scholarly journals Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation

2020 ◽  
Vol 34 (05) ◽  
pp. 7716-7723
Author(s):  
Xiaocheng Feng ◽  
Yawei Sun ◽  
Bing Qin ◽  
Heng Gong ◽  
Yibo Sun ◽  
...  
Keyword(s):  
State Of The Art ◽  
Neural Model ◽  
High Fidelity ◽  
Semantic Relationship ◽  
Style Transfer ◽  
Basketball Game ◽  
Sentence Level ◽  
Parallel Data ◽  
Back Translation ◽  
Text Content

In this paper, we focus on a new practical task, document-scale text content manipulation, which is the opposite of text style transfer and aims to preserve text styles while altering the content. In detail, the input is a set of structured records and a reference text for describing another recordset. The output is a summary that accurately describes the partial content in the source recordset with the same writing style of the reference. The task is unsupervised due to lack of parallel data, and is challenging to select suitable records and style words from bi-aspect inputs respectively and generate a high-fidelity long document. To tackle those problems, we first build a dataset based on a basketball game report corpus as our testbed, and present an unsupervised neural model with interactive attention mechanism, which is used for learning the semantic relationship between records and reference texts to achieve better content transfer and better style preservation. In addition, we also explore the effectiveness of the back-translation in our task for constructing some pseudo-training pairs. Empirical results show superiority of our approaches over competitive methods, and the models also yield a new state-of-the-art result on a sentence-level dataset. 1

scholarly journals Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders

2020 ◽  
Vol 34 (05) ◽  
pp. 9668-9675
Author(s):  
Yanbin Zhao ◽  
Lu Chen ◽  
Zhi Chen ◽  
Kai Yu
Keyword(s):  
State Of The Art ◽  
Automatic Generation ◽  
Complex Sentences ◽  
Text Simplification ◽  
Parallel Data ◽  
Different Types ◽  
Back Translation ◽  
Multiple State ◽  
Simple Pair

Text simplification (TS) rephrases long sentences into simplified variants while preserving inherent semantics. Traditional sequence-to-sequence models heavily rely on the quantity and quality of parallel sentences, which limits their applicability in different languages and domains. This work investigates how to leverage large amounts of unpaired corpora in TS task. We adopt the back-translation architecture in unsupervised machine translation (NMT), including denoising autoencoders for language modeling and automatic generation of parallel data by iterative back-translation. However, it is non-trivial to generate appropriate complex-simple pair if we directly treat the set of simple and complex corpora as two different languages, since the two types of sentences are quite similar and it is hard for the model to capture the characteristics in different types of sentences. To tackle this problem, we propose asymmetric denoising methods for sentences with separate complexity. When modeling simple and complex sentences with autoencoders, we introduce different types of noise into the training process. Such a method can significantly improve the simplification performance. Our model can be trained in both unsupervised and semi-supervised manner. Automatic and human evaluations show that our unsupervised model outperforms the previous systems, and with limited supervision, our model can perform competitively with multiple state-of-the-art simplification systems.

scholarly journals A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer

2019 ◽  
Author(s):  
Fuli Luo ◽  
Peng Li ◽  
Jie Zhou ◽  
Pengcheng Yang ◽  
Baobao Chang ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
Style Transfer ◽  
Mapping Model ◽  
Learning Framework ◽  
Parallel Data ◽  
Benchmark Datasets ◽  
One Step ◽  
Content Preservation ◽  
Mapping Models

Unsupervised text style transfer aims to transfer the underlying style of text but keep its main content unchanged without parallel data. Most existing methods typically follow two steps: first separating the content from the original style, and then fusing the content with the desired style. However, the separation in the first step is challenging because the content and style interact in subtle ways in natural language. Therefore, in this paper, we propose a dual reinforcement learning framework to directly transfer the style of the text via a one-step mapping model, without any separation of content and style. Specifically, we consider the learning of the source-to-target and target-to-source mappings as a dual task, and two rewards are designed based on such a dual structure to reflect the style accuracy and content preservation, respectively. In this way, the two one-step mapping models can be trained via reinforcement learning, without any use of parallel data. Automatic evaluations show that our model outperforms the state-of-the-art systems by a large margin, especially with more than 10 BLEU points improvement averaged on two benchmark datasets. Human evaluations also validate the effectiveness of our model in terms of style accuracy, content preservation and fluency. Our code and data, including outputs of all baselines and our model are available at https://github.com/luofuli/DualRL.

scholarly journals Utilizing Non-Parallel Text for Style Transfer by Making Partial Comparisons

2019 ◽  
Author(s):  
Di Yin ◽  
Shujian Huang ◽  
Xin-Yu Dai ◽  
Jiajun Chen
Keyword(s):  
Data Augmentation ◽  
State Of The Art ◽  
Language Models ◽  
Style Transfer ◽  
Parallel Corpora ◽  
Parallel Data ◽  
Distributional Information ◽  
Parallel Text ◽  
Using Data ◽  
Content Preservation

