Learning towards Abstractive Timeline Summarization

Timeline summarization targets at concisely summarizing the evolution trajectory along the timeline and existing timeline summarization approaches are all based on extractive methods.In this paper, we propose the task of abstractive timeline summarization, which tends to concisely paraphrase the information in the time-stamped events.Unlike traditional document summarization, timeline summarization needs to model the time series information of the input events and summarize important events in chronological order.To tackle this challenge, we propose a memory-based timeline summarization model (MTS).Concretely, we propose a time-event memory to establish a timeline, and use the time position of events on this timeline to guide generation process.Besides, in each decoding step, we incorporate event-level information into word-level attention to avoid confusion between events.Extensive experiments are conducted on a large-scale real-world dataset, and the results show that MTS achieves the state-of-the-art performance in terms of both automatic and human evaluations.

Download Full-text

What is this Article about? Extreme Summarization with Topic-aware Convolutional Neural Networks

Journal of Artificial Intelligence Research ◽

10.1613/jair.1.11315 ◽

2019 ◽

Vol 66 ◽

pp. 243-278

Author(s):

Shashi Narayan ◽

Shay B. Cohen ◽

Mirella Lapata

Keyword(s):

Neural Networks ◽

Long Range ◽

Convolutional Neural Networks ◽

Real World ◽

Large Scale ◽

State Of The Art ◽

British Broadcasting Corporation ◽

Document Summarization ◽

Modeling Approach ◽

Large Scale Dataset

We introduce "extreme summarization," a new single-document summarization task which aims at creating a short, one-sentence news summary answering the question "What is the article about?". We argue that extreme summarization, by nature, is not amenable to extractive strategies and requires an abstractive modeling approach. In the hope of driving research on this task further: (a) we collect a real-world, large scale dataset by harvesting online articles from the British Broadcasting Corporation (BBC); and (b) propose a novel abstractive model which is conditioned on the article's topics and based entirely on convolutional neural networks. We demonstrate experimentally that this architecture captures long-range dependencies in a document and recognizes pertinent content, outperforming an oracle extractive system and state-of-the-art abstractive approaches when evaluated automatically and by humans on the extreme summarization dataset.

Download Full-text

Extrinsic Camera Calibration with Line-Laser Projection

Sensors ◽

10.3390/s21041091 ◽

2021 ◽

Vol 21 (4) ◽

pp. 1091

Author(s):

Izaak Van Crombrugge ◽

Rudi Penne ◽

Steve Vanlanduit

Keyword(s):

Camera Calibration ◽

Real World ◽

Large Scale ◽

State Of The Art ◽

Bundle Adjustment ◽

Field Of View ◽

Extrinsic Calibration ◽

Practical Procedure ◽

Partial Overlap

Knowledge of precise camera poses is vital for multi-camera setups. Camera intrinsics can be obtained for each camera separately in lab conditions. For fixed multi-camera setups, the extrinsic calibration can only be done in situ. Usually, some markers are used, like checkerboards, requiring some level of overlap between cameras. In this work, we propose a method for cases with little or no overlap. Laser lines are projected on a plane (e.g., floor or wall) using a laser line projector. The pose of the plane and cameras is then optimized using bundle adjustment to match the lines seen by the cameras. To find the extrinsic calibration, only a partial overlap between the laser lines and the field of view of the cameras is needed. Real-world experiments were conducted both with and without overlapping fields of view, resulting in rotation errors below 0.5°. We show that the accuracy is comparable to other state-of-the-art methods while offering a more practical procedure. The method can also be used in large-scale applications and can be fully automated.

Download Full-text

Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction

Transactions of the Association for Computational Linguistics ◽

10.1162/tacl_a_00032 ◽

2018 ◽

Vol 6 ◽

pp. 451-465 ◽

Cited By ~ 5

Author(s):

Daniela Gerz ◽

Ivan Vulić ◽

Edoardo Ponti ◽

Jason Naradowsky ◽

Roi Reichart ◽

...

Keyword(s):

Large Scale ◽

Language Modeling ◽

Language Models ◽

Data Sets ◽

High Type ◽

Word Level ◽

Level Information ◽

Character Sequences ◽

Novel Method ◽

Morphologically Rich Languages

Neural architectures are prominent in the construction of language models (LMs). However, word-level prediction is typically agnostic of subword-level information (characters and character sequences) and operates over a closed vocabulary, consisting of a limited word set. Indeed, while subword-aware models boost performance across a variety of NLP tasks, previous work did not evaluate the ability of these models to assist next-word prediction in language modeling tasks. Such subword-level informed models should be particularly effective for morphologically-rich languages (MRLs) that exhibit high type-to-token ratios. In this work, we present a large-scale LM study on 50 typologically diverse languages covering a wide variety of morphological systems, and offer new LM benchmarks to the community, while considering subword-level information. The main technical contribution of our work is a novel method for injecting subword-level information into semantic word vectors, integrated into the neural language modeling training, to facilitate word-level prediction. We conduct experiments in the LM setting where the number of infrequent words is large, and demonstrate strong perplexity gains across our 50 languages, especially for morphologically-rich languages. Our code and data sets are publicly available.

