scholarly journals Multi-Hop Question Generation Using Hierarchical Encoding-Decoding and Context Switch Mechanism

Entropy ◽  
2021 ◽  
Vol 23 (11) ◽  
pp. 1449
Author(s):  
Tianbo Ji ◽  
Chenyang Lyu ◽  
Zhichao Cao ◽  
Peng Cheng
Keyword(s):  
Generation Process ◽  
Text Generation ◽  
Question Generation ◽  
Time Step ◽  
Word Level ◽  
Context Switch ◽  
Context Vector ◽  
Switch Mechanism ◽  
Hierarchical Encoding ◽  
Document Level

Neural auto-regressive sequence-to-sequence models have been dominant in text generation tasks, especially the question generation task. However, neural generation models suffer from the global and local semantic semantic drift problems. Hence, we propose the hierarchical encoding–decoding mechanism that aims at encoding rich structure information of the input passages and reducing the variance in the decoding phase. In the encoder, we hierarchically encode the input passages according to its structure at four granularity-levels: [word, chunk, sentence, document]-level. Second, we progressively select the context vector from the document-level representations to the word-level representations at each decoding time step. At each time-step in the decoding phase, we progressively select the context vector from the document-level representations to word-level. We also propose the context switch mechanism that enables the decoder to use the context vector from the last step when generating the current word at each time-step.It provides a means of improving the stability of the text generation process during the decoding phase when generating a set of consecutive words. Additionally, we inject syntactic parsing knowledge to enrich the word representations. Experimental results show that our proposed model substantially improves the performance and outperforms previous baselines according to both automatic and human evaluation. Besides, we implement a deep and comprehensive analysis of generated questions based on their types.

An Unsupervised Aspect-Aware Recommendation Model with Explanation Text Generation

2022 ◽  
Vol 40 (3) ◽  
pp. 1-29
Author(s):  
Peijie Sun ◽  
Le Wu ◽  
Kun Zhang ◽  
Yu Su ◽  
Meng Wang
Keyword(s):  
Data Privacy ◽  
Auxiliary Information ◽  
Generation Process ◽  
Text Generation ◽  
Generation Task ◽  
Auxiliary Data ◽  
Fine Grained ◽  
Aspect Extraction ◽  
Learning Framework ◽  
Real World Datasets

Review based recommendation utilizes both users’ rating records and the associated reviews for recommendation. Recently, with the rapid demand for explanations of recommendation results, reviews are used to train the encoder–decoder models for explanation text generation. As most of the reviews are general text without detailed evaluation, some researchers leveraged auxiliary information of users or items to enrich the generated explanation text. Nevertheless, the auxiliary data is not available in most scenarios and may suffer from data privacy problems. In this article, we argue that the reviews contain abundant semantic information to express the users’ feelings for various aspects of items, while these information are not fully explored in current explanation text generation task. To this end, we study how to generate more fine-grained explanation text in review based recommendation without any auxiliary data. Though the idea is simple, it is non-trivial since the aspect is hidden and unlabeled. Besides, it is also very challenging to inject aspect information for generating explanation text with noisy review input. To solve these challenges, we first leverage an advanced unsupervised neural aspect extraction model to learn the aspect-aware representation of each review sentence. Thus, users and items can be represented in the aspect space based on their historical associated reviews. After that, we detail how to better predict ratings and generate explanation text with the user and item representations in the aspect space. We further dynamically assign review sentences which contain larger proportion of aspect words with larger weights to control the text generation process, and jointly optimize rating prediction accuracy and explanation text generation quality with a multi-task learning framework. Finally, extensive experimental results on three real-world datasets demonstrate the superiority of our proposed model for both recommendation accuracy and explainability.

scholarly journals Modelling COVID - 19 Transmission in a Hemodialysis Centre Using Simulation Generated Contacts Matrices

