanced Contrastive Prompt‑tuning model, achieves strong few‑shot extractive question answering by converting questions to masked statements, injecting external knowledge via gated fusion, and leveraging contrastive learning alongside masked language modeling, as demonstrated on EMNLP‑2022 benchmarks.
Contrastive LearningNLPknowledge injection
0 likes · 9 min read

The paper reviews classic summarization models, then proposes DSMRC‑S, a span-level extractive dialogue summarization method using distant supervision and a machine‑reading‑comprehension framework, with token‑level labeling and density‑based span selection, achieving state‑of‑the‑art BLEU and ROUGE improvements on a large Meituan dialogue dataset.
BERTDialogue Summarizationmachine reading comprehension
0 likes · 33 min read

This article presents the architecture, techniques, and practical solutions behind intelligent question answering in QQ Browser's search engine, covering knowledge‑graph based QA (KBQA), machine‑reading‑comprehension QA (DeepQA), and information‑retrieval QA (IRQA), and discusses system design, model optimization, and future directions.
AIinformation retrievalknowledge graph
0 likes · 23 min read

This talk explores how multimodal AI, knowledge‑graph‑enhanced script generation, and advanced reading‑comprehension techniques enable virtual anchors to transform e‑commerce live streaming from simple Q&A bots into interactive, content‑rich live broadcasts, addressing challenges of material sourcing, personalization, and low‑latency response.
LiveQAcontent generatione-commerce live streaming
0 likes · 19 min read


AntTechApr 13, 2021 · Artificial Intelligence
The ZhiXiaoBao technical team at Ant Financial broke the SQuAD 2.0 leaderboard with a model that surpasses human performance, detailing the challenges of natural‑language understanding, the specific ranking and data‑augmentation techniques they employed, and the broader impact on fintech knowledge‑base automation and future AI research.
SQuAD 2.0fintechknowledge base
0 likes · 9 min read

This presentation by Baidu senior R&D engineer Wang Quan outlines the evolution, architecture, and recent breakthroughs of Baidu's knowledge graph, covering universal, event, video, and industry-specific graphs, key technologies such as open knowledge mining, self‑learning, multi‑source fusion, and their applications in search, recommendation, dialogue, and intelligent services.
Event Extractionartificial intelligenceindustry applications
0 likes · 22 min read

This article describes Meituan's intelligent question answering system, detailing its three core capabilities—Document QA, Community QA, and Knowledge‑Graph QA—along with the underlying machine‑reading comprehension models, multi‑task learning, answer ranking, and real‑world deployment scenarios across travel, hotel, and retail services.
MeituanNLPQuestion Answering
0 likes · 22 min read

Alibaba’s AI team introduced a multi‑stage, document‑ranking and paragraph‑ranking system built on an Enriched BERT model that topped the MS MARCO reading‑comprehension leaderboard, surpassing previous state‑of‑the‑art methods and even human performance on open‑domain QA tasks.
Alibaba AIEnriched BERTOpen Domain QA
0 likes · 5 min read

The article presents an in‑depth overview of Alibaba's intelligent service bot Ali Xiaomì, covering its platform evolution, core NLP techniques such as intent recognition and machine reading comprehension, multi‑turn recommendation strategies, transfer‑learning approaches across domains and languages, and future technical challenges.
AIReinforcement Learningmachine reading comprehension
0 likes · 11 min read

This article reviews the background of Alibaba's XiaoMi chatbot, explores how machine reading comprehension can be applied to e‑commerce scenarios such as rule interpretation and product inquiries, surveys key datasets and SQuAD‑based models, and discusses practical challenges and solutions for deploying these technologies in real‑world business environments.
AIAlibabadeep learning
0 likes · 18 min read

Alibaba’s AI assistant “Ali Xiaomì” is exploring machine reading comprehension to automatically understand e‑commerce rules and product information, leveraging deep learning models and datasets such as SQuAD, bAbI, and MCTest, while addressing challenges of long texts, answer granularity, and real‑world deployment.
Question Answeringdeep learninge‑commerce AI
0 likes · 18 min read
