Papers with surface realization
FeTaQA: Free-form Table Question Answering (2022.tacl-1)
Copied to clipboard
Linyong Nan, Chiachun Hsieh, Ziming Mao, Xi Victoria Lin, Neha Verma, Rui Zhang, Wojciech Kryściński, Hailey Schoelkopf, Riley Kong, Xiangru Tang, Mutethia Mutuma, Ben Rosand, Isabel Trindade, Renusree Bandaru, Jacob Cunningham, Caiming Xiong, Dragomir Radev, Dragomir Radev
| Challenge: | Existing table-based question answering datasets lack advanced information-based questions that require reasoning and integration of information pieces retrieved from structured knowledge sources. |
| Approach: | They propose a dataset with 10K Wikipedia-based table, question, free-form answer, supporting table cells pairs that can be used to generate an answer. |
| Outcome: | The proposed dataset has 10K Wikipedia-based table, question, free-form answer, supporting table cells pairs. |
DepDist: Surface realization via regex and learned dependency-distance tolerance (D19-63)
Copied to clipboard
| Challenge: | The paper describes a method of inflecting and linearizing a lemmatized dependency tree by: (1) determining a regular expression and substitution to describe each productive wordform rule; (2) learning the dependency distance tolerance for each head-dependent pair; (3) topologically sorting the DAG into a surface realization based on edge weight. |
| Approach: | They propose a method of inflecting and linearizing a lemmatized dependency tree by learning the dependency distance tolerance for each head-dependent pair and topologically sorting the DAG into a surface order based on edge weight. |
| Outcome: | The proposed method generates a morphologically inflected surface order for 11 languages across 18 treebanks. |
Natural Language Generation by Hierarchical Decoding with Linguistic Patterns (N18-2)
Copied to clipboard
| Challenge: | a common and mostly adopted method is the rule-based (or template-based) method for natural language generation. |
| Approach: | They propose a hierarchical decoding NLG model based on linguistic patterns in different levels. |
| Outcome: | The proposed method outperforms the traditional one with a smaller model size. |
A Cascade Approach to Neural Abstractive Summarization with Content Selection and Fusion (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing systems that perform content selection and surface realization are not able to provide sufficient training data for news summarization. |
| Approach: | They propose to use a cascade architecture to perform content selection and surface realization together to generate abstracts. |
| Outcome: | The proposed architecture outperforms or outranks existing systems in terms of content selection and surface realization. |
Select and Attend: Towards Controllable Content Selection in Text Generation (D19-1)
Copied to clipboard
| Challenge: | Recent neural network models conflate content selection and surface realization into a black-box architecture, resulting in content to be described in text cannot be explicitly controlled. |
| Approach: | They propose to decouple content selection from the decoder to allow finer-grained control over the generation. |
| Outcome: | The proposed model can be trained end-to-end without human annotations and achieves promising results in data-totext and headline generation tasks. |
Sentence-Level Content Planning and Style Specification for Neural Text Generation (D19-1)
Copied to clipboard
| Challenge: | Recent advances in text generation systems often produce incoherent and unfaithful outputs . a novel automated text generation system takes into account content selection, text planning, and surface realization. |
| Approach: | They propose an end-to-end trained two-step text generation model that considers sentence-level content planners and language styles. |
| Outcome: | The proposed model outperforms competing models in three domains with diverse topics and varying language styles. |
Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation (P19-1)
Copied to clipboard
| Challenge: | Existing methods for table-to-text generation use encoder-decoder framework, but lack of large parallel data is a problem for many domains. |
| Approach: | They propose a model to separate table-to-text generation into two stages: key fact prediction and surface realization. |
| Outcome: | The proposed model achieves 27.34 BLEU score with only 1,000 parallel data, while the baseline model only achieves 9.71 BLUE score. |
Learning to Select, Track, and Generate for Data-to-Text (P19-1)
Copied to clipboard
Hayate Iso, Yui Uehara, Tatsuya Ishigaki, Hiroshi Noji, Eiji Aramaki, Ichiro Kobayashi, Yusuke Miyao, Naoaki Okazaki, Hiroya Takamura
| Challenge: | Existing models often refer to the same data record multiple times. |
| Approach: | They propose a data-to-text generation model with two modules, one for tracking and the other for text generation. |
