Tagged articles
Seq2Seq
18 articles · Page 1 of 1
This article explains how recurrent neural networks handle variable-length sequences, why LSTM's gated memory cells solve long-term dependency issues, and how attention mechanisms improve translation by weighting encoder hidden states, laying the groundwork for Transformer-based LLMs.
Attention MechanismGRULSTM
0 likes · 7 min read

This article explains why Transformer models surpass traditional RNN‑based seq2seq architectures by introducing self‑attention, multi‑head attention, and positional encoding, detailing the inner workings of encoders, decoders, and attention mechanisms, and comparing their advantages and limitations across NLP and vision tasks.
AttentionGRULSTM
0 likes · 30 min read

This practical guide walks through the full Transformer architecture for Chinese‑to‑English translation, detailing encoder‑decoder structure, tokenization and embeddings, batch handling with padding and masks, positional encodings, parallel teacher‑forcing, self‑ and multi‑head attention, and the complete forward and back‑propagation training steps.
Positional EncodingPyTorchSelf-Attention
0 likes · 26 min read

The article surveys automatic advertising copy generation, detailing why optimization is needed, the fundamentals of neural text generation with Seq2Seq and attention, extractive versus abstractive approaches, modern embeddings and MASS pre‑training, practical data and evaluation methods, and future enhancements such as multi‑stage attention, knowledge integration, and large pre‑trained models.
AIAdvertisingMASS
0 likes · 21 min read

This article presents a method to improve keyword detection in large‑scale speech recognition by integrating a prefix automaton into the beam‑search decoding of seq2seq models, enabling real‑time addition of new terms while reducing computational overhead compared to traditional approaches.
Seq2SeqSpeech Recognitionbeam search
0 likes · 12 min read

Seq2Path treats each sentiment tuple as an independent tree path, training with average path loss and decoding via constrained beam search with a discriminative token, achieving state‑of‑the‑art results on five aspect‑based sentiment analysis datasets and deployment in Alibaba Entertainment AI Brain.
ACLSeq2SeqTree Structure
0 likes · 3 min read


58 TechOct 12, 2021 · Artificial Intelligence
This article presents a practical study of extracting phone numbers from two‑speaker voice dialogues using Seq2Seq models—including LSTM, GRU with attention and feature fusion, and Transformer—detailing data characteristics, model architectures, training strategies, experimental results, and comparative analysis showing the GRU‑Attention approach achieving the best performance.
AttentionGRULSTM
0 likes · 13 min read

This article explains how attention mechanisms are applied to text recognition, covering the basic CNN‑Seq2Seq‑Attention architecture, multi‑scale attention extensions, and a 2D attentional irregular scene text recognizer with detailed network components, training loss, and experimental results.
AttentionCNNComputer Vision
0 likes · 8 min read


JD TechJun 17, 2021 · Artificial Intelligence
The paper introduces MTrajRec, a Seq2Seq multi‑task learning framework that simultaneously restores low‑sampling‑rate GPS trajectories to high‑sampling‑rate and aligns them to the road network, achieving more accurate and efficient trajectory recovery for downstream applications such as navigation and travel‑time estimation.
KDD 2021Seq2Seqdeep learning
0 likes · 9 min read

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.
AttentionBLEUGNMT
0 likes · 11 min read

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.
CMRLNLPSeq2Seq
0 likes · 14 min read

This article explains the fundamentals of seq2seq neural machine translation models, covering encoder‑decoder architecture, word embeddings, context vectors, RNN processing, and the attention mechanism introduced by Bahdanau and Luong, with visual illustrations and reference links for deeper study.
EmbeddingRNNSeq2Seq
0 likes · 11 min read

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.
NLPSeq2Seqcopy mechanism
0 likes · 17 min read


58 TechMar 13, 2019 · Artificial Intelligence
The article describes the design, workflow, and two‑stage model improvements of 58.com’s intelligent writing robot, which uses template matching, seq2seq with attention and BeamSearch, and slot‑replacement techniques to automatically generate titles and body content for real‑estate and used‑car promotions, achieving high publishing volume and readership.
AI writingBLEUBeamSearch
0 likes · 9 min read

This article analyzes the challenges of generating product copy for the 1688 B2B platform, proposes enhancements to attention‑based Seq2Seq and Pointer‑Generator models—including TextCNN classification, convolutional inputs, coverage attention, and beam‑search constraints—and demonstrates significant gains in accuracy, diversity, and reduced repetition through extensive experiments.
AICopy GenerationCoverage Attention
0 likes · 17 min read

This article explains the implementation of open-domain chatbots for customer service, comparing retrieval‑based and generative seq2seq approaches, describing hybrid methods that first attempt constrained retrieval before falling back to generation, and discusses training data, keyword extraction, and performance observations.
AICustomer ServiceSeq2Seq
0 likes · 6 min read

This article explains why attention mechanisms were introduced into Seq2Seq models, how they address the limitations of fixed‑length encoding, the role of bidirectional RNNs, and showcases their impact on machine translation and image captioning with illustrative diagrams.
Attention MechanismRNNSeq2Seq
0 likes · 10 min read

An Alibaba engineer created MusicGo, an AI program that scrapes hip‑hop lyrics, trains a seq2seq LSTM model, and generates rap songs themed around Double 11 and Alibaba's smart logistics, illustrating the practical steps, challenges, and creative adjustments needed for AI‑driven music creation.
AIAlibabaLSTM
0 likes · 7 min read
