paper-with-me

Papers

An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information

2021-03-21 · Zejun Li, Zhongyu Wei, Zhihao Fan, Haijun Shan, Xuanjing Huang

In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach achieves positive results, it introduces a sampling bias and fails to distinguish instances with high semantic similarity. To alleviate the bias, we propose a new sampling strategy to select additional intra-document image-sentence pairs as positive or negative samples. Furthermore, to recognize the complex pattern in intra-document samples, we propose a Transformer based model to capture fine-grained features and implicitly construct a graph for each document, where concepts in a document are introduced to bridge the representation learning of images and sentences in the context of a document. Experimental results show the effectiveness of our approach to alleviate the bias and learn well-aligned multimodal representations.

📄 PDF Abstract BibTeX arXiv:2104.02605

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningSemantic SimilaritySemantic Textual SimilaritySentence

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Centrality Meets Centroid: A Graph-based Approach for Unsupervised Document Summarization

2021-03-29 · Haopeng Zhang, Jiawei Zhang

Unsupervised document summarization has re-acquired lots of attention in recent years thanks to its simplicity and data independence. In this paper, we propose a graph-based unsupervised approach for extractive document …

Document SummarizationExtractive Document SummarizationSentence

Zero-Shot Text Matching for Automated Auditing using Sentence Transformers

2022-10-28 · David Biesner, Maren Pielka, Rajkumar Ramamurthy, Tim Dilmaghani 외

Natural language processing methods have several applications in automated auditing, including document or passage classification, information retrieval, and question answering. However, training such models requires a l…

Information RetrievalQuestion AnsweringRetrievalSemantic Similarity+3

Combining Word Embeddings and N-grams for Unsupervised Document Summarization

2020-04-25 · Zhuolin Jiang, Manaj Srivastava, Sanjay Krishna, David Akodes 외

Graph-based extractive document summarization relies on the quality of the sentence similarity graph. Bag-of-words or tf-idf based sentence similarity uses exact word matching, but fails to measure the semantic similarit…

DiversityDocument SummarizationExtractive Document SummarizationExtractive Summarization+8

Unsupervised Document Embedding via Contrastive Augmentation

2021-03-26 · Dongsheng Luo, Wei Cheng, Jingchao Ni, Wenchao Yu 외

We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image …

Contrastive LearningData AugmentationDocument ClassificationDocument Embedding+3

Optimal Partial Transport Based Sentence Selection for Long-form Document Matching

2022-10-01 · COLING 2022 10 · Weijie Yu, Liang Pang, Jun Xu, Bing Su 외

One typical approach to long-form document matching is first conducting alignment between cross-document sentence pairs, and then aggregating all of the sentence-level matching signals. However, this approach could be pr…

FormSentence