| Outcome: | The proposed model outperforms existing models even without writer information in all evaluation metrics and contributes to content planning and surface realization. |
Contextualization of Morphological Inflection (N19-1)
Copied to clipboard
| Challenge: | In this paper, we isolate the task of predicting a fully inflected sentence from its partially lemmatized version. |
| Approach: | They propose a task that requires morphological features to be inferred from sentential context . they propose morphology-based models that explicitly reconstruct morphologic features before predicting inflected forms . |
| Outcome: | The proposed model is able to predict inflected sentences without relying on morphological annotations. |
DDGIP: Radiology Report Generation Through Disease Description Graph and Informed Prompting (2025.findings-naacl)
Copied to clipboard
| Challenge: | Automatic radiology report generation is challenging due to inherent biases in medical imaging data. |
| Approach: | They propose a disease description graph that encapsulates comprehensive and pertinent disease information. |
| Outcome: | The proposed model outperforms state-of-the-art models on two widely-used datasets . the proposed model is based on a three-layer decoder and improves on existing models . |
Enhancing Content Planning for Table-to-Text Generation with Data Understanding and Verification (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Table-to-text models that select and order salient data and verbalize them fluently are lacking in content planning stage. |
| Approach: | They propose to enhance neural content planning by understanding data values with contextual numerical value representations that bring the sense of value comparison into content planning. |
| Outcome: | The proposed model outperforms existing systems with respect to content planning metrics on ROTOWIRE and MLB datasets. |
Towards Zero-Shot Conditional Summarization with Adaptive Multi-Task Fine-Tuning (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for automatic summarization are limited to providing general-purpose summaries . ad-hoc nature of the task can cause arbitrary summarizing, causing a problem . |
| Approach: | They propose to use multi-task fine-tuning to enable conditional summarization on five tasks . they propose to combine two novel "online" or adaptive task-mixing strategies . |
| Outcome: | The proposed method improves zero-shot conditional summarization quality on five tasks. |
Semantic Composition with PSHRG for Derivation Tree Reconstruction from Graph-Based Meaning Representations (2022.acl-long)
Copied to clipboard
| Challenge: | General graph-based meaning representations (MRs) that model sentence-level semantics aim to provide interpretable intermediate representations that are application-and domain-independent. |
| Approach: | They propose a probabilistic synchronous hyperedge replacement grammar for generating derivation trees from meaning representation graphs with a data-driven approach. |
| Outcome: | The proposed formalism approximates the semantic composition of DMRS graphs and recovers derivations that license them. |
Plan ahead: Self-Supervised Text Planning for Paragraph Completion Task (2020.emnlp-main)
Copied to clipboard
| Challenge: | despite the success of contextualized language models, language models cannot capture textual coherence of a long, multi-sentence document. |
| Approach: | They propose a paragraph completion task that predicts masked sentences in a sentence . they propose SSPlanner that predict what to say first and guides the pretrained model . |
| Outcome: | The proposed model outperforms baseline generation models on the paragraph completion task in automatic and human evaluation. |
Shape of Synth to Come: Why We Should Use Synthetic Data for English Surface Realization (2020.acl-main)
Copied to clipboard
| Challenge: | In the Surface Realization Shared Tasks of 2018 and 2019, there was little difference in absolute performance between systems trained with and without synthetic data. |
| Approach: | They propose to use synthetic data to explore approaches to surface realization from Universal-Dependency-like trees to surface strings for several languages. |
| Outcome: | The proposed method improves performance of a previously state-of-the-art system by 8 BLEU points over the previous system on the English dataset. |
CircuitSynth: Reliable Synthetic Data Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches lack mechanisms to balance linguistic expressivity with formal guarantees regarding validity and coverage. |
| Approach: | They propose a neuro-symbolic framework that decouples semantic reasoning from surface realization. |
| Outcome: | The proposed framework achieves 100% Schema Validity even in complex logic puzzles where unconstrained baselines fail (12.4%) while outperforming state-of-the-art methods in rare-combination coverage. |