Download Full-text

Legal Judgment Prediction Based on Multiclass Information Fusion

Complexity ◽

10.1155/2020/3089189 ◽

2020 ◽

Vol 2020 ◽

pp. 1-12

Author(s):

Kongfan Zhu ◽

Rundong Guo ◽

Weifeng Hu ◽

Zeqiang Li ◽

Yujun Li

Keyword(s):

Information Fusion ◽

Real World ◽

Large Scale ◽

State Of The Art ◽

External Information ◽

Criminal Cases ◽

Law System ◽

Large Scale Dataset ◽

Assistant Systems ◽

Civil Law System

Legal judgment prediction (LJP), as an effective and critical application in legal assistant systems, aims to determine the judgment results according to the information based on the fact determination. In real-world scenarios, to deal with the criminal cases, judges not only take advantage of the fact description, but also consider the external information, such as the basic information of defendant and the court view. However, most existing works take the fact description as the sole input for LJP and ignore the external information. We propose a Transformer-Hierarchical-Attention-Multi-Extra (THME) Network to make full use of the information based on the fact determination. We conduct experiments on a real-world large-scale dataset of criminal cases in the civil law system. Experimental results show that our method outperforms state-of-the-art LJP methods on all judgment prediction tasks.

Download Full-text

Efficient Heterogeneous Collaborative Filtering without Negative Sampling for Recommendation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i01.5329 ◽

2020 ◽

Vol 34 (01) ◽

pp. 19-26 ◽

Cited By ~ 5

Author(s):

Chong Chen ◽

Min Zhang ◽

Yongfeng Zhang ◽

Weizhi Ma ◽

Yiqun Liu ◽

...

Keyword(s):

Collaborative Filtering ◽

Real World ◽

Large Scale ◽

State Of The Art ◽

Heterogeneous Data ◽

Model Parameters ◽

Online Systems ◽

Practical Applications ◽

Real World Datasets ◽

Primary Type

Recent studies on recommendation have largely focused on exploring state-of-the-art neural networks to improve the expressiveness of models, while typically apply the Negative Sampling (NS) strategy for efficient learning. Despite effectiveness, two important issues have not been well-considered in existing methods: 1) NS suffers from dramatic fluctuation, making sampling-based methods difficult to achieve the optimal ranking performance in practical applications; 2) although heterogeneous feedback (e.g., view, click, and purchase) is widespread in many online systems, most existing methods leverage only one primary type of user feedback such as purchase. In this work, we propose a novel non-sampling transfer learning solution, named Efficient Heterogeneous Collaborative Filtering (EHCF) for Top-N recommendation. It can not only model fine-grained user-item relations, but also efficiently learn model parameters from the whole heterogeneous data (including all unlabeled data) with a rather low time complexity. Extensive experiments on three real-world datasets show that EHCF significantly outperforms state-of-the-art recommendation methods in both traditional (single-behavior) and heterogeneous scenarios. Moreover, EHCF shows significant improvements in training efficiency, making it more applicable to real-world large-scale systems. Our implementation has been released 1 to facilitate further developments on efficient whole-data based neural methods.

Download Full-text

Scene text removal via cascaded text stroke detection and erasing

Computational Visual Media ◽

10.1007/s41095-021-0242-8 ◽

2021 ◽

Vol 8 (2) ◽

pp. 273-287

Author(s):

Xuewei Bian ◽

Chaoqun Wang ◽

Weize Quan ◽

Juntao Ye ◽

Xiaopeng Zhang ◽

...

Keyword(s):

Performance Improvement ◽

Real World ◽

Large Scale ◽

State Of The Art ◽

The State ◽

Experimental Results ◽

Processing Unit ◽

Final Model ◽

Scene Text ◽

End To End

AbstractRecent learning-based approaches show promising performance improvement for the scene text removal task but usually leave several remnants of text and provide visually unpleasant results. In this work, a novel end-to-end framework is proposed based on accurate text stroke detection. Specifically, the text removal problem is decoupled into text stroke detection and stroke removal; we design separate networks to solve these two subproblems, the latter being a generative network. These two networks are combined as a processing unit, which is cascaded to obtain our final model for text removal. Experimental results demonstrate that the proposed method substantially outperforms the state-of-the-art for locating and erasing scene text. A new large-scale real-world dataset with 12,120 images has been constructed and is being made available to facilitate research, as current publicly available datasets are mainly synthetic so cannot properly measure the performance of different methods.

Download Full-text

Crop Rotation Modeling for Deep Learning-Based Parcel Classification from Satellite Time Series

Remote Sensing ◽

10.3390/rs13224599 ◽

2021 ◽

Vol 13 (22) ◽

pp. 4599

Author(s):

Félix Quinton ◽

Loic Landrieu

Keyword(s):

Time Series ◽

Deep Learning ◽

Crop Rotation ◽

Large Scale ◽

State Of The Art ◽

Crop Rotations ◽

Learning Approach ◽

Type Mapping ◽

Current State ◽

Crop Type

While annual crop rotations play a crucial role for agricultural optimization, they have been largely ignored for automated crop type mapping. In this paper, we take advantage of the increasing quantity of annotated satellite data to propose to model simultaneously the inter- and intra-annual agricultural dynamics of yearly parcel classification with a deep learning approach. Along with simple training adjustments, our model provides an improvement of over 6.3% mIoU over the current state-of-the-art of crop classification, and a reduction of over 21% of the error rate. Furthermore, we release the first large-scale multi-year agricultural dataset with over 300,000 annotated parcels.

