Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Survey of Approaches to Automatic Question Generation:from 2019 to Early 2021
دراسة استقصائية للنهج لتوليد السؤال التلقائي: من عام 2019 إلى أوائل 2021
204
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
لتوفير تحليل الأبحاث الأخيرة من جيل الأسئلة التلقائي من النص، أجرينا مسح 9 أوراق بين عامي 2019 إلى أوائل 2021، تم استرجاعها من الورق مع التعليمات البرمجية (PWC).تتبع بحثنا الاستطلاع الذي أبلغ عنه كردي وآخرون. (2020)، حيث يتم توفير تحليل 93 ورقة من عام 2014 إلى مبادر عام 2019.لقد قمنا بتحليل الخمسين من الجوانب بما في ذلك: (1) الغرض من جيل السؤال، (2) طريقة التوليد، و (3) تقييم.وجدنا أن النهج الحديثة تميل إلى الاعتماد على المعلومات الدلالية والنماذج القائمة على المحولات تجذب اهتماما متزايدا لأنها أكثر كفاءة.من ناحية أخرى، نظرا لأنه لا يوجد أي مقياس تقييم تلقائي تم الاعتراف على نطاق واسع المصمم لجيل السؤال، يعتمد الباحثون مقاييس مهام معالجة اللغة الطبيعية الأخرى لمقارنة الأنظمة المختلفة.
To provide analysis of recent researches of automatic question generation from text,we surveyed 9 papers between 2019 to early 2021, retrieved from Paper with Code(PwC). Our research follows the survey reported by Kurdi et al.(2020), in which analysis of 93 papers from 2014 to early2019 are provided. We analyzed the 9papers from aspects including: (1) purpose of question generation, (2) generation method, and (3) evaluation. We found that recent approaches tend to rely on semantic information and Transformer-based models are attracting increasing interest since they are more efficient. On the other hand,since there isn't any widely acknowledged automatic evaluation metric designed for question generation, researchers adopt metrics of other natural language processing tasks to compare different systems.
References used
https://aclanthology.org/
rate research
Read More
Deep neural networks and huge language models are becoming omnipresent in natural language applications. As they are known for requiring large amounts of training data, there is a growing body of work to improve the performance in low-resource settin
gs. Motivated by the recent fundamental changes towards neural models and the popular pre-train and fine-tune paradigm, we survey promising approaches for low-resource natural language processing. After a discussion about the different dimensions of data availability, we give a structured overview of methods that enable learning when training data is sparse. This includes mechanisms to create additional labeled data like data augmentation and distant supervision as well as transfer learning settings that reduce the need for target supervision. A goal of our survey is to explain how these methods differ in their requirements as understanding them is essential for choosing a technique suited for a specific low-resource setting. Further key aspects of this work are to highlight open issues and to outline promising directions for future research.
Finding the year of writing for a historical text is of crucial importance to historical research. However, the year of original creation is rarely explicitly stated and must be inferred from the text content, historical records, and codicological cl
ues. Given a transcribed text, machine learning has successfully been used to estimate the year of production. In this paper, we present an overview of several estimation approaches for historical text archives spanning from the 12th century until today.
Information extraction is the task of finding structured information
from unstructured or semi-structured text. It is an important task in
text mining and has been extensively studied in various research
communities including natural language proc
essing, information
retrieval and Web mining. It has a wide range of applications in
domains such as biomedical literature mining and business
intelligence. Two fundamental tasks of information extraction are
named entity recognition and relation extraction. The former refers to
finding names of entities such as people, organizations and
locations. The latter refers to finding the semantic relations between
entities.
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) t
hey 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.
Meeting minutes record any subject matter discussed, decisions reached and actions taken at the meeting. The importance of automatic minuting cannot be overstated. In this paper, we present a sliding window approach to automatic generation of meeting
minutes. It aims at addressing issues pertaining to the nature of spoken text, including the lengthy transcript and lack of document structure, which make it difficult to identify salient content to be included in meeting minutes. Our approach combines a sliding-window approach and a neural abstractive summarizer to navigate through the raw transcript to find salient content. The approach is evaluated on transcripts of natural meeting conversations, where we compare results obtained for human transcripts and two versions of automatic transcripts and discuss how and to what extent the summarizer succeeds at capturing salient content.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
