output
20152024
most citedFeature relevance quantification in explainable AI: A causal problem

156 citations

Showing 2020 · cs.CLShow all

26 papers · 2 filters

cs.CL2020

Using multiple ASR hypotheses to boost i18n NLU performance

Charith Peris, Gokmen Oz, Khadige Abboud +3

Current voice assistants typically use the best hypothesis yielded by their Automatic Speech Recognition (ASR) module as input to their Natural Language Understanding (NLU) module,…

cs.CL2020

Generative Adversarial Networks for Annotated Data Augmentation in Data Sparse NLU

Olga Golovneva, Charith Peris

Data sparsity is one of the key challenges associated with model development in Natural Language Understanding (NLU) for conversational agents. The challenge is made more complex b…

cs.CL2020

Delexicalized Paraphrase Generation

Boya Yu, Konstantine Arkoudas, Wael Hamza

We present a neural model for paraphrasing and train it to generate delexicalized sentences. We achieve this by creating training data in which each input is paired with a number o…

cs.CL20203 cited

Dialog Simulation with Realistic Variations for Training Goal-Oriented Conversational Systems

Chien-Wei Lin, Vincent Auvray, Daniel Elkind +10

Goal-oriented dialog systems enable users to complete specific goals like requesting information about a movie or booking a ticket. Typically the dialog system pipeline contains mu…

cs.CL20201 cited

To What Degree Can Language Borders Be Blurred In BERT-based Multilingual Spoken Language Understanding?

Quynh Do, Judith Gaspers, Tobias Roding +1

This paper addresses the question as to what degree a BERT-based multilingual Spoken Language Understanding (SLU) model can transfer knowledge across languages. Through experiments…

cs.CL202023 cited

Optimal Subarchitecture Extraction For BERT

Adrian de Wynter, Daniel J. Perry

We extract an optimal subset of architectural parameters for the BERT architecture from Devlin et al. (2018) by applying recent breakthroughs in algorithms for neural architecture…