Search Results for author:
Found 37 papers, 9 papers with code
Getting to Production with Few-shot Natural Language Generation Models
In this paper, we study the utilization of pre-trained language models to enable few-shotNatural Language Generation (NLG) in task-oriented dialog systems.
Neural NLG for Methodius: From RST Meaning Representations to Texts
While classic NLG systems typically made use of hierarchically structured content plans that included discourse relations as central components, more recent neural approaches have mostly mapped simple, flat inputs to texts without representing discourse relations explicitly.
Leveraging Large Pretrained Models for WebNLG 2020
In this paper, we report experiments on finetuning large pretrained models to realize resource description framework (RDF) triples to natural language.
Structure-to-Text Generation with Self-Training, Acceptability Classifiers and Context-Conditioning for the GEM Shared Task
We explore the use of self-training and acceptability classifiers with pre-trained models for natural language generation in structure-to-text settings using three GEM datasets (E2E, WebNLG-en, Schema-Guided Dialog).
Building Adaptive Acceptability Classifiers for Neural NLG
We propose a novel framework to train models to classify acceptability of responses generated by natural language generation (NLG) models, improving upon existing sentence transformation and model-based approaches.
Neural Methodius Revisited: Do Discourse Relations Help with Pre-Trained Models Too?
Recent developments in natural language generation (NLG) have bolstered arguments in favor of re-introducing explicit coding of discourse relations in the input to neural models.
Generating Discourse Connectives with Pre-trained Language Models: Conditioning on Discourse Relations Helps Reconstruct the PDTB
Our results suggest that including discourse relation information in the input of the model significantly improves the consistency with which it produces a correctly realized discourse relation in the output.
Self-Training for Compositional Neural NLG in Task-Oriented Dialogue
Neural approaches to natural language generation in task-oriented dialogue have typically required large amounts of annotated training data to achieve satisfactory performance, especially when generating from compositional inputs.
When is Tree Search Useful for LLM Planning? It Depends on the Discriminator
In this paper, we examine how large language models (LLMs) solve multi-step problems under a language agent framework with three components: a generator, a discriminator, and a planning method.
Text-to-SQL Error Correction with Language Models of Code
Thus, we propose a novel representation for SQL queries and their edits that adheres more closely to the pre-training corpora of language models of code.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims.
Towards Transparent Interactive Semantic Parsing via Step-by-Step Correction
In this work, we investigate an interactive semantic parsing framework that explains the predicted logical form step by step in natural language and enables the user to make corrections through natural-language feedback for individual steps.
Best Practices for Data-Efficient Modeling in NLG:How to Train Production-Ready Neural Models with Less Data
In this paper, we present approaches that have helped us deploy data-efficient neural solutions for NLG in conversational systems to production.
The OSU/Facebook Realizer for SRST 2019: Seq2Seq Inflection and Serialized Tree2Tree Linearization
We describe our exploratory system for the shallow surface realization task, which combines morphological inflection using character sequence-to-sequence models with a baseline linearizer that implements a tree-to-tree model using sequence-to-sequence models on serialized trees.
A Tree-to-Sequence Model for Neural NLG in Task-Oriented Dialog
Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems.
Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue
Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems.
LSTM Hypertagging
Hypertagging, or supertagging for surface realization, is the process of assigning lexical categories to nodes in an input semantic graph.
The OSU Realizer for SRST `18: Neural Sequence-to-Sequence Inflection and Incremental Locality-Based Linearization
Surface realization is a nontrivial task as it involves taking structured data and producing grammatically and semantically correct utterances.
Using Paraphrasing and Memory-Augmented Models to Combat Data Sparsity in Question Interpretation with a Virtual Patient Dialogue System
When interpreting questions in a virtual patient dialogue system one must inevitably tackle the challenge of a long tail of relatively infrequently asked questions.
Madly Ambiguous: A Game for Learning about Structural Ambiguity and Why It's Hard for Computers
Madly Ambiguous is an open source, online game aimed at teaching audiences of all ages about structural ambiguity and why it{'}s hard for computers.
Breaking NLP: Using Morphosyntax, Semantics, Pragmatics and World Knowledge to Fool Sentiment Analysis Systems
This paper describes our {``}breaker{''} submission to the 2017 EMNLP {``}Build It Break It{''} shared task on sentiment analysis.
Combining CNNs and Pattern Matching for Question Interpretation in a Virtual Patient Dialogue System
For medical students, virtual patient dialogue systems can provide useful training opportunities without the cost of employing actors to portray standardized patients.
A Corpus of Word-Aligned Asked and Anticipated Questions in a Virtual Patient Dialogue System
We present a corpus of virtual patient dialogues to which we have added manually annotated gold standard word alignments.
