scholarly journals From Neural Sentence Summarization to Headline Generation: A Coarse-to-Fine Approach

2017 ◽  
Author(s):  
Jiwei Tan ◽  
Xiaojun Wan ◽  
Jianguo Xiao
Keyword(s):  
Natural Language ◽  
Natural Language Generation ◽  
Text Summarization ◽  
Experimental Results ◽  
Generation Task ◽  
Document Summarization ◽  
Real Dataset ◽  
Language Generation ◽  
Recent Success ◽  
Coarse To Fine

Headline generation is a task of abstractive text summarization, and previously suffers from the immaturity of natural language generation techniques. Recent success of neural sentence summarization models shows the capacity of generating informative, fluent headlines conditioned on selected recapitulative sentences. In this paper, we investigate the extension of sentence summarization models to the document headline generation task. The challenge is that extending the sentence summarization model to consider more document information will mostly confuse the model and hurt the performance. In this paper, we propose a coarse-to-fine approach, which first identifies the important sentences of a document using document summarization techniques, and then exploits a multi-sentence summarization model with hierarchical attention to leverage the important sentences for headline generation. Experimental results on a large real dataset demonstrate the proposed approach significantly improves the performance of neural sentence summarization models on the headline generation task.

scholarly journals SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks

2018 ◽  
Author(s):  
Ke Wang ◽  
Xiaojun Wan
Keyword(s):  
Natural Language ◽  
State Of The Art ◽  
Natural Language Generation ◽  
Poor Quality ◽  
Experimental Results ◽  
Text Generation ◽  
Language Generation ◽  
Adversarial Networks

Generating texts of different sentiment labels is getting more and more attention in the area of natural language generation. Recently, Generative Adversarial Net (GAN) has shown promising results in text generation. However, the texts generated by GAN usually suffer from the problems of poor quality, lack of diversity and mode collapse. In this paper, we propose a novel framework - SentiGAN, which has multiple generators and one multi-class discriminator, to address the above problems. In our framework, multiple generators are trained simultaneously, aiming at generating texts of different sentiment labels without supervision. We propose a penalty based objective in the generators to force each of them to generate diversified examples of a specific sentiment label. Moreover, the use of multiple generators and one multi-class discriminator can make each generator focus on generating its own examples of a specific sentiment label accurately. Experimental results on four datasets demonstrate that our model consistently outperforms several state-of-the-art text generation methods in the sentiment accuracy and quality of generated texts.

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.

scholarly journals Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems

2019 ◽  
Author(s):  
Fei Mi ◽  
Minlie Huang ◽  
Jiyong Zhang ◽  
Boi Faltings
Keyword(s):  
Natural Language ◽  
Natural Language Generation ◽  
Dialogue Systems ◽  
Language Generation ◽  
Low Resource ◽  
Recent Success ◽  
Resource Setting ◽  
Meta Learning ◽  
Training Examples ◽  
Task Oriented

Natural language generation (NLG) is an essential component of task-oriented dialogue systems. Despite the recent success of neural approaches for NLG, they are typically developed for particular domains with rich annotated training examples. In this paper, we study NLG in a low-resource setting to generate sentences in new scenarios with handful training examples. We formulate the problem from a meta-learning perspective, and propose a generalized optimization-based approach (Meta-NLG) based on the well-recognized model-agnostic meta-learning (MAML) algorithm. Meta-NLG defines a set of meta tasks, and directly incorporates the objective of adapting to new low-resource NLG tasks into the meta-learning optimization process. Extensive experiments are conducted on a large multi-domain dataset (MultiWoz) with diverse linguistic variations. We show that Meta-NLG significantly outperforms other training procedures in various low-resource configurations. We analyze the results, and demonstrate that Meta-NLG adapts extremely fast and well to low-resource situations.

scholarly journals Computational Understanding, Generation and Evaluation of Creative Expressions

2021 ◽  
Author(s):  
Khalid Alnajjar
Keyword(s):  
Genetic Algorithm ◽  
Natural Language ◽  
Evaluation Method ◽  
Theoretical Foundation ◽  
Evolutionary Process ◽  
Natural Language Generation ◽  
Computational Creativity ◽  
Generation Task ◽  
Aesthetic Quality ◽  
Language Generation

Computational creativity has received a good amount of research interest in generating creative artefacts programmatically. At the same time, research has been conducted in computational aesthetics, which essentially tries to analyse creativity exhibited in art. This thesis aims to unite these two distinct lines of research in the context of natural language generation by building, from models for interpretation and generation, a cohesive whole that can assess its own generations. I present a novel method for interpreting one of the most difficult rhetoric devices in the figurative use of language: metaphors. The method does not rely on hand-annotated data and it is purely data-driven. It obtains the state of the art results and is comparable to the interpretations given by humans. We show how a metaphor interpretation model can be used in generating metaphors and metaphorical expressions. Furthermore, as a creative natural language generation task, we demonstrate assigning creative names to colours using an algorithmic approach that leverages a knowledge base of stereotypical associations for colours. Colour names produced by the approach were favoured by human judges to names given by humans 70% of the time. A genetic algorithm-based method is elaborated for slogan generation. The use of a genetic algorithm makes it possible to model the generation of text while optimising multiple fitness functions, as part of the evolutionary process, to assess the aesthetic quality of the output. Our evaluation indicates that having multiple balanced aesthetics outperforms a single maximised aesthetic. From an interplay of neural networks and the traditional AI approach of genetic algorithms, we present a symbiotic framework. This is called the master-apprentice framework. This makes it possible for the system to produce more diverse output as the neural network can learn from both the genetic algorithm and real people. The master-apprentice framework emphasises a strong theoretical foundation for the creative problem one seeks to solve. From this theoretical foundation, a reasoned evaluation method can be derived. This thesis presents two different evaluation practices based on two different theories on computational creativity. This research is conducted in two distinct practical tasks: pun generation in English and poetry generation in Finnish.

Sign in / Sign up

Export Citation Format

Share Document