This article examines how reinforcement‑learning techniques such as PPO, DPO, and GRPO are integrated into the Baixiaosheng QA system to improve answer stability, deepen domain knowledge understanding, and accelerate response generation, and it evaluates the impact of Reinforcement Fine‑Tuning (RFT) on real‑world performance.
The ICDAR 2023 BDVT-QA competition, organized by Alibaba DAMO Academy, introduces a novel dataset of 1,000 born‑digital video clips for end‑to‑end video text recognition and video text question answering, offering cash prizes, detailed dataset access, and a lineup of leading academic and industry experts.
This presentation details the XiaoAi intelligent assistant’s QA system, covering its application scenarios, information extraction techniques (including relation and event extraction with SPO/PSO models), graph‑based question answering methods, cross‑domain slot extraction, path retrieval, and practical Q&A insights.
This article presents an in‑depth overview of intelligent question answering in QQ Browser search, covering its background, the core KBQA and DeepQA technologies, system architecture, challenges, recent advances such as end‑to‑end, knowledge‑guided and multimodal QA, and practical Q&A for deployment.
This article presents a comprehensive overview of temporal knowledge graphs, outlines the challenges of building question‑answering systems over them, introduces the TSQA method with its three‑step pipeline for time‑sensitive reasoning, and reports experimental results showing significant improvements on complex queries.
This article introduces the intelligent question‑answering technology used in WeChat Search, covering background, knowledge‑graph‑based QA, document‑based QA, technical pipelines, key modules such as entity linking and relation recognition, and future research directions.
This article presents a comprehensive overview of Xiaomi's Xiao AI intelligent QA system, detailing its background, three core answering modules—knowledge‑graph QA, retrieval‑based FAQ, and reading‑comprehension—and the underlying methods such as template matching, cross‑domain semantic parsing, path‑based reasoning, semantic retrieval, and neural matching, while also discussing performance results and practical trade‑offs.
Meituan’s knowledge‑based question answering system tackles diverse, constraint‑rich, multi‑hop queries across pre‑sale, in‑sale and post‑sale scenarios by integrating fine‑grained query understanding, relation recognition, sub‑graph retrieval and answer ranking, employing optimized BERT models, pre‑training tasks, and domain‑specific enhancements to boost response speed, conversion rates, and benchmark performance, while acknowledging remaining challenges in long‑tail and complex queries.
The CCKS 2021 Life Service Domain Knowledge Graph QA competition challenges participants to build Chinese question‑answering systems that retrieve factual answers from a combined OpenKG and Meituan life‑service graph, covering tasks such as entity recognition, relation extraction and semantic parsing, with registration May‑July, cash prizes up to ¥20 000 and internship offers for top student teams.
This article details the design, iterative development, and performance optimizations of 58's AI‑driven intelligent Q&A chatbot, covering its overall three‑layer architecture, the QABot, TaskBot, and answer‑recommendation modules, as well as dynamic strategy adjustment, caching mechanisms, and real‑world deployment results.
The CKBQA task introduced at CCKS2021 challenges participants to build Chinese knowledge‑graph question answering systems that combine Meituan’s life‑services KG with open‑domain data from PKUBASE, requiring accurate, efficient and explainable handling of both domain‑specific and open‑domain queries to advance real‑world applications such as smart customer service and e‑commerce.
This article introduces the typical applications of intelligent question answering, compares chat‑type, knowledge‑type and task‑type bots, and then details the end‑to‑end architecture, knowledge‑base construction, semantic‑equivalence modeling with BERT‑BIMPM, knowledge‑graph QA pipelines, and NL2SQL techniques, concluding with practical deployment insights.
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.
The article reviews the open‑source qa_match tool from 58.com, detailing its deep‑learning based question‑answer matching architecture, hierarchical knowledge‑base support, lightweight pre‑training model SPTM, and practical applications, while summarizing the live‑stream presentation and Q&A session.
The article introduces qa_match V1.1, an open‑source deep‑learning QA matching tool that adds one‑level knowledge‑base support, releases a lightweight Bi‑LSTM pre‑trained language model (SPTM), and provides detailed architecture, training data, performance benchmarks, future plans, and contribution guidelines.
