Deep Attentive Ranking Networks for Learning to Order Sentences

Kumar, Pawan; Brahma, Dhanajit; Karnick, Harish; Rai, Piyush

doi:10.1609/aaai.v34i05.6323

Cited by 33 publications

(37 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allows for the original input to then be matrix-multiplied by the row-stochastic permutation matrix, resulting in the desired reordering (Nishida & Nakayama, 2017), (Emami & Ranka, 2018). It is a sign of the complexity of the field that no clear preferred formalization of its core challenge has emerged, with ranking (for example) still finding useful application in active research (Kumar et al, 2020).…”

Section: Progress In Permutation Learningmentioning

confidence: 99%

“…Alternatively, if a ranking framework is applied, where a score is generated for each element and subsequently used to sort all elements into a new permutation, we gain access to well documented listwise losses, such as the ones successfully employed in the ListNet or ListMLE (Kumar et al, 2020) frameworks. Many metrics that would lend themselves to ordering challenges do not have defined derivatives for their entire domain.…”

Section: Differentiable Loss Functionsmentioning

confidence: 99%

See 1 more Smart Citation

Set-to-Sequence Methods in Machine Learning: A Review

Jurewicz¹,

Derczynski

2021

jair

View full text Add to dashboard Cite

Machine learning on sets towards sequential output is an important and ubiquitous task, with applications ranging from language modelling and meta-learning to multi-agent strategy games and power grid optimization. Combining elements of representation learning and structured prediction, its two primary challenges include obtaining a meaningful, permutation invariant set representation and subsequently utilizing this representation to output a complex target permutation. This paper provides a comprehensive introduction to the _eld as well as an overview of important machine learning methods tackling both of these key challenges, with a detailed qualitative comparison of selected model architectures.

show abstract

Section: Progress In Permutation Learningmentioning

confidence: 99%

Section: Differentiable Loss Functionsmentioning

confidence: 99%

Set-to-Sequence Methods in Machine Learning: A Review

Jurewicz¹,

Derczynski

2021

jair

View full text Add to dashboard Cite

show abstract

“…(1) Ranking or Sorting frameworks: Pairwise Model ; RankTxNet (Kumar et al, 2020); B-TSort (Prabhumoye et al, 2020).…”

Section: Baselinesmentioning

confidence: 99%

“…In recent years, several approaches based on ranking or sorting frameworks have been devel- oped to deal with this task. RankTxNet (Kumar et al, 2020) computes a score for each sentence and sorts these scores with ranking based loss functions. Pairwise Model adopts a pairwise ranking algorithm to learn the relative order of each sentence pair.…”

Section: Introductionmentioning

confidence: 99%

BERT-enhanced Relational Sentence Ordering Network

Cui¹,

Li²,

Zhang³

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

In this paper, we introduce a novel BERTenhanced Relational Sentence Ordering Network (referred to as BERSON) by leveraging BERT for capturing a better dependency relationship among sentences to enhance the coherence modeling for the entire paragraph. In particular, we develop a new Relational Pointer Decoder (referred as RPD) by incorporating the relative ordering information into the pointer network with a Deep Relational Module (referred as DRM), which utilizes BERT to exploit the deep semantic connection and relative ordering between sentences. This enables us to strengthen both local and global dependencies among sentences. Extensive evaluations are conducted on six public datasets. The experimental results demonstrate the effectiveness and promise of BERSON, showing a significant improvement over the state-of-the-art by a wide margin. * Corresponding author An unordered set of sentences Coherent paragraph 1 Dan was walking during the night.1 Dan was walking during the night. 3 They tried to steal his book bag.2 A group of thieves surrounded him. 4 A bystander noticed them.3 They tried to steal his book bag. 2 A group of thieves surrounded him. 4 A bystander noticed them. 5 But she continued to walk away.5 But she continued to walk away.

show abstract

“…Cui et al (2018) use a transformer network for the paragraph encoder to allow for reliable paragraph encoding. Prior work (Logeswaran et al, 2018;Cui et al, 2018;Kumar et al, 2020) has treated this task as a sequence prediction task where the order of the sentences is predicted as a sequence. The decoder is initialized by the document representation and it outputs the index of sentences in sequential order.…”

Section: Introductionmentioning

confidence: 99%

Topological Sort for Sentence Ordering

Prabhumoye¹,

Salakhutdinov²,

Black³

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Sentence ordering is the task of arranging the sentences of a given text in the correct order. Recent work using deep neural networks for this task has framed it as a sequence prediction problem. In this paper, we propose a new framing of this task as a constraint solving problem and introduce a new technique to solve it. Additionally, we propose a human evaluation for this task. The results on both automatic and human metrics across four different datasets show that this new technique is better at capturing coherence in documents.

show abstract

Deep Attentive Ranking Networks for Learning to Order Sentences

Cited by 33 publications

References 17 publications

Set-to-Sequence Methods in Machine Learning: A Review

Set-to-Sequence Methods in Machine Learning: A Review

BERT-enhanced Relational Sentence Ordering Network

Topological Sort for Sentence Ordering

Contact Info

Product

Resources

About