Filters








1,282 Hits in 6.5 sec

Split and Rephrase

Shashi Narayan, Claire Gardent, Shay B. Cohen, Anastasia Shimorina
2017 Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing  
We propose a new sentence simplification task (Split-and-Rephrase) where the aim is to split a complex sentence into a meaning preserving sequence of shorter sentences.  ...  Like sentence simplification, splitting-and-rephrasing has the potential of benefiting both natural language processing and societal applications.  ...  Acknowledgements We thank Bonnie Webber and Annie Louis for early discussions on the ideas presented in the paper. We thank Rico Sennrich for directing us to multi-source NMT models.  ... 
doi:10.18653/v1/d17-1064 dblp:conf/emnlp/NarayanGCS17 fatcat:ndggre56mrcgxeg4vfddmdat4m

Split and Rephrase [article]

Shashi Narayan and Claire Gardent and Shay B. Cohen and Anastasia Shimorina
2017 arXiv   pre-print
We propose a new sentence simplification task (Split-and-Rephrase) where the aim is to split a complex sentence into a meaning preserving sequence of shorter sentences.  ...  Like sentence simplification, splitting-and-rephrasing has the potential of benefiting both natural language processing and societal applications.  ...  Acknowledgements We thank Bonnie Webber and Annie Louis for early discussions on the ideas presented in the paper. We thank Rico Sennrich for directing us to multi-source NMT models.  ... 
arXiv:1707.06971v1 fatcat:e2x2lq7uqze5heeonwozqhnef4

Data-Driven Sentence Simplification: Survey and Benchmark

Fernando Alva-Manchego, Carolina Scarton, Lucia Specia
2020 Computational Linguistics  
Sentence Simplification (SS) aims to modify a sentence in order to make it easier to read and understand.  ...  We expect that this survey will serve as a starting point for researchers interested in the task and help spark new ideas for future developments.  ...  uses the split MRs and rephrases based on a sequence-to-sequence model.  ... 
doi:10.1162/coli_a_00370 fatcat:k7mlggplrreudk5pgq62x2fmva

Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading [article]

Yifan Gao, Chien-Sheng Wu, Shafiq Joty, Caiming Xiong, Richard Socher, Irwin King, Michael R. Lyu, Steven C.H. Hoi
2020 arXiv   pre-print
Code and models are released at https://github.com/Yifan-Gao/explicit_memory_tracker.  ...  The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions.  ...  Acknowledgments We thank Max Bartolo and Patrick Lewis for evaluating our submitted models on the hidden test set, and for their helpful replies on dataset related questions.  ... 
arXiv:2005.12484v2 fatcat:d32ijotxlzg23dw5loq5fnf3su

Transformer-Based Models for Automatic Identification of Argument Relations: A Cross-Domain Evaluation [article]

Ramon Ruiz-Dolz, Stella Heras, Jose Alemany, Ana García-Fornes
2020 arXiv   pre-print
We obtain a macro F1-score of 0.70 with the US2016 evaluation corpus, and a macro F1-score of 0.61 with the Moral Maze cross-domain corpus.  ...  We present an exhaustive analysis of the behavior of transformer-based models (i.e., BERT, XLNET, RoBERTa, DistilBERT and ALBERT) when predicting argument relations.  ...  We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan V GPUs used for this research.  ... 
arXiv:2011.13187v1 fatcat:hnqfkusc5vb2xf3en44fqg43fe

Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading [article]

Yifan Gao, Chien-Sheng Wu, Jingjing Li, Shafiq Joty, Steven C.H. Hoi, Caiming Xiong, Irwin King, Michael R. Lyu
2020 arXiv   pre-print
Specifically, we split the document into clause-like elementary discourse units (EDU) using a pre-trained discourse segmentation model, and we train our model in a weakly-supervised manner to predict whether  ...  Based on the learned EDU and entailment representations, we either reply to the user our final decision "yes/no/irrelevant" of the initial question, or generate a follow-up question to inquiry more information  ...  Acknowledgments We thank Max Bartolo and Patrick Lewis for evaluating our submitted models on the hidden test set.  ... 
arXiv:2010.01838v3 fatcat:okmyydob35dsrbrk36govm7224

Automatically Detecting Likely Edits in Clinical Notes Created Using Automatic Speech Recognition

Kevin Lybarger, Mari Ostendorf, Meliha Yetisgen
2018 AMIA Annual Symposium Proceedings  
We create detection models using logistic regression and conditional random field models, exploring a variety of text-based features that consider the structure of clinical notes and exploit the medical  ...  Experimental results on a large corpus of practitioner-edited clinical notes show that 67% of sentence-level edits and 45% of word-level edits can be detected with a false detection rate of 15%.  ...  Acknowledgements We thank Eve Riskin, Thomas Payne, and Andrew White for their assistance.  ... 
pmid:29854187 pmcid:PMC5977669 fatcat:6cemlu6pu5f77c4qbxlwcqsdoe

Learning Language-Visual Embedding for Movie Understanding with Natural-Language [article]

