Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userWhats The Latest? A Question-driven News Chatbot
143
0
0.0
(
0
)
Added by
Philippe Laban
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
This work describes an automatic news chatbot that draws content from a diverse set of news articles and creates conversations with a user about the news. Key components of the system include the automatic organization of news articles into topical chatrooms, integration of automatically generated questions into the conversation, and a novel method for choosing which questions to present which avoids repetitive suggestions. We describe the algorithmic framework and present the results of a usability study that shows that news readers using the system successfully engage in multi-turn conversations about specific news stories.
rate research
Read More
A flaw in QA evaluation is that annotations often only provide one gold answer. Thus, model predictions semantically equivalent to the answer but superficially different are considered incorrect. This work explores mining alias entities from knowledge bases and using them as additional gold answers (i.e., equivalent answers). We incorporate answers for two settings: evaluation with additional answers and model training with equivalent answers. We analyse three QA benchmarks: Natural Questions, TriviaQA, and SQuAD. Answer expansion increases the exact match score on all datasets for evaluation, while incorporating it helps model training over real-world datasets. We ensure the additional answers are valid through a human post hoc evaluation.
Question generation is a challenging task which aims to ask a question based on an answer and relevant context. The existing works suffer from the mismatching between question type and answer, i.e. generating a question with type $how$ while the answer is a personal name. We propose to automatically predict the question type based on the input answer and context. Then, the question type is fused into a seq2seq model to guide the question generation, so as to deal with the mismatching problem. We achieve significant improvement on the accuracy of question type prediction and finally obtain state-of-the-art results for question generation on both SQuAD and MARCO datasets.
In the last few years, open-domain question answering (ODQA) has advanced rapidly due to the development of deep learning techniques and the availability of large-scale QA datasets. However, the current datasets are essentially designed for synchronic document collections (e.g., Wikipedia). Temporal news collections such as long-term news archives spanning several decades, are rarely used in training the models despite they are quite valuable for our society. In order to foster the research in the field of ODQA on such historical collections, we present ArchivalQA, a large question answering dataset consisting of 1,067,056 question-answer pairs which is designed for temporal news QA. In addition, we create four subparts of our dataset based on the question difficulty levels and the containment of temporal expressions, which we believe could be useful for training or testing ODQA systems characterized by different strengths and abilities. The novel QA dataset-constructing framework that we introduce can be also applied to create datasets over other types of collections.
In the last several years, the field of computer assisted language learning has increasingly focused on computer aided question generation. However, this approach often provides test takers with an exhaustive amount of questions that are not designed for any specific testing purpose. In this work, we present a personalized computer aided question generation that generates multiple choice questions at various difficulty levels and types, including vocabulary, grammar and reading comprehension. In order to improve the weaknesses of test takers, it selects questions depending on an estimated proficiency level and unclear concepts behind incorrect responses. This results show that the students with the personalized automatic quiz generation corrected their mistakes more frequently than ones only with computer aided question generation. Moreover, students demonstrated the most progress between the pretest and post test and correctly answered more difficult questions. Finally, we investigated the personalizing strategy and found that a student could make a significant progress if the proposed system offered the vocabulary questions at the same level of his or her proficiency level, and if the grammar and reading comprehension questions were at a level lower than his or her proficiency level.
There are 8000 galaxies, including 1600 at z larger than 1.6, which could be simultaneously observed in an E-ELT field of view of 40 sq. arcmin. A considerable fraction of astrophysical discoveries require large statistical samples, which can only be obtained with multi-object spectrographs (MOS). MOSAIC will provide a vast discovery space, enabled by a multiplex of 200 and spectral resolving powers of R=5000 and 20000. MOSAIC will also offer the unique capability of more than 10 high-definition (multi-object adaptive optics, MOAO) integral-field units, optimised to investigate the physics of the sources of reionization. The combination of these modes will make MOSAIC the world-leading MOS facility, contributing to all fields of contemporary astronomy, from extra-solar planets, to the study of the halo of the Milky Way and its satellites, and from resolved stellar populations in nearby galaxies out to observations of the earliest first-light structures in the Universe. It will also study the distribution of the dark and ordinary matter at all scales and epochs of the Universe. Recent studies of critical technical issues such as sky-background subtraction and MOAO have demonstrated that such a MOS is feasible with state-of-the-art technology and techniques. Current studies of the MOSAIC team include further trade-offs on the wavelength coverage, a solution for compensating for the non-telecentric new design of the telescope, and tests of the saturation of skylines especially in the near-IR bands. In the 2020s the E-ELT will become the worlds largest optical/IR telescope, and we argue that it has to be equipped as soon as possible with a MOS to provide the most efficient, and likely the best way to follow-up on James Webb Space Telescope (JWST) observations.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