Text style transfer aims to rephrase a given sentence into a different style without changing its original content. Since parallel corpora (i.e. sentence pairs with the same content but different styles) are usually unavailable, most previous works solely guide the transfer process with distributional information, i.e. using style-related classifiers or language models, which neglect the correspondence of instances, leading to poor transfer performance, especially for the content preservation. In this paper, we propose making partial comparisons to explicitly model the content and style correspondence of instances, respectively. To train the partial comparators, we propose methods to extract partial-parallel training instances automatically from the non-parallel data, and to further enhance the training process by using data augmentation. We perform experiments that compare our method to other existing approaches on two review datasets. Both automatic and manual evaluations show that our approach can significantly improve the performance of existing adversarial methods, and outperforms most state-of-the-art models. Our code and data will be available on Github.

scholarly journals Efficient End-to-End Sentence-Level Lipreading with Temporal Convolutional Networks

2021 ◽  
Vol 11 (15) ◽  
pp. 6975
Author(s):  
Tao Zhang ◽  
Lun He ◽  
Xudong Li ◽  
Guoqing Feng
Keyword(s):  
Performance Improvement ◽  
State Of The Art ◽  
Error Rates ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Sentence Level ◽  
End To End ◽  
High Level ◽  
Improved Accuracy ◽  
Talking Face

Lipreading aims to recognize sentences being spoken by a talking face. In recent years, the lipreading method has achieved a high level of accuracy on large datasets and made breakthrough progress. However, lipreading is still far from being solved, and existing methods tend to have high error rates on the wild data and have the defects of disappearing training gradient and slow convergence. To overcome these problems, we proposed an efficient end-to-end sentence-level lipreading model, using an encoder based on a 3D convolutional network, ResNet50, Temporal Convolutional Network (TCN), and a CTC objective function as the decoder. More importantly, the proposed architecture incorporates TCN as a feature learner to decode feature. It can partly eliminate the defects of RNN (LSTM, GRU) gradient disappearance and insufficient performance, and this yields notable performance improvement as well as faster convergence. Experiments show that the training and convergence speed are 50% faster than the state-of-the-art method, and improved accuracy by 2.4% on the GRID dataset.

scholarly journals High-Fidelity Simulated Players for Interactive Narrative Planning

2018 ◽  
Author(s):  
Pengcheng Wang ◽  
Jonathan Rowe ◽  
Wookhee Min ◽  
Bradford Mott ◽  
James Lester
Keyword(s):  
State Of The Art ◽  
Data Driven ◽  
High Fidelity ◽  
Interactive Narrative ◽  
Interaction Data ◽  
Convolutional Networks ◽  
Novel Approach ◽  
Adaptation Policies ◽  
Narrative Planning ◽  
Prior State

Interactive narrative planning offers significant potential for creating adaptive gameplay experiences. While data-driven techniques have been devised that utilize player interaction data to induce policies for interactive narrative planners, they require enormously large gameplay datasets. A promising approach to addressing this challenge is creating simulated players whose behaviors closely approximate those of human players. In this paper, we propose a novel approach to generating high-fidelity simulated players based on deep recurrent highway networks and deep convolutional networks. Empirical results demonstrate that the proposed models significantly outperform the prior state-of-the-art in generating high-fidelity simulated player models that accurately imitate human players’ narrative interactions. Using the high-fidelity simulated player models, we show the advantage of more exploratory reinforcement learning methods for deriving generalizable narrative adaptation policies.

scholarly journals Geomorphometry: Today and Tomorrow

2018 ◽  
Author(s):  
John P Wilson
Keyword(s):  
Content Knowledge ◽  
State Of The Art ◽  
High Fidelity ◽  
Terrain Modeling ◽  
Actionable Knowledge ◽  
Digital Terrain ◽  
Current State ◽  
Digital Terrain Modeling ◽  
Key Innovations

This paper summarizes the current state-of-the-art in geomorphometry and describes the innovations that are close at hand and will be required to push digital terrain modeling forward in the future. These innovations will draw on concepts and methods from computer science and the spatial sciences and require greater collaboration to produce “actionable” knowledge and outcomes. The key innovations include rediscovering and using what we already know, developing new digital terrain modeling methods, clarifying and strengthening the role of theory, developing high-fidelity DEMs, developing and embracing new visualization methods, adopting new computational approaches, and making better use of provenance, credibility, and application-content knowledge.

scholarly journals Efficient Context-Aware Neural Machine Translation with Layer-Wise Weighting and Input-Aware Gating

2020 ◽  
Author(s):  
Hongfei Xu ◽  
Deyi Xiong ◽  
Josef van Genabith ◽  
Qiuhui Liu
Keyword(s):  
Machine Translation ◽  
Contextual Information ◽  
Computational Cost ◽  
Representation Learning ◽  
Vital Role ◽  
Context Aware ◽  
Neural Machine Translation ◽  
Gating Mechanism ◽  
Sentence Level ◽  
Parallel Data

