The article explains how Tencent addresses the limitations of traditional content understanding methods in personalized recommendation by introducing an interest‑graph framework that combines classification, concept, entity, and event layers, and details the associated mining, matching, and online evaluation techniques.
This article provides a comprehensive overview of natural language processing fundamentals, covering the challenges of language modeling, N‑gram and Markov assumptions, smoothing techniques such as discounting and add‑one, evaluation via perplexity, basic tasks like Chinese word segmentation, subword tokenization, POS tagging, syntactic and semantic parsing, and a range of downstream applications including information extraction, sentiment analysis, question answering, machine translation, and dialogue systems.
At iQIYI’s iTech Conference, Zhang Zhigang detailed a full‑stack search ranking system that combines NLP‑driven query analysis, hierarchical indexing, multi‑stage coarse‑to‑fine ranking, Transformer‑based re‑ranking, sparse‑feature DNN enhancements and LIME/SE‑Block explainability, delivering measurable gains in CTR and NDCG for the platform’s video search.
This article presents the background, problem analysis, data preprocessing, modeling approaches and optimization results of applying various NLP methods—including statistical models, word embeddings, attention mechanisms and pretrained language models such as BERT—to improve the accuracy of classifying Ctrip ticket customer service dialogues.
This article reviews the fundamentals of entity‑relation extraction, surveys joint extraction techniques such as sequence labeling, table‑filling and seq2seq models, discusses document‑level graph‑based methods, highlights experimental findings, and outlines future research directions in knowledge‑graph construction.
The Local Life Comprehensive Demand Knowledge Graph (GENE) reorients Meituan’s supply‑demand matching by building a multi‑layer, user‑centric graph that captures intent and consideration, employing BERT, Word2Vec, ELECTRA, and reinforcement‑learning models to generate concrete and scene‑based demand nodes, now powering parent‑child, leisure, medical‑beauty, and education services.
This article describes how Douyin built an AI‑powered feedback management platform that uses NLP to automatically tag and cluster user comments, maps them to business scenarios, defines quantitative experience metrics, and creates a closed‑loop system for rapid problem discovery and product improvement.
Using Python, the author collected and visualized Douban and Weibo comments on the film “Chinese Doctor,” showing rating distributions, keyword word clouds, and fan sentiment, and compares the 2021 movie with the 2019 documentary to illustrate audience perception of the pandemic drama.
Baidu's ERNIE 3.0 introduces a 100‑billion‑parameter, knowledge‑graph‑augmented language model that breaks 54 Chinese NLP benchmarks, achieves human‑level performance on SuperGLUE, and demonstrates strong generation and zero‑shot capabilities, now available for public demo and research.
This article describes how Dingxiangyuan's algorithm team adopted Milvus for distributed vector indexing to improve semantic search in their community forum, detailing the background, retrieval workflow, various embedding models—including Bi‑Encoder, Spherical Embedding, and Knowledge Embedding—and summarizing the benefits and future applications.
This comprehensive survey reviews the latest research on graph neural networks applied to natural language processing, covering graph construction methods, graph representation learning techniques, encoder‑decoder models, static and dynamic graph building, and discusses challenges, benchmarks, and future directions in the field.
This article describes how 58.com built an end‑to‑end bidding service that crawls tender documents, classifies them into multiple categories with BERT‑based models (including softmax, sigmoid and ensemble approaches) and extracts key entities using BERT‑CRF and reading‑comprehension techniques, achieving over 90% overall accuracy and dramatically improving recall and precision.
This tutorial walks you through installing the jieba Python library, explains its three segmentation modes—precise, full, and search—demonstrates how to add or delete words, manage custom dictionaries, handle stop words, perform weight analysis, adjust word frequencies, and retrieve token positions, all with clear code examples and visual output.
This article presents seven practical Python scripts—from a concise web scraper for Zhihu images and a chatbot conversation loop to a Naive Bayes poem author classifier, a lottery number generator, an automated essay writer, a screen‑capture tool, and a GIF creator—demonstrating how to avoid reinventing the wheel while exploring diverse automation tasks.
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.
ConSERT is a contrastive self‑supervised framework that fine‑tunes BERT with augmented sentence views and NT‑Xent loss to overcome embedding collapse, delivering roughly 8% higher STS performance than prior methods, remaining robust in few‑shot and supervised scenarios, and now deployed in Meituan’s NLP pipelines.
