paper-with-me

홈 › Papers

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

2022-05-01 · ECNLP (ACL) 2022 5 · Tannon Kew, Martin Volk

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.

📄 PDF Abstract BibTeX

Code (1)

zurichnlp/specific_hospo_respo 공식 구현 pytorch

Tasks

Response GenerationSpecificityText Generation

Similar Papers 제목 키워드 기반

Linguistically-Informed Specificity and Semantic Plausibility for Dialogue Generation

2019-06-01 · NAACL 2019 6 · Wei-Jen Ko, Greg Durrett, Junyi Jessy Li

Sequence-to-sequence models for open-domain dialogue generation tend to favor generic, uninformative responses. Past work has focused on word frequency-based approaches to improving specificity, such as penalizing respon…

Dialogue GenerationInformativenessRerankingSpecificity

Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review

2026-01-19 · Qian Ruan, Iryna Gurevych arxiv

Author response (rebuttal) writing is a critical stage of scientific peer review that demands substantial author effort. In practice, authors possess domain expertise, author-only information, and response strategies - c…

Response Generation

Learning to Control the Specificity in Neural Response Generation

2018-07-01 · ACL 2018 7 · Ruqing Zhang, Jiafeng Guo, Yixing Fan, Yanyan Lan 외

In conversation, a general response (e.g., {``}I don{'}t know{''}) could correspond to a large variety of input utterances. Previous generative conversational models usually employ a single model to learn the relationshi…

Machine TranslationResponse GenerationSpecificity

Consistent Response Generation with Controlled Specificity

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Junya Takayama, Yuki Arase

We propose a method to control the specificity of responses while maintaining the consistency with the utterances. We first design a metric based on pointwise mutual information, which measures the co-occurrence degree b…

Response GenerationSpecificity

Data-driven Discovery of Biophysical T Cell Receptor Co-specificity Rules

2024-12-18 · Andrew G. T. Pyo, Yuta Nagano, Martina Milighetti, James Henderson 외

The biophysical interactions between the T cell receptor (TCR) and its ligands determine the specificity of the cellular immune response. However, the immense diversity of receptors and ligands has made it challenging to…

DiversitySpecificity