Existing Neural Machine Translation (NMT) systems are generally trained on a large amount of sentence-level parallel data, and during prediction sentences are independently translated, ignoring cross-sentence contextual information. This leads to inconsistency between translated sentences. In order to address this issue, context-aware models have been proposed. However, document-level parallel data constitutes only a small part of the parallel data available, and many approaches build context-aware models based on a pre-trained frozen sentence-level translation model in a two-step training manner. The computational cost of these approaches is usually high. In this paper, we propose to make the most of layers pre-trained on sentence-level data in contextual representation learning, reusing representations from the sentence-level Transformer and significantly reducing the cost of incorporating contexts in translation. We find that representations from shallow layers of a pre-trained sentence-level encoder play a vital role in source context encoding, and propose to perform source context encoding upon weighted combinations of pre-trained encoder layers' outputs. Instead of separately performing source context and input encoding, we propose to iteratively and jointly encode the source input and its contexts and to generate input-aware context representations with a cross-attention layer and a gating mechanism, which resets irrelevant information in context encoding. Our context-aware Transformer model outperforms the recent CADec [Voita et al., 2019c] on the English-Russian subtitle data and is about twice as fast in training and decoding.

scholarly journals Two-Level Transformer and Auxiliary Coherence Modeling for Improved Text Segmentation

2020 ◽  
Vol 34 (05) ◽  
pp. 7797-7804
Author(s):  
Goran Glavašš ◽  
Swapna Somasundaran
Keyword(s):  
State Of The Art ◽  
Language Transfer ◽  
Text Segmentation ◽  
Word Embeddings ◽  
Neural Architecture ◽  
Text Coherence ◽  
Sentence Level ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Cross Lingual

Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and segmentation, we introduce a novel supervised model for text segmentation with simple but explicit coherence modeling. Our model – a neural architecture consisting of two hierarchically connected Transformer networks – is a multi-task learning model that couples the sentence-level segmentation objective with the coherence objective that differentiates correct sequences of sentences from corrupt ones. The proposed model, dubbed Coherence-Aware Text Segmentation (CATS), yields state-of-the-art segmentation performance on a collection of benchmark datasets. Furthermore, by coupling CATS with cross-lingual word embeddings, we demonstrate its effectiveness in zero-shot language transfer: it can successfully segment texts in languages unseen in training.

scholarly journals A Goal-Driven Tree-Structured Neural Model for Math Word Problems

2019 ◽  
Author(s):  
Zhipeng Xie ◽  
Shichao Sun
Keyword(s):  
Word Problems ◽  
State Of The Art ◽  
Neural Model ◽  
Neural Models ◽  
Top Down ◽  
Feedforward Networks ◽  
Whole Process ◽  
Expression Tree ◽  
Generate Solution ◽  
Human Problem

Most existing neural models for math word problems exploit Seq2Seq model to generate solution expressions sequentially from left to right, whose results are far from satisfactory due to the lack of goal-driven mechanism commonly seen in human problem solving. This paper proposes a tree-structured neural model to generate expression tree in a goal-driven manner. Given a math word problem, the model first identifies and encodes its goal to achieve, and then the goal gets decomposed into sub-goals combined by an operator in a top-down recursive way. The whole process is repeated until the goal is simple enough to be realized by a known quantity as leaf node. During the process, two-layer gated-feedforward networks are designed to implement each step of goal decomposition, and a recursive neural network is used to encode fulfilled subtrees into subtree embeddings, which provides a better representation of subtrees than the simple goals of subtrees. Experimental results on the dataset Math23K have shown that our tree-structured model outperforms significantly several state-of-the-art models.

scholarly journals Modeling Topical Relevance for Multi-Turn Dialogue Generation

2020 ◽  
Author(s):  
Hainan Zhang ◽  
Yanyan Lan ◽  
Liang Pang ◽  
Hongshen Chen ◽  
Zhuoye Ding ◽  
...  
Keyword(s):  
Topic Model ◽  
State Of The Art ◽  
Training Dataset ◽  
Common Phenomenon ◽  
New Model ◽  
Sentence Level ◽  
Topic Distribution ◽  
Topic Drift ◽  
Relevant Context ◽  
Customer Services

Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly. However, existing models usually use word or sentence level similarities to detect the relevant contexts, which fail to well capture the topical level relevance. In this paper, we propose a new model, named STAR-BTM, to tackle this problem. Firstly, the Biterm Topic Model is pre-trained on the whole training dataset. Then, the topic level attention weights are computed based on the topic representation of each context. Finally, the attention weights and the topic distribution are utilized in the decoding process to generate the corresponding responses. Experimental results on both Chinese customer services data and English Ubuntu dialogue data show that STAR-BTM significantly outperforms several state-of-the-art methods, in terms of both metric-based and human evaluations.

Sign in / Sign up

Export Citation Format

Share Document