This article explains the Transformer architecture—its self‑attention core, multi‑head attention, positional encoding, encoder‑decoder structure, and how it overcomes RNN limitations, providing a foundation for its use in NLP, image detection, and OCR.
The paper outlines an end‑to‑end pipeline that standardizes highly personalized food‑delivery dish names by combining rule‑based and BERT‑DSSM text synonym detection with EfficientNet image classification, constructing a multi‑level taxonomy that improves aggregation, supply‑demand analysis, recall ranking and merchant tagging.
This article introduces a curated selection of lesser‑known Python libraries for data‑science tasks—including data acquisition, date‑time handling, imbalanced‑learning, fast keyword extraction, fuzzy string matching, time‑series modeling, 3‑D visualization, web‑app building, and reinforcement‑learning—providing installation commands and concise usage examples.
Automatic homework grading leverages AI to transform captured images into graded results through preprocessing, layout analysis, OCR, answer matching, and strategy modules, while addressing three question categories—logical, text‑rich, and graphic—each presenting distinct technical challenges and future research directions.
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 explores the landscape of text matching in NLP, covering problem types, three model interaction levels, sentence embedding techniques, supervised and unsupervised approaches, and the role of contrastive learning with alignment and uniformity metrics.
This article presents a comprehensive overview of Meituan's query understanding system, detailing how entity recognition, entity linking, query rewriting, and intent detection are designed and deployed to improve O2O search relevance across diverse local services.
This article presents a collection of Python 3.6.4 scripts that demonstrate how to scrape Zhihu images, converse with chatbots, classify Tang poems using NLP, generate random lottery numbers, automatically compose apology letters, capture screen images, and create animated GIFs, providing practical code examples for each task.
This article explains the BERT model by first reviewing the Encoder-Decoder framework, then detailing the attention mechanism—including self-attention and multi-head attention—before describing the full Transformer architecture and finally outlining BERT’s encoder-only design, training stages, and fine-tuning applications.
The article describes how NetEase adapts a pre‑trained BERT model to classify news articles into ultra‑short, short, or long timeliness categories by combining rule‑based strong and weak time cues, key‑sentence extraction, domain‑embedding fusion and multi‑layer semantic aggregation, achieving accurate and interpretable predictions for its platform.
This article reviews recent advances in abstractive summarization, covering pointer‑generator networks with coverage loss, integration of entity knowledge, strategies to mitigate repetition such as unlikelihood training and nucleus sampling, and emerging non‑autoregressive approaches like the Levenshtein Transformer.
The article reviews the Chinese NLP pre‑training model generalization competition, detailing data preprocessing, augmentation, external data usage, model scaling and architecture tweaks, loss functions, learning‑rate and adversarial training strategies, regularization techniques, post‑processing optimizations, and ineffective methods, highlighting their impact on performance metrics.
Youku’s new text‑video alignment system automatically generates short video summaries by extracting multimodal video and linguistic features, matching sentences to clips through embedding and tag‑level models, and enabling AI‑driven auto‑editing that cuts production time from days to minutes.
This article describes how a team at Longquan Temple leverages deep‑learning, NLP, and OCR technologies to automatically punctuate, recognize, and translate the massive Buddhist canon, achieving near‑human accuracy and dramatically accelerating scholarly work on ancient texts.
This article provides an in‑depth introduction to multi‑task learning (MTL), explaining its core concepts, why it is widely used in recommendation systems, NLP, CV and reinforcement learning, and offering guidance on model architectures, loss design, auxiliary tasks, and practical deployment tips.
This article presents a comprehensive study on generating recruitment job titles by combining a rule‑based pipeline with advanced seq2seq models—including BiLSTM‑Attention, Pointer‑Generator, and a Field‑Gate Dual‑Attention architecture—demonstrating significant performance gains on real‑world hiring data.
The article presents a comprehensive overview of Ant Group's intelligent service research, summarizing recent AI‑focused papers on text classification, stance detection, data augmentation, knowledge distillation for ranking, reinforcement‑learning‑based dialogue clarification, behavior‑cloning dialogue systems, anti‑fraud outbound bots, tag‑based service recommendation, and multi‑agent service groups, while also highlighting future directions and recruitment opportunities.
