Methods › Natural Language Processing › Subword Segmentation › BPE › Papers, page 184

Byte Pair Encoding

BPE

Papers archive 2025-07-28

archive papers tagged: 18,975 · with a code link: 8,675 · where Syntology ran a sample: 2,895 (2,443 with a run with no instrument failure, 452 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (2,895 of 18,975 tagged: 2,443 with a run with no instrument failure, 452 where every run was a failure of Syntology's instrument)

Page 184 of 190: papers 18,301 to 18,400 of 18,975, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

• Improving N-gram Language Models with Pre-trained Deep Transformer
  22 Nov 2019 · 0 repositories · arXiv:1911.10235
• Neuron Interaction Based Representation Composition for Neural Machine Translation
  22 Nov 2019 · 0 repositories · arXiv:1911.09877
• Spectral Graph Transformer Networks for Brain Surface Parcellation
  22 Nov 2019 · 0 repositories · arXiv:1911.10118
• Paraphrasing with Large Language Models
  21 Nov 2019 · 0 repositories · arXiv:1911.09661
• WildMix Dataset and Spectro-Temporal Transformer Model for Monoaural Audio Source Separation
  21 Nov 2019 · 0 repositories · arXiv:1911.09783
• MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
  19 Nov 2019 · 0 repositories · arXiv:1911.08139
• Unsupervised Natural Question Answering with a Small Model
  19 Nov 2019 · 0 repositories · arXiv:1911.08340
• Graph Transformer for Graph-to-Sequence Learning
  18 Nov 2019 · 1 repository · arXiv:1911.07470
  Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples)
• MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning
  17 Nov 2019 · 3 repositories · arXiv:1911.09483
  Syntology official: not harvested · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
• Music theme recognition using CNN and self-attention
  16 Nov 2019 · 0 repositories · arXiv:1911.07041
• Evaluating robustness of language models for chief complaint extraction from patient-generated text
  15 Nov 2019 · 0 repositories · arXiv:1911.06915
• Selection-based Question Answering of an MOOC
  15 Nov 2019 · 1 repository · arXiv:1911.07629
• Sequential Recommendation with Relation-Aware Kernelized Self-Attention
  15 Nov 2019 · 0 repositories · arXiv:1911.06478
• Attention on Abstract Visual Reasoning
  14 Nov 2019 · 0 repositories · arXiv:1911.05990
• Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA
  14 Nov 2019 · 1 repository · arXiv:1911.06258
• Character-based NMT with Transformer
  12 Nov 2019 · 0 repositories · arXiv:1911.04997
• SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery
  12 Nov 2019 · 1 repository · arXiv:1911.04738
  Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)
• Attending to Entities for Better Text Understanding
  11 Nov 2019 · 0 repositories · arXiv:1911.04361
• BP-Transformer: Modelling Long-Range Context via Binary Partitioning
  11 Nov 2019 · 2 repositories · arXiv:1911.04070
  Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 7 harvested samples)
• Disentangle, align and fuse for multimodal and semi-supervised image segmentation
  11 Nov 2019 · 2 repositories · arXiv:1911.04417
• Long-span language modeling for speech recognition
  11 Nov 2019 · 0 repositories · arXiv:1911.04571
• TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection
  11 Nov 2019 · 2 repositories · arXiv:1911.04118
• Distilling Knowledge Learned in BERT for Text Generation
  10 Nov 2019 · 2 repositories · arXiv:1911.03829
  Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
• INSET: Sentence Infilling with INter-SEntential Transformer
  10 Nov 2019 · 1 repository · arXiv:1911.03892
• Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks
  10 Nov 2019 · 2 repositories · arXiv:1911.03863
• Listen and Fill in the Missing Letters: Non-Autoregressive Transformer for Speech Recognition
  10 Nov 2019 · 0 repositories · arXiv:1911.04908
• Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding
  10 Nov 2019 · 0 repositories · arXiv:1911.06156
• TENER: Adapting Transformer Encoder for Named Entity Recognition
  10 Nov 2019 · 6 repositories · arXiv:1911.04474
  Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
• Two-Headed Monster And Crossed Co-Attention Networks
  10 Nov 2019 · 0 repositories · arXiv:1911.03897
• A Reinforced Generation of Adversarial Examples for Neural Machine Translation
  9 Nov 2019 · 1 repository · arXiv:1911.03677
