A Survey on Machine Reading Comprehension Systems
- URL: http://arxiv.org/abs/2001.01582v2
- Date: Tue, 20 Oct 2020 20:50:51 GMT
- Title: A Survey on Machine Reading Comprehension Systems
- Authors: Razieh Baradaran, Razieh Ghiasi, and Hossein Amirkhani
- Abstract summary: We present a comprehensive survey on different aspects of machine reading comprehension systems.
We illustrate the recent trends in this field based on 241 reviewed papers from 2016 to 2020.
Our investigations demonstrate that the focus of research has changed in recent years from answer extraction to answer generation.
- Score: 1.5293427903448022
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Machine reading comprehension is a challenging task and hot topic in natural
language processing. Its goal is to develop systems to answer the questions
regarding a given context. In this paper, we present a comprehensive survey on
different aspects of machine reading comprehension systems, including their
approaches, structures, input/outputs, and research novelties. We illustrate
the recent trends in this field based on 241 reviewed papers from 2016 to 2020.
Our investigations demonstrate that the focus of research has changed in recent
years from answer extraction to answer generation, from single to
multi-document reading comprehension, and from learning from scratch to using
pre-trained embeddings. We also discuss the popular datasets and the evaluation
metrics in this field. The paper ends with investigating the most cited papers
and their contributions.
Related papers
- Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges [7.140449861888235]
This review categorizes works in text generation into five main tasks.
For each task, we review their relevant characteristics, sub-tasks, and specific challenges.
Our investigation shows nine prominent challenges common to all tasks and sub-tasks in recent text generation publications.
arXiv Detail & Related papers (2024-05-24T14:38:11Z) - Automated Audio Captioning: an Overview of Recent Progress and New
Challenges [56.98522404673527]
Automated audio captioning is a cross-modal translation task that aims to generate natural language descriptions for given audio clips.
We present a comprehensive review of the published contributions in automated audio captioning, from a variety of existing approaches to evaluation metrics and datasets.
arXiv Detail & Related papers (2022-05-12T08:36:35Z) - Multi Document Reading Comprehension [0.0]
Reading (RC) is a task of answering a question from a given passage or a set of passages.
Recent trials and experiments in the field of Natural Language Processing (NLP) have proved that machines can be provided with the ability to process the text in the passage.
arXiv Detail & Related papers (2022-01-05T16:54:48Z) - Tell Me How to Survey: Literature Review Made Simple with Automatic
Reading Path Generation [16.07200776251764]
How to glean papers worth reading from the massive literature to do a quick survey or keep up with the latest advancement about a specific research topic has become a challenging task.
Existing academic search engines such as Google Scholar return relevant papers by individually calculating the relevance between each paper and query.
We introduce Reading Path Generation (RPG) which aims at automatically producing a path of papers to read for a given query.
arXiv Detail & Related papers (2021-10-12T20:58:46Z) - Open-Retrieval Conversational Machine Reading [80.13988353794586]
In conversational machine reading, systems need to interpret natural language rules, answer high-level questions, and ask follow-up clarification questions.
Existing works assume the rule text is provided for each user question, which neglects the essential retrieval step in real scenarios.
In this work, we propose and investigate an open-retrieval setting of conversational machine reading.
arXiv Detail & Related papers (2021-02-17T08:55:01Z) - Inquisitive Question Generation for High Level Text Comprehension [60.21497846332531]
We introduce INQUISITIVE, a dataset of 19K questions that are elicited while a person is reading through a document.
We show that readers engage in a series of pragmatic strategies to seek information.
We evaluate question generation models based on GPT-2 and show that our model is able to generate reasonable questions.
arXiv Detail & Related papers (2020-10-04T19:03:39Z) - A Survey on Text Classification: From Shallow to Deep Learning [83.47804123133719]
The last decade has seen a surge of research in this area due to the unprecedented success of deep learning.
This paper fills the gap by reviewing the state-of-the-art approaches from 1961 to 2021.
We create a taxonomy for text classification according to the text involved and the models used for feature extraction and classification.
arXiv Detail & Related papers (2020-08-02T00:09:03Z) - Machine Identification of High Impact Research through Text and Image
Analysis [0.4737991126491218]
We present a system to automatically separate papers with a high from those with a low likelihood of gaining citations.
Our system uses both a visual classifier, useful for surmising a document's overall appearance, and a text classifier, for making content-informed decisions.
arXiv Detail & Related papers (2020-05-20T19:12:24Z) - Document Modeling with Graph Attention Networks for Multi-grained
Machine Reading Comprehension [127.3341842928421]
Natural Questions is a new challenging machine reading comprehension benchmark.
It has two-grained answers, which are a long answer (typically a paragraph) and a short answer (one or more entities inside the long answer)
Existing methods treat these two sub-tasks individually during training while ignoring their dependencies.
We present a novel multi-grained machine reading comprehension framework that focuses on modeling documents at their hierarchical nature.
arXiv Detail & Related papers (2020-05-12T14:20:09Z) - ORB: An Open Reading Benchmark for Comprehensive Evaluation of Machine
Reading Comprehension [53.037401638264235]
We present an evaluation server, ORB, that reports performance on seven diverse reading comprehension datasets.
The evaluation server places no restrictions on how models are trained, so it is a suitable test bed for exploring training paradigms and representation learning.
arXiv Detail & Related papers (2019-12-29T07:27:23Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.