No article text was recorded for this version.
subword-to-word alignment
Version 1 of 137 papers50 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement
- Blog: SynCode: LLM Generation with Grammar Augmentation
- Blog: Enhancing Machine Translation with Dependency-Aware Self-Attention
- Blog: Sentiment Analysis with Weighted Graph Convolutional Networks
- Blog: Automata-based constraints for language model decoding
- Blog: Do Syntax Trees Help Pre-trained Transformers Extract Information?
- Blog: Syntax-augmented Multilingual BERT for Cross-lingual Transfer
- Blog: RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL
- Blog: Dependency-Based Self-Attention for Transformer NMT
- Blog: Dependency-Based Self-Attention for Transformer Neural Machine Translation
- Blog: Leveraging Grammar Induction for Language Understanding and Generation
- Blog: Flexible and Efficient Grammar-Constrained Decoding
- Blog: Synchromesh: Reliable Code Generation from Pre-trained Language Models
- Blog: Continuous Diffusion Models Can Obey Formal Syntax
- Blog: IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking
- Blog: Hybrid Multilingual Parsing with HPSG for SRL
- Blog: Enforcing Grammar in Code Synthesis with Transformers
- Blog: Syntax-informed Question Answering with Heterogeneous Graph Transformer
- Blog: Syntax-guided Localized Self-attention by Constituency Syntactic Distance
- Blog: The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task
- Blog: Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-sentence Dependency Graph
- Blog: Correctness-Guaranteed Code Generation via Constrained Decoding
- Blog: Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo
- Blog: An Empirical Study of Building a Strong Baseline for Constituency Parsing
- Blog: Multilingual Pre-training with Universal Dependency Learning
- Blog: Token Alignment via Character Matching for Subword Completion
- Blog: Gram2Token: Enabling Run-time GPU-Native Grammar-Constrained Decoding for LLMs
- Blog: Structural Adapters in Pretrained Language Models for AMR-to-Text Generation
- Blog: XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models
- Blog: Semantics-Aware BERT for Language Understanding
- Blog: Modeling Graph Structure in Transformer for Better AMR-to-Text Generation
- Blog: AtTGen: Attribute Tree Generation for Real-World Attribute Joint Extraction
- Blog: Speculative Decoding for Verilog: Speed and Quality, All in One
- Blog: Learning to Map Frequent Phrases to Sub-Structures of Meaning Representation for Neural Semantic Parsing
- Blog: DoughnutPRIS at TAC KBP 2016
- Blog: Enhancing BERT for Lexical Normalization
- Blog: FPAI at SemEval-2020 Task 10: A Query Enhanced Model with RoBERTa for Emphasis Selection
History & citation
Current · Permanent link
- This direction split from Reconciling Sub-word Tokenization with Structural Constraints (54% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_subword_to_word_alignment_b1fe5fbd,
title = {subword-to-word alignment},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/subword-to-word-alignment/rdr_b1fe5fbd5d124bb4ad9eef9df3160be5},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_subword_to_word_alignment_b1fe5fbd_v1,
title = {subword-to-word alignment},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/subword-to-word-alignment/rdr_b1fe5fbd5d124bb4ad9eef9df3160be5/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}