InFillmore: Frame-Guided Language Generation with Bidirectional Context
Not on the map. Why?
Abstract (arXiv)
We propose a structured extension to bidirectional-context conditional language generation, or "infilling," inspired by Frame Semantic theory (Fillmore, 1976). Guidance is provided through two approaches: (1) model fine-tuning, conditioning directly on observed symbolic frames, and (2) a novel extension to disjunctive lexically constrained decoding that leverages frame semantic lexical units. Automatic and human evaluations confirm that frame-guided generation allows for explicit manipulation of intended infill semantics, with minimal loss in distinguishability from human-generated text. Our methods flexibly apply to a variety of use scenarios, and we provide a codebase and interactive demo available from https://nlp.jhu.edu/demos/infillmore.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 32 of its 50 references that are in the map. First posted on arXiv 8 Mar 2021.
Builds on
32 of 50 references.
References · 32
- 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
- 2019The Curious Case of Neural Text Degenerationcited by 2,881
- 2018Hierarchical Neural Story Generationcited by 1,182
- 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
- 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
- 2017Lexically Constrained Decoding for Sequence Generation Using Grid Beam Searchcited by 234
- 2018Plan-And-Write: Towards Better Automatic Storytellingcited by 232
- 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 181
- 2020NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraintscited by 146
- 2019Strategies for Structuring Story Generationcited by 124
- 2020Enabling Language Models to Fill in the Blankscited by 121
- 2020PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Trackingcited by 104
20 more
- 2018CGMH: Constrained Sentence Generation by Metropolis-Hastings Samplingcited by 93
- 2020Content Planning for Neural Story Generation with Aristotelian Rescoringcited by 92
- 2019Counterfactual Story Reasoning and Generationcited by 87
- 2017Event Representations for Automated Story Generation with Deep Neural Netscited by 62
- 2020Lexically Constrained Neural Machine Translation with Levenshtein Transformercited by 45
- 2019Plan, Write, and Revise: an Interactive System for Open-Domain Story Generationcited by 43
- 2018A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generationcited by 42
- 2019ParaBank: Monolingual Bitext Generation and Sentential Paraphrasing via Lexically-constrained Neural Machine Translationcited by 38
- 2017Story Generation from Sequence of Independent Short Descriptionscited by 26
- 2020Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generationcited by 26
- 2021LOME: Large Ontology Multilingual Extractioncited by 23
- 2020Toward Better Storylines with Sentence-Level Language Modelscited by 14
- 2019Neural Machine Translation with Explicit Phrase Alignmentcited by 12
- 2018BFGAN: Backward and Forward Generative Adversarial Networks for Lexically Constrained Sentence Generationcited by 9
- 2020COD3S: Diverse Generation with Discrete Semantic Signaturescited by 9
- 2019Neural Machine Translation with Noisy Lexical Constraintscited by 8
- 2019WriterForcing: Generating more interesting story endingscited by 4
- 2020Iterative Paraphrastic Augmentation with Discriminative Span Alignmentcited by 4
- 2019Learning Efficient Lexically-Constrained Neural Machine Translation with External Memorycited by 2
- 2019Learning to Predict Explainable Plots for Neural Story Generationcited by 2
Built on by
Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 1.
2 papers.