2021 ◽  
Author(s):  
Mohammadali Tofighi ◽  
Ali Asgary ◽  
Asad A. Merchant ◽  
Mohammad Ali Shafiee ◽  
Mahdi M. Najafabadi ◽  
...  
Keyword(s):  
Discrete Event ◽  
Intermittent Hemodialysis ◽  
Physical Interaction ◽  
Generation Process ◽  
Care Providers ◽  
Time Step ◽  
Dialysis Unit ◽  
Agent Based ◽  
Micro Scale ◽  
Contact Matrix

AbstractThe COVID-19 pandemic has been particularly threatening to the patients with end-stage kidney disease (ESKD) on intermittent hemodialysis and their care providers. Hemodialysis patients who receive life-sustaining medical therapy in healthcare settings, face unique challenges as they need to be at a dialysis unit three or more times a week, where they are confined to specific settings and tended to by dialysis nurses and staff with physical interaction and in close proximity. Despite the importance and critical situation of the dialysis units, modelling studies of the SARS-CoV-2 spread in these settings are very limited. In this paper, we have used a combination of discrete event and agent-based simulation models, to study the operations of a typical large dialysis unit and generate contact matrices to examine outbreak scenarios. We present the details of the contact matrix generation process and demonstrate how the simulation calculates a micro-scale contact matrix comprising the number and duration of contacts at a micro-scale time step. We have used the contacts matrix in an agent-based model to predict disease transmission under different scenarios. The results show that micro-simulation can be used to estimate contact matrices, which can be used effectively for disease modelling in dialysis and similar settings.

scholarly journals Direct and Indirect Effects of Literacy Skills and Writing Fluency on Writing Quality Across Three Genres

2020 ◽  
Vol 10 (11) ◽  
pp. 297
Author(s):  
Gary A. Troia ◽  
Julie S. Brehmer ◽  
Kaitlin Glause ◽  
Heather L. Reichmuth ◽  
Frank Lawrence
Keyword(s):  
Indirect Effects ◽  
Cognitive Effort ◽  
Literacy Skills ◽  
Direct And Indirect Effects ◽  
Text Generation ◽  
Writing Quality ◽  
School Year ◽  
Word Level ◽  
Path Analyses ◽  
Text Length

Data were collected for this study early in the school year to analyze the direct and indirect effects of word-level literacy skills (word recognition, spelling, and written vocabulary use) and handwriting fluency on writing quality across three genres of typewritten papers. We further explored whether typing fluency and text generation fluency mediated the effects. Finally, we examined whether there was any difference in the effects across three writing genres. Fourth and fifth graders (N = 175) from 21 typical classrooms in 12 different Midwestern U.S. schools participated. Regression path analyses were employed and revealed that word-level literacy skills had both significant direct and serial indirect effects on quality, via typing fluency and then text generation fluency (text length) when controlling for handwriting fluency. Further, handwriting fluency had no direct effect when controlling for word-level literacy skills but did have a significant serial indirect effect on writing quality via typing fluency then text generation fluency. Results indicate that handwriting fluency matters, even when composing on the computer. Stronger transcription fluency, particularly by hand, leads to higher quality writing, likely because less cognitive effort is devoted to transcription. This study adds to limited research on the cross-modal effects of transcription on writing quality.

A topological embedding of the lexicon for semantic distance computation

2010 ◽  
Vol 16 (3) ◽  
pp. 245-275
Author(s):  
N. DAVIS ◽  
C. GIRAUD-CARRIER ◽  
D. JENSEN
Keyword(s):  
Metric Space ◽  
Complete Metric Space ◽  
Order Relation ◽  
Semantic Distance ◽  
Distance Measures ◽  
Topological Transformation ◽  
Topological Embedding ◽  
Word Level ◽  
Natural Connection ◽  
Document Level

AbstractWe show how a quantitative context may be established for what is essentially qualitative in nature by topologically embedding a lexicon (here, WordNet) in a complete metric space. This novel transformation establishes a natural connection between the order relation in the lexicon (e.g., hyponymy) and the notion of distance in the metric space, giving rise to effective word-level and document-level lexical semantic distance measures. We provide a formal account of the topological transformation and demonstrate the value of our metrics on several experiments involving information retrieval and document clustering tasks.