This article introduces the concepts, tasks, and recent advances in text sentiment analysis, focusing on attribute‑level sentiment (TG‑ABSA) and opinion‑quadruple extraction, describing unsupervised, reading‑comprehension, and multi‑task deep‑learning approaches, their implementation on Huawei Cloud, experimental results, and future research directions.
This article explores the current state of AI, the evolution of NLP and voice assistants, common pitfalls in AI product development, and practical product‑management methods—including user segmentation, metric design, and lifecycle planning—to help engineers and product managers deliver effective AI‑driven solutions.
This article explores the intersection of natural language processing and operations, outlines common text‑handling challenges, and presents three concrete AIOps case studies—log Q&A, anomaly detection, and ticket recommendation—while reflecting on a closed‑loop AI workflow and future research directions.
In an InfoQ interview, JD Technology senior algorithm scientist Wu Youzheng reviews the rapid advances of natural language processing in 2020—including GPT‑3, multimodal dialogue, knowledge‑enhanced pre‑training, and knowledge graphs—while outlining the most promising research directions and practical challenges for the coming year.
This article presents an in‑depth overview of Alibaba Feizhu's travel‑scene search system, covering its background, architecture, query understanding, tagging, POI mining, synonym extraction, recall strategies, model designs, performance results, and future directions for personalization and explainability.
This article describes how a Chinese online medical platform tackled the large‑scale extraction and structuring of hospital report images by combining OCR, deep‑learning text‑region detection, fast text classification, and advanced NER techniques, detailing challenges, algorithm choices, performance results, and remaining issues.
This article explains key concepts of neural machine translation, covering Seq2Seq encoder‑decoder models, beam search strategies, BLEU evaluation, various attention mechanisms, and the enhancements introduced in Google's Neural Machine Translation system to improve speed, OOV handling, and translation quality.
This article details the background, challenges, architecture, model selection, and future directions of the business‑opportunity slot recognition module used in 58.com’s intelligent customer service, highlighting how regex‑model fusion and IDCNN‑CRF improve entity extraction for phone, WeChat, address, and time slots.
This weekly roundup covers ShardingSphere's top‑5 ranking among Chinese‑led open‑source projects, Taro's entry into the 2020 China Open‑Source TOP4, Raspberry Pi Pico's $4 launch, Visual Studio's native WSL 2 support, Elasticsearch's license shift, Facebook's AI for the visually impaired, JD's future‑tech whitepaper, an AAAI paper on modal‑free segmentation, and SimCLR applied to NLP pre‑training.
The 2017 Transformer model introduced by Vaswani et al. revolutionized machine translation by relying solely on attention mechanisms, outperforming traditional RNN and CNN approaches through parallel processing and improved contextual understanding.
This article explains how customer‑service chatbots use well‑structured knowledge bases and advanced sentence‑similarity algorithms to achieve over 90% question‑matching rates, covering knowledge‑base construction, maintenance, and the core AI models that power accurate responses.
This article analyzes Xianyu's second‑hand attribute extraction pipeline, detailing the challenges of sparse product data, the decomposition into NER and classification tasks, the use of Albert‑Tiny, StructBert and regex methods, deployment strategies, evaluation results, and future directions.
This week’s developer newsletter highlights China’s 11.3‑billion‑parameter Wenhui AI model, Rokid’s dual‑camera MR glasses, the TypeScript 4.2 beta release, a Go generics proposal for 1.18, Docker’s 2021 priorities, the Industrial Internet action plan, a robust DARTS paper from ICLR 2021, and the open‑source TextBox library for text generation.
This article presents a systematic exploration of text pre‑training models for dialogue classification in information‑security scenarios, comparing baseline TextCNN, an enhanced TextCNN_role, RoBERTa with domain‑adaptive pre‑training, and a distilled mini‑model, and discusses their performance, trade‑offs, and future directions.
The Amap team introduced LRC‑BERT, a contrastive‑learning‑based knowledge‑distillation framework that employs a novel COS‑NCE loss, gradient‑perturbation, and a two‑stage training schedule, enabling a 4‑layer student model to retain about 97 % of BERT‑Base accuracy while being 7.5× smaller and 9.6× faster, and it has already improved real‑world traffic‑event extraction performance.
This article provides a comprehensive overview of sequence labeling tasks in NLP, covering their definition, common tag schemes (BIO, BIEO, BIESO), comparisons with other NLP tasks, major modeling approaches such as HMM, CRF, RNN and BERT, real‑world applications like POS tagging, NER, event extraction and gene analysis, and a step‑by‑step PyTorch implementation with dataset preparation, training pipeline, and evaluation metrics.