• Zero-Shot Paraphrase Generation with Multilingual Language Models
  9 Nov 2019 · 0 repositories · arXiv:1911.03597
• Graph-to-Graph Transformer for Transition-based Dependency Parsing
  8 Nov 2019 · 1 repository · arXiv:1911.03561
• Question Generation from Paragraphs: A Tale of Two Hierarchical Models
  8 Nov 2019 · 0 repositories · arXiv:1911.03407
• Resurrecting Submodularity for Neural Text Generation
  8 Nov 2019 · 0 repositories · arXiv:1911.03014
• Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models
  8 Nov 2019 · 3 repositories · arXiv:1911.06194
• Lipschitz Constrained Parameter Initialization for Deep Transformers
  8 Nov 2019 · 0 repositories · arXiv:1911.03179
• Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs
  7 Nov 2019 · 2 repositories · arXiv:1911.02707
  Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples)
• Microsoft Research Asia's Systems for WMT19
  7 Nov 2019 · 0 repositories · arXiv:1911.06191
• Porous Lattice-based Transformer Encoder for Chinese NER
  7 Nov 2019 · 0 repositories · arXiv:1911.02733
• Probing Contextualized Sentence Representations with Visual Awareness
  7 Nov 2019 · 0 repositories · arXiv:1911.02971
• An End-to-end Approach for Lexical Stress Detection based on Transformer
  6 Nov 2019 · 0 repositories · arXiv:1911.04862
• CoKE: Contextualized Knowledge Graph Embedding
  6 Nov 2019 · 3 repositories · arXiv:1911.02168
  Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
• Enriching Conversation Context in Retrieval-based Chatbots
  6 Nov 2019 · 0 repositories · arXiv:1911.02290
• Fast Transformer Decoding: One Write-Head is All You Need
  6 Nov 2019 · 4 repositories · arXiv:1911.02150
  Syntology 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
• Graph Transformer Networks
  6 Nov 2019 · 1 repository · arXiv:1911.06455
• Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds
  6 Nov 2019 · 0 repositories · arXiv:1911.02365
• Improving Bidirectional Decoding with Dynamic Target Semantics in Neural Machine Translation
  5 Nov 2019 · 0 repositories · arXiv:1911.01597
• Unsupervised Cross-lingual Representation Learning at Scale
  5 Nov 2019 · 35 repositories · arXiv:1911.02116
  Syntology official (archive's flag): 12 ran · 40 ran (of which 13 constructed an object rather than computing a result; 35 with no instrument failure: 4 honoured, 1 violated, 30 with no contract checked; 5 where Syntology's instrument failed) · 19 unverified (of 59 harvested samples) · 52 pointer-only (licence)
• Assessing Social and Intersectional Biases in Contextualized Word Representations
  4 Nov 2019 · 1 repository · arXiv:1911.01485
• An Algorithm for Routing Capsules in All Domains
  2 Nov 2019 · 1 repository · arXiv:1911.00792
• Machine Translation Evaluation using Bi-directional Entailment
  2 Nov 2019 · 0 repositories · arXiv:1911.00681
• Aggregating Bidirectional Encoder Representations Using MatchLSTM for Sequence Matching
  1 Nov 2019 · 0 repositories
• Automatically Extracting Challenge Sets for Non-Local Phenomena in Neural Machine Translation
  1 Nov 2019 · 0 repositories
• Combining Global Sparse Gradients with Local Gradients in Distributed Neural Network Training
  1 Nov 2019 · 0 repositories
• CVIT's submissions to WAT-2019
  1 Nov 2019 · 0 repositories
• Dialect Text Normalization to Normative Standard Finnish
  1 Nov 2019 · 1 repository
• DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
  1 Nov 2019 · 6 repositories · arXiv:1911.00536
  Syntology community repositories only · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified (of 12 harvested samples) · 12 pointer-only (licence)
• English to Hindi Multi-modal Neural Machine Translation and Hindi Image Captioning
  1 Nov 2019 · 0 repositories
• Enhanced Transformer Model for Data-to-Text Generation
  1 Nov 2019 · 0 repositories
• FASPell: A Fast, Adaptable, Simple, Powerful Chinese Spell Checker Based On DAE-Decoder Paradigm
  1 Nov 2019 · 1 repository
• GEM: Generative Enhanced Model for adversarial attacks
  1 Nov 2019 · 0 repositories
• Generalizing Question Answering System with Pre-trained Language Model Fine-tuning
  1 Nov 2019 · 0 repositories
• Idiap NMT System for WAT 2019 Multimodal Translation Task
  1 Nov 2019 · 0 repositories
• IIT-KGP at COIN 2019: Using pre-trained Language Models for modeling Machine Comprehension
  1 Nov 2019 · 0 repositories
