Trainable Methods for Surface Natural Language Generation

We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked only with domainspecific semantic attributes, while the last system, called NLG3, requires a corpus marked with both semantic attributes and syntactic dependency information. All systems attempt to produce a grammatical natural language phrase from a domain-specific semantic representation. NLG1 serves a baseline system and uses phrase frequencies to generate a whole phrase in one step, while NLG2 and NLG3 use maximum entropy probability models to individually generate each word in the phrase. The systems NLG2 and NLG3 learn to determine both the word choice and the word order of the phrase. We present experiments in which we generate phrases to describe flights in the air travel domain.

• Publication year

  2000

• Venue

  Applied Natural Language Processing Conference

• Publication date

  2000-04-29

• Fields of study

  Computer Science

• Identifiers
  arXiv cs/0006028
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Maximum entropy models for natural language ambiguity resolution

  1998cited by this paper
• Generation that Exploits Corpus-Based Statistical Knowledge

  1998influential reference
• A Fast and Portable Realizer for Text Generation Systems

  1997cited by this paper
• Floating Constraints in Lexical Choice

  1997cited by this paper
• KPML development environment - multilingual linguistic resource development and sentence generation

  1996cited by this paper
• An Overview of SURGE: a Reusable Comprehensive Syntactic Realization Component

  1996cited by this paper
• A Maximum Entropy Approach to Natural Language Processing

  1996cited by this paper
• NLG vs. Templates

  1995cited by this paper

• Abstractive text summarization: State of the art, challenges, and improvements

  2024cites this paper
• Compositional Generalization for Data-to-Text Generation

  2023cites this paper
• Parsing and Generation for the Abstract Meaning Representation

  2022cites this paper
• An Optimization of Conversational System Based Conceptual Natural Language Understanding

  2022cites this paper
• Natural Language Generation Using Link Grammar for General Conversational Intelligence

  2021cites this paper
• Decoding Methods in Neural Language Generation: A Survey

  2021cites this paper
• CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training

  2020cites this paper
• Interpretable NLG for Task-oriented Dialogue Systems with Heterogeneous Rendering Machines

  2020cites this paper
• Strategies for Structuring Story Generation

  2019cites this paper
• Gating mechanism based Natural Language Generation for spoken dialogue systems

  2019cites this paper
• A topic-driven language model for learning to generate diverse sentences

  2019cites this paper
• BoFGAN: Towards A New Structure of Backward-or-Forward Generative Adversarial Nets

  2019cites this paper
• Conversational AI: An Overview of Methodologies, Applications & Future Scope

  2019cites this paper
• Deep learning for image captioning: an encoder-decoder architecture with soft attention

  2019cites this paper
• A survey on automatic image caption generation

  2018cites this paper
• Extracting Linguistic Resources from the Web for Concept-to-Text Generation

  2018cites this paper
• Sentence Packaging in Text Generation from Semantic Graphs as a Community Detection Problem

  2018cites this paper
• Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation

  2017cites this paper
• Semantic Refinement GRU-Based Neural Language Generation for Spoken Dialogue Systems

  2017cites this paper
• Neural-based Natural Language Generation in Dialogue using RNN Encoder-Decoder with Semantic Aggregation

  2017cites this paper
• Creating Training Corpora for NLG Micro-Planners

  2017cites this paper
• Enhanced semantic refinement gate for RNN-based neural language generator

  2017cites this paper
• Multimodal Machine Learning: A Survey and Taxonomy

  2017cites this paper
• Syntactic Form and Discourse Function in Natural Language Generation

  2016cites this paper
• Syntactic and referential choice in corpus-based generation: modeling source, context and interactions

  2016influential citation
• Marie Sk lodowska-Curie Actions ( MSCA ) Innovative Training Networks ( ITN ) H 2020-MSCA-ITN-2014

  2015cites this paper
• D2.3.1 Overview and Comparison of Existing Generators

  2015cites this paper
• Natural language interaction with semantic web ontologies

  2015cites this paper
• Natural laNguage geNeratioN, ParaPhrasiNg aNd summarizatioN of user reviews with recurreNt Neural Networks

  2015cites this paper
• Generating and Simplifying Sentences

  2014cites this paper
• 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue

  2014cites this paper
• Deep stochastic sentence generation : resources and strategies

  2014cites this paper
• From captions to visual concepts and back

  2014cites this paper
• Context-Sensitive Natural Language Generation: From Knowledge-Driven to Data-Driven Techniques

  2014cites this paper
• Word Ordering with Phrase-Based Grammars

  2014cites this paper
• Text corpus for natural language story-telling sentence generation: A design and evaluation

  2014cites this paper
• Hierarchical joint learning for natural language generation

  2013cites this paper
• Creating a natural language summary from a compressed causal graph

  2013cites this paper
• Combining Referring Expression Generation and Surface Realization: A Corpus-Based Investigation of Architectures

  2013cites this paper
• Portuguese text generation using factored language models

  2013cites this paper
• Indoor Scene Knowledge Acquisition Using Natural Language Descriptions

  2013cites this paper
• Generating Natural Language Descriptions from OWL Ontologies: the NaturalOWL System

  2013cites this paper
• Unsupervised Learning Summarization Templates from Concise Summaries