Atousa Torabi, Niket Tandon, Leonid Sigal
2016 arXiv   pre-print
Our best model archives Recall@10 of 19.2% on annotation and 18.9% on video retrieval tasks for subset of 1000 samples.  ...  We evaluate our models on large scale LSMDC16 movie dataset for two tasks: 1) Standard Ranking for video annotation and retrieval 2) Our proposed movie multiple-choice test.  ...  Training: We found it useful to train with both video-sentence (LSMDC) and image-sentence (COCO) datasets; to accommodate this for standard ranking task we treat images as one-frame videos.  ... 
arXiv:1609.08124v1 fatcat:4nzwhzuvizej3e7ll36gq5pvie

Neural Machine Translation from Simplified Translations [article]

Josep Crego, Jean Senellart
2016 arXiv   pre-print
Based on knowledge distillation idea, we then train an NMT system using the simplified bi-text, and show that it outperforms the initial system that was built over the reference data set.  ...  We perform an elementary analysis of the translated corpus and report accuracy results of the proposed approach on English-to-French and English-to-German translation tasks.  ...  Acknowledgments We would like to thank Yoon Kim and Prof. Alexander Rush for their valuable insights with knowledge distillation experiments.  ... 
arXiv:1612.06139v1 fatcat:vikiukgwjzfztmgh3gezporz5y

Read, Highlight and Summarize: A Hierarchical Neural Semantic Encoder-based Approach [article]

Rajeev Bhatt Ambati, Saptarashmi Bandyopadhyay, Prasenjit Mitra
2019 arXiv   pre-print
In this paper, we propose a method based on extracting the highlights of a document; a key concept that is conveyed in a few sentences.  ...  Though there is a hierarchy in the way humans use language by forming paragraphs from sentences and sentences from words, hierarchical models have usually not worked that much better than their traditional  ...  We have used the same train/validation/test split and examples for a fair comparison with the existing models.  ... 
arXiv:1910.03177v2 fatcat:mfvtdsxk5ba4fps3tvrtscivrm

Unsupervised Neural Text Simplification

Sai Surya, Abhijit Mishra, Anirban Laha, Parag Jain, Karthik Sankaranarayanan
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
The core framework is composed of a shared encoder and a pair of attentional-decoders, crucially assisted by discrimination-based losses and denoising.  ...  Our analysis (both quantitative and qualitative involving human evaluators) on public test data shows that the proposed model can perform text-simplification at both lexical and syntactic levels, competitive  ...  References Mikel Artetxe, Gorka Labaka, and Eneko Agirre. 2018a. Unsupervised statistical machine translation.  ... 
doi:10.18653/v1/p19-1198 dblp:conf/acl/SuryaMLJS19 fatcat:mvbgh5vzzndenbx3zx6e63mwpu

Integrating Linguistic Knowledge to Sentence Paraphrase Generation

Zibo Lin, Ziran Li, Ning Ding, Hai-Tao Zheng, Ying Shen, Wei Wang, Cong-Zhi Zhao
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
However, it is intuitive that a model can generate more expressive and diverse paraphrase with the help of such knowledge.  ...  Besides, a multi-task architecture is designed to help the framework jointly learn the selection of synonym pairs and the generation of expressive paraphrase.  ...  RNN-based models is adept at capturing the semantics of short sentences with the help of internal memory units.  ... 
doi:10.1609/aaai.v34i05.6354 fatcat:xe5xmsk2d5cvnlnmgfctf244nq

Datasets and Benchmarks for Task-Oriented Log Dialogue Ranking Task

Xinnuo Xu, Yizhe Zhang, Lars Liden, Sungjin Lee
2020 Interspeech 2020  
task labelled with dialogue quality for ranker training and evaluation (3) present a detailed description of the data collection pipeline, which is entirely based on crowd-sourcing (4) finally report  ...  a benchmark result of dialogue ranking, which shows the usability of the data and sets a baseline for future studies.  ...  with seed dialogues. (2) A dialogue system is trained and deployed. (3) Real users interact with the system and generate log dialogues  ... 
doi:10.21437/interspeech.2020-1341 dblp:conf/interspeech/XuZLL20 fatcat:4i4pg2nawbbinmt77qyk76n6ei

Detecting and Classifying Malevolent Dialogue Responses: Taxonomy, Data and Methodology [article]

Yangjun Zhang, Pengjie Ren, Maarten de Rijke
2020 arXiv   pre-print
Second, we create a labelled multi-turn dialogue dataset and formulate the MDRDC task as a hierarchical classification task over this taxonomy.  ...  Corpus-based conversational interfaces are able to generate more diverse and natural responses than template-based or retrieval-based agents.  ...  (See Section 7.4) Dataset For all the experiments, we create training, validation and test splits with a ratio of 7:1:2.  ... 
arXiv:2008.09706v1 fatcat:zipkjnxpqvfdzliccpraiaafpa

Multimodal Intelligence: Representation Learning, Information Fusion, and Applications [article]

Chao Zhang, Zichao Yang, Xiaodong He, Li Deng
2020 arXiv   pre-print
In this paper, we provide a technical review of available models and learning methods for multimodal intelligence.  ...  Therefore, it is of broad interest to study the more difficult and complex problem of modeling and learning across multiple modalities.  ...  ACKNOWLEDGEMENT The authors are grateful to the editor and anonymous reviewers for their valuable suggestions that helped to make this paper better.  ... 
arXiv:1911.03977v3 fatcat:ojazuw3qzvfqrdweul6qdpxuo4
« Previous Showing results 1 — 15 out of 1,282 results