natural-language-processing-2

Sentence Pair Modeling

3260 papers • 126 benchmarks • 313 datasets

Comparing two sentences and their relationship based on their internal representation.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in sentence-pair-modeling-2

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find sentence-pair-modeling-2 models and implementations

Datasets

No datasets available.

Subtasks

Semantic Similarity

Most implemented papers

ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations

Jiaxin Bai, Shizhe Diao, Yan Song, Tong Zhang, Yonggang Wang•Fri Nov 01 2019

ZEN is proposed, a BERT-based Chinese text encoder enhanced by n-gram representations, where different combinations of characters are considered during training, thus potential word or phrase boundaries are explicitly pre-trained and fine-tuned with the character encoder (BERT).

145

Content

0

Paper Graph

Character-Based Neural Networks for Sentence Pair Modeling

Wuwei Lan, Wei Xu•Sun May 20 2018

The experiments show that subword models without any pretrained word embedding can achieve new state-of-the-art results on two social media datasets and competitive results on news data for paraphrase identification.

17 0

Paper Graph

Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering

Wuwei Lan, Wei Xu•Mon Jun 11 2018

It is shown that encoding contextual information by LSTM and inter-sentence interactions are critical and the Enhanced Sequential Inference Model is the best so far for larger datasets, while the Pairwise Word Interaction Model achieves the best performance when less data is available.

127 0

Paper Graph

Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks

Nandan Thakur, Iryna Gurevych, Nils Reimers, Johannes Daxenberger•Thu Oct 15 2020

This work presents a simple yet efficient data augmentation strategy called Augmented SBERT, where the cross-encoder is used to label a larger set of input pairs to augment the training data for the bi-encoding, and shows that, in this process, selecting the sentence pairs is non-trivial and crucial for the success of the method.

293 0

Paper Graph

Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding

Avi Caciularu, Noam Koenigstein, Itzik Malkiel, Oren Barkan, Noam Razin, Ori Katz•Tue Aug 13 2019

Distilled Sentence Embedding is introduced - a model that is based on knowledge distillation from cross-attentive models, focusing on sentence-pair tasks that significantly outperforms several ELMO variants and other sentence embedding methods, while accelerating computation of the query-candidate sentence-pairs similarities.

37 0

Paper Graph

Adding a benchmark result helps the community track progress.