Measuring the ‘I don’t know’ Problem through the Lens of Gricean Quantity

Khayrallah, Huda; Sedoc, João

doi:10.18653/v1/2021.naacl-main.450

Cited by 2 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…in the training data; in dialogue modelling it has been referred to as the "I don't know" problem (Khayrallah and Sedoc, 2021).…”

Section: Reviewmentioning

confidence: 99%

Improving Specificity in Review Response Generation with Data-Driven Data Filtering

Kew¹,

Völk²

2022

Proceedings of the Fifth Workshop on E-Commerce and NLP (ECNLP 5)

View full text Add to dashboard Cite

Responding to online customer reviews has become an essential part of successfully managing and growing a business both in e-commerce and the hospitality and tourism sectors. Recently, neural text generation methods intended to assist authors in composing responses have been shown to deliver highly fluent and natural looking texts. However, they also tend to learn a strong, undesirable bias towards generating overly generic, one-size-fits-all outputs to a wide range of inputs. While this often results in 'safe', high-probability responses, there are many practical settings in which greater specificity is preferable. In this work we examine the task of generating more specific responses for online reviews in the hospitality domain by identifying generic responses in the training data, filtering them and fine-tuning the generation model. We experiment with a range of data-driven filtering methods and show through automatic and human evaluation that, despite a 60% reduction in the amount of training data, filtering helps to derive models that are capable of generating more specific, useful responses.

show abstract

“…in the training data; in dialogue modelling it has been referred to as the "I don't know" problem (Khayrallah and Sedoc, 2021).…”

Section: Reviewmentioning

confidence: 99%