paper-with-me

홈 › Papers

Syntax-driven Iterative Expansion Language Models for Controllable Text Generation

2020-04-05 · EMNLP (spnlp) 2020 11 · Noe Casas, José A. R. Fonollosa, Marta R. Costa-jussà

The dominant language modeling paradigm handles text as a sequence of discrete tokens. While that approach can capture the latent structure of the text, it is inherently constrained to sequential dynamics for text generation. We propose a new paradigm for introducing a syntactic inductive bias into neural text generation, where the dependency parse tree is used to drive the Transformer model to generate sentences iteratively. Our experiments show that this paradigm is effective at text generation, with quality between LSTMs and Transformers, and comparable diversity, requiring less than half their decoding steps, and its generation process allows direct control over the syntactic constructions of the generated text, enabling the induction of stylistic variations.

📄 PDF Abstract BibTeX arXiv:2004.02211

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityInductive BiasLanguage ModelingLanguage ModellingText Generation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Controllability Test for Nonlinear Datatic Systems

2024-05-15 · Yujie Yang, Letian Tao, Likun Wang, Shengbo Eben Li

Controllability is a fundamental property of control systems, serving as the prerequisite for controller design. While controllability test is well established in modelic (i.e., model-driven) control systems, extending i…

DanceCrafter: Fine-Grained Text-Driven Controllable Dance Generation via Choreographic Syntax

2026-04-20 · Hang Yuan, Xiaolin Hu, Yan Wan, Menglin Gao 외 arxiv

Text-driven controllable dance generation remains under-explored, primarily due to the severe scarcity of high-quality datasets and the inherent difficulty of articulating complex choreographies. Characterizing dance is …

ControllableGPT: A Ground-Up Designed Controllable GPT for Molecule Optimization

2025-02-15 · Xuefeng Liu, Songhao Jiang, Bo Li, Rick Stevens

Large Language Models (LLMs) employ three popular training approaches: Masked Language Models (MLM), Causal Language Models (CLM), and Sequence-to-Sequence Models (seq2seq). However, each approach has its strengths and l…

InteracSPARQL: An Interactive System for SPARQL Query Refinement Using Natural Language Explanations

2025-11-03 · Xiangru Jian, Zhengyuan Dong, M. Tamer Özsu arxiv

In recent years, querying semantic web data using SPARQL has remained challenging, especially for non-expert users, due to the language's complex syntax and the prerequisite of understanding intricate data structures. To…

ADORE: Iterative Query Expansion with Retrieval-Grounded Relevance Feedback

2026-06-11 · Amin Bigdeli, Negar Arabzadeh, Radin Hamidi Rad, Sajad Ebrahimi 외 arxiv

LLM-based query expansion improves retrieval by enriching the original query with additional context. Yet most methods remain generation-driven, producing plausible pseudo-documents or expansions without checking how the…