تهدف توليد السؤال الطبيعي (QG) إلى توليد أسئلة من مقطع، ويتم الرد على الأسئلة التي تم إنشاؤها من المقطع.معظم النماذج مع نموذج الأداء الحديث النص الذي تم إنشاؤه سابقا في كل خطوة فك التشفير.ومع ذلك، (1) يتجاهلون معلومات الهيكل الغني المخفية في النص الذي تم إنشاؤه سابقا.(2) يتجاهلون تأثير الكلمات المنسوخة على مرور.ندرك أن المعلومات في الكلمات التي تم إنشاؤها مسبقا بمثابة معلومات مساعدة في الجيل اللاحق.لمعالجة هذه المشكلات، نقوم بتصميم وحدة فك الترميز المستندة إلى شبكة الرسم البياني للتكرار (IGND) لنموذج الجيل السابق باستخدام شبكة عصبية رسم بيانية في كل خطوة فك التشفير.علاوة على ذلك، يلتقط نموذج الرسم البياني لدينا علاقات التبعية في المقطع الذي يعزز الجيل.توضح النتائج التجريبية أن نموذجنا يتفوق على النماذج الحديثة مع مهام QG على مستوى الجملة على مجموعات بيانات الفريق وماركو.
Natural question generation (QG) aims to generate questions from a passage, and generated questions are answered from the passage. Most models with state-of-the-art performance model the previously generated text at each decoding step. However, (1) they ignore the rich structure information that is hidden in the previously generated text. (2) they ignore the impact of copied words on the passage. We perceive that information in previously generated words serves as auxiliary information in subsequent generation. To address these problems, we design the Iterative Graph Network-based Decoder (IGND) to model the previous generation using a Graph Neural Network at each decoding step. Moreover, our graph model captures dependency relations in the passage that boost the generation. Experimental results demonstrate that our model outperforms the state-of-the-art models with sentence-level QG tasks on SQuAD and MARCO datasets.
References used
https://aclanthology.org/
The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge from large
Understanding speaker's feelings and producing appropriate responses with emotion connection is a key communicative skill for empathetic dialogue systems. In this paper, we propose a simple technique called Affective Decoding for empathetic response
Due to efficient end-to-end training and fluency in generated texts, several encoder-decoder framework-based models are recently proposed for data-to-text generations. Appropriate encoding of input data is a crucial part of such encoder-decoder model
Despite excellent performance on tasks such as question answering, Transformer-based architectures remain sensitive to syntactic and contextual ambiguities. Question Paraphrasing (QP) offers a promising solution as a means to augment existing dataset
Amidst rising mental health needs in society, virtual agents are increasingly deployed in counselling. In order to give pertinent advice, counsellors must first gain an understanding of the issues at hand by eliciting sharing from the counsellee. It