scholarly journals Automatic Question Generation and Evaluation

2021 ◽  
Vol 23 (05) ◽  
pp. 751-761
Author(s):  
Parth Panchal ◽  
◽  
Janak Thakkar ◽  
Veerapathiramoorthy Pillai ◽  
Shweta Patil ◽  
...  
Keyword(s):  
Language Processing ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Generation Process ◽  
Question Generation ◽  
Machine Learning Classification ◽  
Pos Tagging ◽  
Text Document ◽  
Rule Based Approach ◽  
Automatic Question Generation

Generation of questions from an extract is a very tedious task for humans and an even tougher one for machines. In Automatic Question Generation (AQG), it is extremely important to examine the ways in which this can be achieved with sufficient levels of accuracy and efficiency. The way in which this can be taken ahead is by using Natural Language Processing (NLP) to process the input and to work with it for AQG. Using NLP with question generation algorithms the system can generate the questions for a better understanding of the text document. The input is pre-processed before actually moving in for the question generation process. The questions formed are first checked for proper context satisfaction with the context of the input to avoid invalid or unanswerable question generation. It is then preprocessed using various NLP-based mechanisms like tokenization, named entity recognition(NER) tagging, parts of speech(POS) tagging, etc. The question generation system consists of a machine learning classification-based Fill in the blank(FIB) generator that also generates multiple choices and a rule-based approach to generate Wh-type questions. It also consists of a question evaluator where the user can evaluate the generated question. The results of these evaluations can help in improving our system further. Also, evaluation of Wh questions has been done using the BLEU score to determine whether the automatically generated questions resemble closely the human-generated ones. This system can be used in various places to help ease the question generation and also at self-evaluator systems where the students can assess themselves so as to determine their conceptual understanding. Apart from educational use, it would also be helpful in building chatbot-based applications. This work can help improve the overall understanding of the level to which the concept given is understood by the candidate and the ways in which it can be understood more properly. We have taken a simple yet effective approach to generate the questions. Our evaluation results show that our model works well on simpler sentences.

scholarly journals Triple-to-Text Generation with an Anchor-to-Prototype Framework

2020 ◽  
Author(s):  
Ziran Li ◽  
Zibo Lin ◽  
Ning Ding ◽  
Hai-Tao Zheng ◽  
Ying Shen
Keyword(s):  
Natural Language ◽  
State Of The Art ◽  
Experimental Results ◽  
Training Data ◽  
Generation Process ◽  
Text Generation ◽  
Language Generation ◽  
Structured Input ◽  
Textual Description ◽  
Specific Description

Generating a textual description from a set of RDF triplets is a challenging task in natural language generation. Recent neural methods have become the mainstream for this task, which often generate sentences from scratch. However, due to the huge gap between the structured input and the unstructured output, the input triples alone are insufficient to decide an expressive and specific description. In this paper, we propose a novel anchor-to-prototype framework to bridge the gap between structured RDF triples and natural text. The model retrieves a set of prototype descriptions from the training data and extracts writing patterns from them to guide the generation process. Furthermore, to make a more precise use of the retrieved prototypes, we employ a triple anchor that aligns the input triples into groups so as to better match the prototypes. Experimental results on both English and Chinese datasets show that our method significantly outperforms the state-of-the-art baselines in terms of both automatic and manual evaluation, demonstrating the benefit of learning guidance from retrieved prototypes to facilitate triple-to-text generation.

scholarly journals Generating Indonesian Question Automatically Based on Bloom’s Taxonomy Using Template Based Method

2018 ◽  
pp. 145-152 ◽  
Author(s):  
Selvia Ferdiana Kusuma ◽  
Rinanza Zulmy Alhamri
Keyword(s):  
Learning Process ◽  
Evaluation Process ◽  
Bloom's Taxonomy ◽  
Field Evaluation ◽  
Final Evaluation ◽  
Generation Process ◽  
New Materials ◽  
Question Generation ◽  
Identification Process ◽  
Bloom’S Taxonomy