This article reviews the evolution of pretraining models in NLP, discusses the practical challenges of deploying large models such as inference latency, knowledge integration, and task adaptation, and presents Xiaomi’s optimization techniques including knowledge distillation, low‑precision inference, operator fusion, and multi‑granularity segmentation for dialogue systems.
The article reviews the rise of AI‑driven intelligent writing robots, outlines industry use cases, explains two main generation methods, and details how 58.com leverages massive structured data to automatically produce narrative, emotion‑rich listings for vehicles, housing, and jobs, enhancing user engagement.
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.
This article explains how voice assistants rely on NLP's three processing layers, examines the shortcomings of the traditional DIS semantic structure, introduces the hierarchical CMRL schema with its six element types, and presents two neural models—copy‑write seq2seq and seq2tree—for accurate semantic parsing of complex commands.
This article explains how voice assistants rely on a three‑layer NLP pipeline (lexical, syntactic, and semantic analysis), discusses the shortcomings of the traditional DIS (Domain‑Intent‑Slot) structure for complex commands, and introduces the hierarchical CMRL schema along with two neural models (copy‑write seq2seq and seq2tree) for converting natural language into structured logical expressions.
This article introduces LightSeq, an open‑source, GPU‑accelerated inference engine that dramatically speeds up Transformer‑based models such as BERT and GPT by up to 14× over TensorFlow, supports multiple decoding strategies, integrates seamlessly with major deep‑learning frameworks, and provides detailed performance benchmarks and technical optimizations.
This article reviews current query expansion methods, contrasting relevance‑based models that rely on terms or entities with generative models that encode whole queries, discusses challenges of handling long and complex queries, and surveys recent research on encoding queries, session modeling, and multi‑task feature integration.
This article demonstrates how to crawl Douban short reviews for the TV show "Actors Please Take Your Place" Season 2, clean and deduplicate the data, apply Baidu's SKEP sentiment model, and visualize word clouds, rating distributions, posting times, and sentiment scores, providing full Python code for replication.
This article presents a comprehensive study on slot (entity) recognition and error correction for voice robots, describing the labeling scheme, data annotation, IDCNN+CRF and BiLSTM+CRF models, a pinyin‑based similarity algorithm, and reporting significant accuracy improvements in real‑world deployments.
This article provides a step‑by‑step illustrated guide to the Transformer architecture, covering its macro structure, detailed self‑attention mechanisms, multi‑head attention, positional encoding, residual connections, decoder operation, training process, loss functions, and includes complete PyTorch and custom Python code examples.
This article provides a comprehensive overview of natural language processing, tracing its origins from Turing's seminal test to modern techniques like regular expressions, word order importance, word embeddings, Word2vec, GloVe, and knowledge‑ and retrieval‑based chatbot methods.
This article provides a comprehensive overview of BERT and related NLP advances, covering its historical context, model architecture, input‑output mechanisms, comparisons with CNNs, word‑embedding evolution, pre‑training strategies like MLM and next‑sentence prediction, and practical guidance for fine‑tuning and feature extraction.
The article recaps the inaugural Multimodal Natural Language Processing workshop at NLPCC 2020, highlighting breakthroughs in multimodal summarization, pre‑training models, AI‑driven art, visual‑language interaction, and multimodal dialogue systems, and showcases research from leading institutions and industry partners.
Alibaba Cloud open‑sources EasyTransfer, a high‑performance deep transfer‑learning framework for NLP that unifies pre‑training, knowledge distillation, meta‑learning and distributed deployment, offering a rich ModelZoo, AppZoo and seamless integration with the PAI ecosystem.
This article describes a speaker role recognition system for a voice analysis platform, detailing a gender‑based pre‑filter, keyword‑matching and TextCNN‑based text classification, and single‑sentence correction methods that together improve role assignment accuracy by about 6% over baseline third‑party solutions.
The paper introduces QDGAT, a question‑directed graph attention network that enhances numerical reasoning in reading comprehension by explicitly modeling relationships among numbers, entities, and questions, and demonstrates its effectiveness through extensive experiments on the DROP dataset.
The article reviews NLP interpretability techniques, contrasting white‑box approaches that probe model internals such as neuron analysis, diagnostic classifiers, and attention with black‑box strategies like rationales, adversarial testing, and local surrogates, and argues that black‑box methods are generally more practical for business deployment despite offering shallower insights.
