natural-language-processing-9

Semantic Retrieval

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in semantic-retrieval-9

Trend

Dataset

Best Model

Actions

Contract Discovery

Libraries

i

Use these libraries to find semantic-retrieval-9 models and implementations

Datasets

Contract Discovery

Phrase-in-Context

Subtasks

No subtasks available.

Most implemented papers

Revealing the Importance of Semantic Retrieval for Machine Reading at Scale

Mohit Bansal, Yixin Nie, Songhe Wang•Sat Aug 31 2019

This work proposes a simple yet effective pipeline system with special consideration on hierarchical semantic retrieval at both paragraph and sentence level, and their potential effects on the downstream task, and illustrates that intermediate semantic retrieval modules are vital for shaping upstream data distribution and providing better data for downstream modeling.

147

Content

0

Paper Graph

MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval

Zhiyong Lu, Qiao Jin, Qingyu Chen, Won Kim, Donald C. Comeau, Lana Yeganova, John Wilbur•Sat Jul 01 2023

Experimental results show that MedCPT sets new state-of-the-art performance on six biomedical IR tasks, outperforming various baselines including much larger models including much larger models such as GPT-3-sized cpt-text-XL.

201 0

Paper Graph

Semantic Query-by-example Speech Search Using Visual Grounding

Karen Livescu, H. Kamper, Aristotelis Anastassiou•Sun Apr 14 2019

A segmental QbE approach where variable-duration speech segments (queries, search utterances) are mapped to fixed-dimensional embedding vectors and it is shown that aQbE system using an embedding function trained on visually grounded speech data outperforms a purely acoustic QBE system in terms of both exact and semantic retrieval performance.

30 0

Paper Graph

Sentence Embedding Models for Ancient Greek Using Multilingual Knowledge Distillation

Kevin Krahn, D. Tate, Andrew C. Lamicela•Wed Aug 23 2023

This work uses a multilingual knowledge distillation approach to train BERT models to produce sentence embeddings for Ancient Greek text and evaluates their models on translation search, semantic similarity, and semantic retrieval tasks and investigates translation bias.

5 0

Paper Graph

Contract Discovery: Dataset and a Few-shot Semantic Retrieval Challenge with Competitive Baselines

Łukasz Borchmann, Dawid Wisniewski, Andrzej Gretkowski, Izabela Kosmala, Dawid Jurkiewicz, Lukasz Szalkiewicz, Gabriela Pałka, Karol Kaczmarek, Agnieszka Kaliska, Filip Grali'nski•Wed Oct 07 2020

It is shown that state-of-the-art pretrained encoders fail to provide satisfactory results on the task proposed, and Language Model-based solutions perform better, especially when unsupervised fine-tuning is applied.

21 0

Paper Graph

Semantic Models for the First-Stage Retrieval: A Comprehensive Review

Ruqing Zhang, Yixing Fan, Jiafeng Guo, Xueqi Cheng, Yinqiong Cai, Fei Sun•Sun Mar 07 2021

The current landscape of the first-stage retrieval models under a unified framework is described to clarify the connection between classical term-based retrieval methods, early semantic retrieved methods, and neural semantic retrieval methods.

160 0

Paper Graph

Deep Unsupervised Image Hashing by Maximizing Bit Entropy

J. V. Gemert, Yun-qiang Li•Mon Dec 21 2020

This work proposes an unsupervised deep hashing layer called Bi-Half Net that maximizes entropy of the binary codes and designs a new parameter-free network layer to explicitly force continuous image features to approximate the optimal half-half bit distribution.

104 0

Paper Graph

Evaluation of Audio-Visual Alignments in Visually Grounded Speech Models

Khazar Khorrami, O. Räsänen•Sun Jul 04 2021

This work formalizes the alignment problem in terms of an audiovisual alignment tensor that is based on earlier VGS work, introduces systematic metrics for evaluating model performance in aligning visual objects and spoken words, and proposes a new VGS model variant for the alignment task utilizing cross-modal attention layer.

9 0

Paper Graph

Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation

Xuandong Zhao, Lei Li, Zhiguo Yu, Ming-li Wu•Mon Mar 14 2022

This paper proposes Homomorphic Projective Distillation to learn compressed sentence embeddings and augments a small Transformer encoder model with learnable projection layers to produce compact representations while mimicking a large pre-trained language model to retain the sentence representation quality.

8 0

Paper Graph

Semantic Information Recovery in Wireless Networks

Edgar Beck, C. Bockelmann, A. Dekorsy•Wed Apr 27 2022

This work model semantics by means of hidden random variables and defines the semantic communication task as the data-reduced and reliable transmission of messages over a communication channel such that semantics is best preserved, and considers this task as an end-to-end Information Bottleneck problem, enabling compression while preserving relevant information.

33 0

Paper Graph

Adding a benchmark result helps the community track progress.