Sentence Ordering and Coherence Modeling using Recurrent Neural Networks

Logeswaran, Lajanugen; Lee, Honglak; Radev, Dragomir

doi:10.1609/aaai.v32i1.11997

Cited by 53 publications

(34 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A series of approaches had been invented to tackle this rearranging problem. [ 89–92 ] There the topological sort method was selected, [ 93,94 ] a standard algorithm for linear ordering of the vertices of a directed graph. Precisely, we have

\mathcal {C}_n

set of constraints for this sub‐trajectory.…”

Section: Methodsmentioning

confidence: 99%

Pre‐Training of Equivariant Graph Matching Networks with Conformation Flexibility for Drug Binding

Jin

Jiang³

et al. 2022

Advanced Science

View full text Add to dashboard Cite

The latest biological findings observe that the motionless “lock‐and‐key” theory is not generally applicable and that changes in atomic sites and binding pose can provide important information for understanding drug binding. However, the computational expenditure limits the growth of protein trajectory‐related studies, thus hindering the possibility of supervised learning. A spatial‐temporal pre‐training method based on the modified equivariant graph matching networks, dubbed ProtMD which has two specially designed self‐supervised learning tasks: atom‐level prompt‐based denoising generative task and conformation‐level snapshot ordering task to seize the flexibility information inside molecular dynamics (MD) trajectories with very fine temporal resolutions is presented. The ProtMD can grant the encoder network the capacity to capture the time‐dependent geometric mobility of conformations along MD trajectories. Two downstream tasks are chosen to verify the effectiveness of ProtMD through linear detection and task‐specific fine‐tuning. A huge improvement from current state‐of‐the‐art methods, with a decrease of 4.3% in root mean square error for the binding affinity problem and an average increase of 13.8% in the area under receiver operating characteristic curve and the area under the precision‐recall curve for the ligand efficacy problem is observed. The results demonstrate a strong correlation between the magnitude of conformation's motion in the 3D space and the strength with which the ligand binds with its receptor.

show abstract

\mathcal {C}_n

set of constraints for this sub‐trajectory.…”

Section: Methodsmentioning

confidence: 99%

Pre‐Training of Equivariant Graph Matching Networks with Conformation Flexibility for Drug Binding

Jin

Jiang³

et al. 2022

Advanced Science

View full text Add to dashboard Cite

show abstract

“…Sentence encoders are trained to extract sentence-level features [49,58,74]. We use SBERT [74] which finetunes a pre-trained language model to allow it to better capture semantic similarity using feature cosine distance.…”

Section: Sampling Image Pairs Using Languagementioning

confidence: 99%

Learning Visual Representations via Language-Guided Sampling

Banani¹,

Desai²,

Johnson³

2023

Preprint

View full text Add to dashboard Cite

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. This happens because language abstracts away visual variation to represent and communicate concepts. Building on this intuition, we propose an alternative approach to visual learning: using language similarity to sample semantically similar image pairs for contrastive learning. Our approach deviates from image-based contrastive learning by using language to sample pairs instead of hand-crafted augmentations or learned clusters. Our approach also deviates from image-text contrastive learning by relying on pre-trained language models to guide the learning rather than minimize a cross-modal similarity. Through a series of experiments, we show that language-guided learning can learn better features than both image-image and image-text representation learning approaches.

show abstract

“…Neural language models that generate word and document embeddings have become increasingly popular in recent years. Numerous research efforts have suggested enhancing distributed representations of documents/sentences [Le and Mikolov, 2014, Dai et al, 2015, Kiros et al, 2015, Hill et al, 2016, Pagliardini et al, 2017, Logeswaran and Lee, 2018, Gupta et al, 2019, Cer et al, 2018, Sinoara et al, 2019. These methods efficiently calculate the semantic similarity of words by capturing the similarity of the respective vector representations.…”

Section: Advanced Language Modelsmentioning

confidence: 99%

Leveraging Structural and Semantic Measures for JSON Document Clustering

D¹,

Thilagam²

2023

jucs

View full text Add to dashboard Cite

In recent years, the increased use of smart devices and digital business opportunities has generated massive heterogeneous JSON data daily, making efficient data storage and management more difficult. Existing research uses different similarity metrics and clusters the documents to support the above tasks effectively. However, extant approaches have focused on either structural or semantic similarity of schemas. As JSON documents are application-specific, differently annotated JSON schemas are not only structurally heterogeneous but also differ by the context of the JSON attributes. Therefore, there is a need to consider the structural, semantic, and contextual properties of JSON schemas to perform meaningful clustering of JSON documents. This work proposes an approach to cluster heterogeneous JSON documents using the similarity fusion method. The similarity fusion matrix is constructed using structural, semantic, and contextual measures of JSON schemas. The experimental results demonstrate that the proposed approach outperforms the existing approaches significantly. 

show abstract

Sentence Ordering and Coherence Modeling using Recurrent Neural Networks

Cited by 53 publications

References 26 publications

Pre‐Training of Equivariant Graph Matching Networks with Conformation Flexibility for Drug Binding

Pre‐Training of Equivariant Graph Matching Networks with Conformation Flexibility for Drug Binding

Learning Visual Representations via Language-Guided Sampling

Leveraging Structural and Semantic Measures for JSON Document Clustering

Contact Info

Product

Resources

About