This article surveys the evolution of pre‑training models for natural language processing, detailing model architectures such as Encoder‑AE, Decoder‑AR, Encoder‑Decoder, Prefix LM, and PLM, analyzing why models like RoBERTa, T5, and GPT‑3 excel, and offering practical guidance for building strong pre‑training systems.
The article presents AliCoCo, Alibaba’s large‑scale e‑commerce knowledge graph that models user demand as concepts, describes its four‑layer architecture, the algorithms for concept extraction, taxonomy building, and item association, and demonstrates its impact on search and recommendation systems.
This article presents Tencent's research on hotspot mining and event extraction for information flow, detailing the challenges of timeliness, comprehensiveness, and heat rationality, the combined use of time‑series analysis, topic detection, clustering, and dynamic‑time‑warping, and the resulting framework and its applications to text, image, and video recommendation.
This article introduces a curated collection of lesser‑known Python libraries for data‑science tasks—including wget, pendulum, imbalanced‑learn, flashtext, fuzzywuzzy, pyflux, ipyvolume, dash, and gym—detailing their purpose, installation commands, and concise code examples to help practitioners expand their toolkit.
This presentation details the challenges and solutions for short‑text understanding in medical health, covering DingXiangYuan’s business scenarios, NLP pipeline components, knowledge‑graph construction, concept mining, and their impact on search, recommendation, and tagging systems.
DiDi AI Labs’ NLP team earned third place in the WMT2020 Chinese‑to‑English news translation task with a 36.6 BLEU score, using an enhanced Transformer‑2 model that incorporates self‑attention, relative positional attention, iterative back‑translation, knowledge distillation, data cleaning, ensembling, and other techniques, now deployed across DiDi’s international services.
This article introduces a curated selection of lesser‑known Python packages—such as wget, pendulum, imbalanced‑learn, FlashText, fuzzywuzzy, PyFlux, ipyvolume, Dash, and Gym—detailing their installation commands, core functionalities, and code examples to help data scientists expand their toolkit beyond the usual pandas, scikit‑learn, and matplotlib.
This article describes how Xiaomi's AI team tackles Automatic Speech Recognition (ASR) query errors by analyzing error patterns, employing BERT, ELECTRA and a soft‑masked BERT model, generating synthetic noisy data with a fuzzy‑phoneme generator, and presenting experimental results and future research directions.
This article provides a step‑by‑step tutorial on preparing data, pre‑training the SPTM language model, fine‑tuning a text‑classification model, generating predictions, and creating a submission file for the 58.com AI algorithm competition using the open‑source qa_match toolkit.
The article reviews the principles of popular pretrained language models, compares their architectures, and details how NetEase Yanxuan applied BERT, GPT and ELMo to classification, matching, sequence labeling and generation tasks, presenting experimental results and deployment insights.
This article introduces chatbots, explains rule‑based and self‑learning types, describes how AI‑driven bots work, and provides a complete Python tutorial using the ChatterBot library—including environment setup, installation, and full source code for a functional chatbot.
This article reviews the evolution of encoder‑decoder based text generation, covering classic seq2seq with attention, pointer networks, copy mechanisms, knowledge‑enhanced models, convolutional approaches, and the latest Transformer‑based pre‑training such as MASS, highlighting their architectures, key innovations, and practical considerations.
This article presents the design, implementation, and performance of 58.com’s dialogue robot for local life services, detailing its business background, overall AI architecture, core QABot and TaskBot capabilities, intelligent lead generation, opportunity mining, and future research directions.
This announcement describes the rise of AI‑driven intelligent customer service, highlights 58.com’s long‑standing system, and introduces a competition that provides real‑world data for participants to develop advanced text‑matching and classification models using state‑of‑the‑art NLP techniques.
This article presents 58.com’s intelligent voice quality inspection system, detailing its overall architecture, speech separation, speaker role identification, NLP‑based tagging, model choices such as VGG, BERT, ALBERT and SPTM, and real‑world call‑center use cases that improve efficiency and reduce risk.
The article surveys fine‑grained character sentiment analysis for script evaluation, detailing traditional, target‑dependent and aspect‑level methods, describing iQIYI’s BERT‑TD‑LSTM and CNN architectures, addressing challenges such as character name recognition and long‑range context, and outlining future improvements after a Parasite case study.