The article introduces qa_match V1.1, an open‑source, Apache‑licensed lightweight question‑answer matching system that adds a simple pre‑trained language model (SPTM), supports one‑level knowledge bases, details model architecture, training resources, performance benchmarks, future plans, and contribution guidelines.
The article presents qa_match, a TensorFlow‑based open‑source QA matching system that combines BiLSTM‑attention domain classification with DSSM intent matching, explains its architecture, training workflow, features, future roadmap, and how developers can contribute to the project.
This article reviews the evolution of semantic matching models for travel question‑answering, covering traditional keyword and probabilistic methods, deep‑learning encoders such as LSTM, CNN, and Transformer, interaction‑based architectures like MatchPyramid and hCNN, as well as transfer‑learning and multilingual extensions to improve practical deployment.
This article describes the design, model selection, experimental evaluation, and engineering optimization of an AI‑driven post‑sale question‑answering system for hotel services, covering FAQ construction, intent detection, deep‑learning matching models such as DSSM, ESIM, BERT, and their performance and latency trade‑offs.
The article introduces qa_match, an open‑source lightweight QA matching tool built on TensorFlow that combines BiLSTM‑based domain classification, DSSM‑based intent matching, and a model‑fusion strategy to deliver accurate, multi‑type responses for intelligent customer service applications.
This article presents an in‑depth overview of Alibaba's Xiaomì conversational AI system, describing how structured knowledge—including FAQs, phrase‑based knowledge, knowledge graphs, and machine‑read documents—is organized into a two‑level schema and applied to knowledge‑based QA (KBQA) and event‑based QA (EBQA) with detailed model pipelines, ranking, type inference, and recommendation techniques, while also discussing practical challenges and future directions.
This talk presents how Meituan leverages knowledge‑graph QA (KBQA) across restricted and complex smart‑interaction scenarios, compares semantic‑parsing and information‑retrieval approaches, introduces three‑layer concept nodes to handle entity explosion and non‑connected queries, and outlines architectural refinements for multi‑turn dialogue integration.
At SIGIR 2019 in Paris, Alipay presented two AI research papers—one applying reinforcement learning to predict user intent in customer‑service bots and another introducing the unsupervised QUEST method that builds noisy quasi‑knowledge graphs for answering complex multi‑document questions.
This article surveys the rapid proliferation of BERT-based research over the past six months, analyzing its impact on various NLP tasks such as question answering, information retrieval, dialog systems, summarization, data augmentation, classification, and sequence labeling, while also discussing the model's strengths, limitations, and future research opportunities.
The article explains how Tmall’s new “Most Concerned” module leverages NLP techniques, fastText embeddings, Bi‑LSTM classifiers, and a custom clustering algorithm to filter, group, and link consumer questions with relevant product reviews, improving the shopping experience across many product categories.
This article presents an overview of machine reading comprehension, covering the evolution from modular question‑answering systems to end‑to‑end neural models, discusses key datasets such as SQuAD and MS MARCO, and explores voice interaction technologies and future industry trends.
An extensive overview of ACL 2018, featuring acceptance statistics, award-winning papers, tutorial insights, and concise summaries of notable research across machine translation, semantic parsing, question answering, domain adaptation, text classification, summarization, dialogue systems, generation, and related tools.
This article explains what intelligent assistants are, distinguishes them from simple chatbots, outlines a four‑step deep‑learning NLP framework (Embed‑Encode‑Attend‑Predict), and demonstrates its use in intent recognition, knowledge mining, automatic question answering, and industry deployments.
Alibaba’s Tmall Genie X1 showcases a new semantic encoding model called Conv‑RNN that improves intelligent question answering and text classification, achieving state‑of‑the‑art results on benchmark datasets while illustrating the broader impact of semantic encoding on NLP applications.
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.
This article reviews the evolution of automatic question answering systems, outlines their core processing framework, and details how deep neural networks—especially CNNs, RNNs, and DCNNs—enable semantic representation, matching, and answer generation, while also discussing current challenges and future directions.
This article presents a knowledge‑graph‑driven question answering system, detailing its three‑layer architecture, semantic search and disambiguation techniques, verb‑semantic templates, deep‑learning models, experimental results, and current challenges in data quality and model integration.
This NSF‑funded project aims to develop algorithms that incrementally process partially observed data, integrating generative models with reinforcement‑learning policies to decide when to act, applied to simultaneous machine translation and quiz‑bowl style question answering.