  2013cites this paper
• Portuguese Text Generation from Large Corpora

  2012cites this paper
• GeneratingNaturalLanguageDescriptionsfromOWLOntologies:A DetailedPresentationoftheNaturalOWLSystem

  2012cites this paper
• Underspecifying and Predicting Voice for Surface Realisation Ranking

  2011cites this paper
• Designing service-oriented chatbot systems using a construction grammar-driven natural language generation system

  2011cites this paper
• Data-Driven Response Generation in Social Media

  2011cites this paper
• Optimising Natural Language Generation Decision Making For Situated Dialogue

  2011cites this paper
• A Brief Introduction to Natural Language Understanding and Generation

  2010cites this paper
• Tuning Machine-Learning Algorithms for Battery-Operated Portable Devices

  2010cites this paper
• Research progress on system-generated language: From the psycholinguistic perspective

  2010cites this paper
• Text Generation for Brazilian Portuguese: the Surface Realization Task

  2010cites this paper
• Evaluating a dialog language generation system: comparing the mountain system to other NLG approaches

  2010cites this paper
• Sentence Correction Incorporating Relative Position and Parse Template Language Models

  2010cites this paper
• Dependency Graph Based Sentence Fusion and Compression

  2010cites this paper
• Data-driven Natural Language Generation: Making Machines Talk Like Humans Using Natural Corpora

  2010cites this paper
• A Hybrid Tree Framework for Semantic Parsing and Natural Language Generation

  2009cites this paper
• Dependency Based Chinese Sentence Realization

  2009cites this paper
• Empirical Realization Ranking

  2009cites this paper
• Automatic correction of grammatical errors in non-native English text

  2009cites this paper
• Statistical methods in natural language understanding and spoken dialogue systems

  2009cites this paper
• Symbolic-to-statistical Hybridization: Extending Generation-heavy Machine Translation

  2009cites this paper
• Symbolic-to-statistical hybridization: extending generation-heavy machine translation

  2009cites this paper
• A NLG-based Application for Walking Directions

  2009cites this paper
• Which Semantics for Neighbourhood Semantics?

  2009cites this paper
• M OUNTAIN : A Translation-based Approach to Natural Language Generation for Dialog Systems

  2009cites this paper
• Automatic generation of weather forecast texts using comprehensive probabilistic generation-space models

  2008cites this paper
• Text-to-text generation by monolingual machine translation

  2008cites this paper
• Word Order Correction for Language Transfer Using Relative Position Language Modeling

  2008cites this paper
• Dependency-based n-gram models for general purpose sentence realisation

  2008cites this paper
• User acceptance model driven design

  2008cites this paper
• Exploiting Multi-Word Units in History-Based Probabilistic Generation

  2007cites this paper
• ¿Qué es la generación de lenguaje natural? Una visión general sobre el proceso de generación

  2007cites this paper
• The German Vorfeld and Local Coherence

  2007cites this paper
• Concept-Based Speech-to-Speech Translation Using Maximum Entropy Models for Statistical Natural Concept Generation

  2006cites this paper
• Combining Machine Learning and Rule-Based Approaches in

  2006cites this paper
• Improving Text Fluency by Reordering of Constituents

  2006cites this paper
• Expert Tutoring and Natural Language Feedback in Intelligent Tutoring Systems

  2006cites this paper
• Combining machine learning and rule-based approaches in Spanish syntactic generation

  2006cites this paper
• Robust PCFG-Based Generation Using Automatically Acquired LFG Approximations

  2006cites this paper
• Combining Linguistic and Statistical Methods for Bi-directional English Chinese Translation in the Flight Domain

  2006cites this paper
• Modeling the dative alternation with automatically extracted features

  2006cites this paper
• Automatic Grammar Correction for

  2006cites this paper
• Automatic grammar correction for second-language learners

  2006cites this paper
• Building Surface Realizers Automatically from Corpora ∗ Huayan Zhong and

  2005cites this paper
• Indirect supervised learning of strategic generation logic

  2005cites this paper
• A hybrid dialogue strategy for speech-enabled mobile commerce

  2005cites this paper
• A Domain-Specific Statistical Surface Realizer

  2005cites this paper
• A Case-Based Reasoning Approach for Speech Corpus Generation

  2005cites this paper
• Spatial Descriptions as Referring Expressions in the MapTask Domain

  2005cites this paper
• Statistical Generation: Three Methods Compared and Evaluated

  2005cites this paper
• The Types and Distributions of Errors in a Wide Coverage Surface Realizer Evaluation

  2005cites this paper
• Use of maximum entropy in natural word generation for statistical concept-based speech-to-speech translation

  2005cites this paper
• Discourse context and statistical natural language generation

  2005cites this paper
• Japanese case analysis based on machine learning method that uses borrowed supervised data

  2005cites this paper
• Vers une meilleure utilisabilité des mémoires de traduction, fondée sur un alignement sous-phrastique

  2005cites this paper
• Language generation and speech synthesis in dialogues for language learning

  2004cites this paper
• On feature selection in maximum entropy approach to statistical concept-based speech-to-speech translation

  2004cites this paper
• Applications of Language Modeling in Speech-To-Speech Translation

  2004cites this paper