In education field, evaluation is needed to know the extent to which the learning process has been done. The evaluation process can be done through the provision of questions with varying degrees of difficulty. However, making questions with varying degrees of difficulty is not easy. Someone must understand the whole new materials to make the question. If there are a lot of materials, it takes a little time to change them to be a question. Therefore, it is necessary to automate the question generation process, in order to facilitate and accelerate the question generation process. This research introduces a template-based method to generate questions based on New Bloom's Taxonomy. There were 4 stages in this research, dataset collection, pattern identification process, question generating process & classification, and final evaluation process result. The dataset consists of 60 samples of paragraphs that derived from 9 courses of study courses Informatics Engineering. The 60 paragraphs produced 278 sentences and 654 questions. The proposed method is capable of producing an accuracy of 81.65% to generate questions using New Bloom's Taxonomy classification. So it can be concluded that the proposed method can be used to generate questions with varying difficulty levels in accordance with New Bloom's Taxonomy.

scholarly journals Multi-Agent Discussion Mechanism for Natural Language Generation

2019 ◽  
Vol 33 ◽  
pp. 6096-6103 ◽  
Author(s):  
Xu Li ◽  
Mingming Sun ◽  
Ping Li
Keyword(s):  
Natural Language ◽  
Natural Language Generation ◽  
Text Summarization ◽  
Final Decision ◽  
Target Sequence ◽  
Text Generation ◽  
Time Step ◽  
Language Generation ◽  
Decoder Architecture ◽  
Multi Agent

We introduce the discussion mechanism into the multiagent communicating encoder-decoder architecture for Natural Language Generation (NLG) tasks and prove that by applying the discussion mechanism, the communication between agents becomes more effective. Generally speaking, an encoder-decoder architecture predicts target-sequence word by word in several time steps. At each time step of prediction, agents with the discussion mechanism predict the target word after several discussion steps. In the first step of discussion, agents make their choice independently and express their decision to other agents. In the next discussion step, agents collect other agents’ decision to update their own decisions, then express the updated decisions to others again. After several iterations, the agents make their final decision based on a well-communicated situation. The benefit of the discussion mechanism is that multiple encoders can be designed as different structures to fit the specified input or to fetch different representations of inputs.We train and evaluate the discussion mechanism on Table to Text Generation, Text Summarization and Image Caption tasks, respectively. Our empirical results demonstrate that the proposed multi-agent discussion mechanism is helpful for maximizing the utility of the communication between agents.

Chronological Ordering Based on Context Overlap Detection

2012 ◽  
Vol 2 (4) ◽  
pp. 31-44
Author(s):  
Mohamed H. Haggag ◽  
Bassma M. Othman
Keyword(s):  
Language Processing ◽  
Linguistic Knowledge ◽  
Syntactic Analysis ◽  
Text Generation ◽  
Context Processing ◽  
Domain Specific ◽  
Word Level ◽  
Sentence Level ◽  
Proposed Model ◽  
Chronological Sequence

Context processing plays an important role in different Natural Language Processing applications. Sentence ordering is one of critical tasks in text generation. Following the same order of sentences in the row sources of text is not necessarily to be applied for the resulted text. Accordingly, a need for chronological sentence ordering is of high importance in this regard. Some researches followed linguistic syntactic analysis and others used statistical approaches. This paper proposes a new model for sentence ordering based on sematic analysis. Word level semantics forms a seed to sentence level sematic relations. The model introduces a clustering technique based on sentences senses relatedness. Following to this, sentences are chronologically ordered through two main steps; overlap detection and chronological cause-effect rules. Overlap detection drills down into each cluster to step through its sentences in chronological sequence. Cause-effect rules forms the linguistic knowledge controlling sentences relations. Evaluation of the proposed algorithm showed the capability of the proposed model to process size free texts, non-domain specific and open to extend the cause-effect rules for specific ordering needs.

Word-level Text Generation from Language Models

2021 ◽  
Author(s):  
Ponrudee Netisopakul ◽  
Usanisa Taoto
Keyword(s):  
Language Models ◽  
Text Generation ◽  
Word Level
Sign in / Sign up

Export Citation Format

Share Document