Download Full-text

App Download Forecasting: An Evolutionary Hierarchical Competition Approach

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2017/415 ◽

2017 ◽

Cited By ~ 6

Author(s):

Yingzi Wang ◽

Nicholas Jing Yuan ◽

Yu Sun ◽

Chuan Qin ◽

Xing Xie

Keyword(s):

Time Series ◽

Future Development ◽

Real World ◽

State Of The Art ◽

Time Series Forecasting ◽

Comprehensive Understanding ◽

Competition Analysis ◽

Multi Scale ◽

Multi Level ◽

Product Sales

Product sales forecasting enables comprehensive understanding of products' future development, making it of particular interest for companies to improve their business, for investors to measure the values of firms, and for users to capture the trends of a market. Recent studies show that the complex competition interactions among products directly influence products' future development. However, most existing approaches fail to model the evolutionary competition among products and lack the capability to organically reflect multi-level competition analysis in sales forecasting. To address these problems, we propose the Evolutionary Hierarchical Competition Model (EHCM), which effectively considers the time-evolving multi-level competition among products. The EHCM model systematically integrates hierarchical competition analysis with multi-scale time series forecasting. Extensive experiments using a real-world app download dataset show that EHCM outperforms state-of-the-art methods in various forecasting granularities.

Download Full-text

Evaluation and Comparison of Random Forest and A-LSTM Networks for Large-scale Winter Wheat Identification

Remote Sensing ◽

10.3390/rs11141665 ◽

2019 ◽

Vol 11 (14) ◽

pp. 1665 ◽

Cited By ~ 11

Author(s):

Tianle He ◽

Chuanjie Xie ◽

Qingsheng Liu ◽

Shiying Guan ◽

Gaohuan Liu

Keyword(s):

Time Series ◽

Random Forest ◽

Winter Wheat ◽

Large Scale ◽

Short Term Memory ◽

State Of The Art ◽

Training Sample ◽

Central China ◽

Surface Reflectance ◽

The Impact

Machine learning comprises a group of powerful state-of-the-art techniques for land cover classification and cropland identification. In this paper, we proposed and evaluated two models based on random forest (RF) and attention-based long short-term memory (A-LSTM) networks that can learn directly from the raw surface reflectance of remote sensing (RS) images for large-scale winter wheat identification in Huanghuaihai Region (North-Central China). We used a time series of Moderate Resolution Imaging Spectroradiometer (MODIS) images over one growing season and the corresponding winter wheat distribution map for the experiments. Each training sample was derived from the raw surface reflectance of MODIS time-series images. Both models achieved state-of-the-art performance in identifying winter wheat, and the F1 scores of RF and A-LSTM were 0.72 and 0.71, respectively. We also analyzed the impact of the pixel-mixing effect. Training with pure-mixed-pixel samples (the training set consists of pure and mixed cells and thus retains the original distribution of data) was more precise than training with only pure-pixel samples (the entire pixel area belongs to one class). We also analyzed the variable importance along the temporal series, and the data acquired in March or April contributed more than the data acquired at other times. Both models could predict winter wheat coverage in past years or in other regions with similar winter wheat growing seasons. The experiments in this paper showed the effectiveness and significance of our methods.

Download Full-text

Comparison of Stochastic and Machine Learning Methods for Multi-Step Ahead Forecasting of Hydrological Processes

10.20944/preprints201710.0133.v1 ◽

2017 ◽

Cited By ~ 5

Author(s):

Georgia A. Papacharalampous ◽

Hristos Tyralis ◽

Demetris Koutsoyiannis

Keyword(s):

Machine Learning ◽

Time Series ◽

Stochastic Processes ◽

Real World ◽

Large Scale ◽

Simulation Experiment ◽

Learning Methods ◽

Machine Learning Methods ◽

Stationary Stochastic Processes ◽

First Time

We perform an extensive comparison between 11 stochastic to 9 machine learning methods regarding their multi-step ahead forecasting properties by conducting 12 large-scale computational experiments. Each of these experiments uses 2 000 time series generated by linear stationary stochastic processes. We conduct each simulation experiment twice; the first time using time series of 110 values and the second time using time series of 310 values. Additionally, we conduct 92 real-world case studies using mean monthly time series of streamflow and particularly focus on one of them to reinforce the findings and highlight important facts. We quantify the performance of the methods using 18 metrics. The results indicate that the machine learning methods do not differ dramatically from the stochastic, while none of the methods under comparison is uniformly better or worse than the rest. However, there are methods that are regularly better or worse than others according to specific metrics.

Download Full-text