• Improving Answer Selection and Answer Triggering using Hard Negatives
  1 Nov 2019 · 0 repositories
• Improving Generalization of Transformer for Speech Recognition with Parallel Schedule Sampling and Relative Positional Embedding
  1 Nov 2019 · 0 repositories · arXiv:1911.00203
• Improving Natural Language Understanding by Reverse Mapping Bytepair Encoding
  1 Nov 2019 · 0 repositories
• Inspecting Unification of Encoding and Matching with Transformer: A Case Study of Machine Reading Comprehension
  1 Nov 2019 · 0 repositories
• Investigating the Effectiveness of BPE: The Power of Shorter Sequences
  1 Nov 2019 · 0 repositories
• Long Warm-up and Self-Training: Training Strategies of NICT-2 NMT System at WAT-2019
  1 Nov 2019 · 0 repositories
• LTRC-MT Simple & Effective Hindi-English Neural Machine Translation Systems at WAT 2019
  1 Nov 2019 · 0 repositories
• Mixed Multi-Head Self-Attention for Neural Machine Translation
  1 Nov 2019 · 0 repositories
• Natural Language Generation for Effective Knowledge Distillation
  1 Nov 2019 · 1 repository
• On the Relation between Position Information and Sentence Length in Neural Machine Translation
  1 Nov 2019 · 0 repositories
• Our Neural Machine Translation Systems for WAT 2019
  1 Nov 2019 · 0 repositories
• Pingan Smart Health and SJTU at COIN - Shared Task: utilizing Pre-trained Language Models and Common-sense Knowledge in Machine Reading Tasks
  1 Nov 2019 · 0 repositories
• Recurrent Positional Embedding for Neural Machine Translation
  1 Nov 2019 · 0 repositories
• Recycling a Pre-trained BERT Encoder for Neural Machine Translation
  1 Nov 2019 · 0 repositories
• Sarah's Participation in WAT 2019
  1 Nov 2019 · 0 repositories
• Selecting, Planning, and Rewriting: A Modular Approach for Data-to-Document Generation and Translation
  1 Nov 2019 · 0 repositories
• Self-Adaptive Scaling for Learnable Residual Structure
  1 Nov 2019 · 0 repositories
• Supervised neural machine translation based on data augmentation and improved training & inference process
  1 Nov 2019 · 0 repositories
• SYSTRAN @ WAT 2019: Russian-Japanese News Commentary task
  1 Nov 2019 · 0 repositories
• SYSTRAN @ WNGT 2019: DGT Task
  1 Nov 2019 · 0 repositories
• The Concordia NLG Surface Realizer at SRST 2019
  1 Nov 2019 · 0 repositories
• Transformer and seq2seq model for Paraphrase Generation
  1 Nov 2019 · 0 repositories
• Transformer-based Model for Single Documents Neural Summarization
  1 Nov 2019 · 0 repositories
• Transformer Dissection: An Unified Understanding for Transformer's Attention via the Lens of Kernel
  1 Nov 2019 · 0 repositories
• ``Transforming'' Delete, Retrieve, Generate Approach for Controlled Text Style Transfer
  1 Nov 2019 · 0 repositories
• Attention Is All You Need for Chinese Word Segmentation
  31 Oct 2019 · 1 repository · arXiv:1910.14537
• Document-level Neural Machine Translation with Associated Memory Network
  31 Oct 2019 · 0 repositories · arXiv:1910.14528
• NAT: Neural Architecture Transformer for Accurate and Compact Architectures
  31 Oct 2019 · 1 repository · arXiv:1910.14488
• Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning
  31 Oct 2019 · 1 repository · arXiv:1910.14613
• Parameter Sharing Decoder Pair for Auto Composing
  31 Oct 2019 · 0 repositories · arXiv:1910.14270
• Masked Language Model Scoring
  31 Oct 2019 · 6 repositories · arXiv:1910.14659
  Syntology official: no sample here; runs from other or unrecorded repositories · 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 10 harvested samples) · 3 pointer-only (licence)
• Transfer Learning from Transformers to Fake News Challenge Stance Detection (FNC-1) Task
  31 Oct 2019 · 0 repositories · arXiv:1910.14353
• An Augmented Transformer Architecture for Natural Language Generation Tasks
  30 Oct 2019 · 0 repositories · arXiv:1910.13634
• Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer
  30 Oct 2019 · 0 repositories · arXiv:1910.13923
• Transformer-based Cascaded Multimodal Speech Translation
  29 Oct 2019 · 0 repositories · arXiv:1910.13215
• BPE-Dropout: Simple and Effective Subword Regularization
  29 Oct 2019 · 7 repositories · arXiv:1910.13267
  Syntology official (archive's flag): 3 ran · 24 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 1 violated, 14 with no contract checked; 9 where Syntology's instrument failed) · 0 unverified (of 24 harvested samples) · 1 pointer-only (licence)