paper-with-me

홈 › Papers

Expanding, Retrieving and Infilling: Diversifying Cross-Domain Question Generation with Flexible Templates

2021-04-01 · EACL 2021 2 · Xiaojing Yu, Anxiao Jiang

Sequence-to-sequence based models have recently shown promising results in generating high-quality questions. However, these models are also known to have main drawbacks such as lack of diversity and bad sentence structures. In this paper, we focus on question generation over SQL database and propose a novel framework by expanding, retrieving, and infilling that first incorporates flexible templates with a neural-based model to generate diverse expressions of questions with sentence structure guidance. Furthermore, a new activation/deactivation mechanism is proposed for template-based sequence-to-sequence generation, which learns to discriminate template patterns and content patterns, thus further improves generation quality. We conduct experiments on two large-scale cross-domain datasets. The experiments show that the superiority of our question generation method in producing more diverse questions while maintaining high quality and consistency under both automatic evaluation and human evaluation.

📄 PDF Abstract BibTeX

Code (1)

xiaojingyu92/eriqg 공식 구현 pytorch

Tasks

DiversityQuestion GenerationQuestion-GenerationSentence

Similar Papers 제목 키워드 기반

$\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization

2024-10-07 · Dylan Zhang, Justin Wang, Francois Charton

Understanding and accurately following instructions is critical for large language models (LLMs) to be effective across diverse tasks. In this work, we rigorously examine the key factors that enable models to generalize …

DiversityInstruction Following

Diversifying Agent's Behaviors in Interactive Decision Models

2022-03-06 · Yinghui Pan, Hanyi Zhang, Yifeng Zeng, Biyang Ma 외

Modelling other agents' behaviors plays an important role in decision models for interactions among multiple agents. To optimise its own decisions, a subject agent needs to model what other agents act simultaneously in a…

Diversity

Enabling Language Models to Fill in the Blanks

2020-05-11 · ACL 2020 6 · Chris Donahue, Mina Lee, Percy Liang

We present a simple approach for text infilling, the task of predicting missing spans of text at any position in a document. While infilling could enable rich functionality especially for writing assistance tools, more a…

Language ModelingLanguage ModellingText Infilling

Towards Probabilistically-Sound Beam Search with Masked Language Models

2024-02-22 · Creston Brooks, Robert Calef, Charlie Cowen-Breen, Anna Sappington

Beam search with masked language models (MLMs) is challenging in part because joint probability distributions over sequences are not readily available, unlike for autoregressive models. However, estimating such distribut…

Ancient Text RestorationText Infilling

A Simple yet Effective Framework for Few-Shot Aspect-Based Sentiment Analysis

2023-07-18 · SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval 2023 7 · Zengzhi, Wang; Qiming, Xie; Rui, Xia

The pre-training and fine-tuning paradigm has become the mainstream framework in the field of Aspect-Based Sentiment Analysis (ABSA). Although it has achieved sound performance in the domains containing enough fine-grain…

Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Aspect Term Extraction and Sentiment ClassificationSentiment Analysis+2