The announcement introduces an AI‑driven intelligent customer service competition, highlighting the importance of text matching and classification in NLP, describing 58.com’s existing system, providing a real‑world dataset, and inviting participants to develop precise models using the latest deep‑learning techniques.
This article examines the policy backdrop, industry challenges, and JD Health’s AI‑driven smart triage solution—including its knowledge‑base, NLP, and multimodal fusion algorithms—and showcases its impact during the COVID‑19 surge while outlining future platform and lifecycle extensions.
In this interview, DYG team member Wang He introduces his teammates, explains why they formed the team, and shares detailed model‑fusion techniques—including input variation, diverse model architectures, and training‑target differences—to boost competition scores during the final stage.
This article examines how large pretrained BERT models can be compressed via knowledge distillation into a lightweight TextCNN classifier for efficient garbage opinion detection, detailing traditional distillation methods, several practical schemes, experimental results, and the advantages of the approach.
This article presents a comprehensive overview of automatic speech recognition (ASR) error correction techniques employed by Xiaomi's Xiao‑Ai team, detailing problem definition, related work on BERT and ELECTRA, a custom generator‑discriminator architecture with a fuzzy‑phoneme simulator, experimental results, and prospective research directions.
This article details the end‑to‑end process of extracting and leveraging tags for used‑car listings, covering data collection, segmentation, NLP‑based tokenization, word‑vector generation, tag‑library construction, and online retrieval flow to improve personalized recall and CTR.
This article shares the Xiaomi AI Lab NLP team's experience in the NLPCC lightweight language model competition, discusses efficiency challenges of large pretrained models like BERT, and details practical inference optimizations—including model distillation, batching, FP16 quantization, and FasterTransformer integration—that dramatically reduce latency and hardware costs in production.
The article explains how the GEAR model uses graph neural networks and BERT representations to aggregate multiple pieces of evidence for fact verification, improving accuracy on datasets like FEVER and offering applications in misinformation detection, knowledge‑graph completion, and advertising analytics.
The article surveys the rapid growth of AI, presenting adoption statistics, a Forrester‑predicted market surge, a ranked list of the ten most popular AI technologies with vendor examples, and the key obstacles enterprises face when implementing AI solutions.
This article explains how Weibo's advertising platform leverages content understanding—covering system architecture, problems caused by insufficient comprehension, the construction of NLP and vision capabilities, content‑based ad strategies, and a celebrity‑brand knowledge graph—to improve ad relevance and ROI.
NetEase improves its news‑feed recommendation by applying a multi‑stage semantic text understanding pipeline—lexical analysis, hierarchical content tagging, and quality filtering—using two‑level classifiers, LDA‑based topic modeling, multi‑label concept and entity extraction, and dense vector representations to better capture user interests and boost personalization performance.
The Baidu ACL 2020 paper sharing live session recap presents three NLP research papers—on unsupervised style transfer, sentiment‑knowledge‑enhanced pre‑training, and conversational recommendation over multi‑type dialogs—detailing their novel models, methodologies, and key contributions.
This article shares a competition winner's step‑by‑step solution for predicting user age and gender from ad click sequences, treating IDs as words, using word2vec embeddings, a custom transformer‑LSTM model, dual‑task loss, and weight‑search post‑processing.
This article reviews how natural language processing is used in financial investment analysis, summarizing case studies from Two Sigma, BlackRock, UC Berkeley and other institutions that apply topic modeling, event extraction and sentiment analysis to improve portfolio performance and achieve excess returns.
This article explains how enterprises can classify structured, semi‑structured and unstructured data as “dark data”, why traditional RPA struggles with it, and how AI technologies like NLP, computer vision and machine learning—exemplified by Automation Anywhere’s IQ‑Bot—enable end‑to‑end automation of hidden information.
The AIS 2020 Conference, co‑hosted by the Beijing Academy of Artificial Intelligence and Meituan, showcased 74 top ACL, IJCAI and SIGIR papers across 15 sessions on NLP, AI and IR topics, streamed free online on May 23‑24 2020 with keynote speakers from leading Chinese universities.
This article describes how advanced natural‑language‑processing, big‑data, and deep‑learning techniques are integrated into an end‑to‑end platform for financial asset management, covering large‑scale bid‑tender text analysis, few‑shot sentiment monitoring, model architectures, data‑enhancement methods, and practical deployment results.