paper-with-me

Papers

Learning semantic similarity in a continuous space

2018-12-01 · NeurIPS 2018 12 · Michel Deudon

We address the problem of learning semantic representation of questions to measure similarity between pairs as a continuous distance metric. Our work naturally extends Word Mover’s Distance (WMD) [1] by representing text documents as normal distributions instead of bags of embedded words. Our learned metric measures the dissimilarity between two questions as the minimum amount of distance the intent (hidden representation) of one question needs to "travel" to match the intent of another question. We first learn to repeat, reformulate questions to infer intents as normal distributions with a deep generative model [2] (variational auto encoder). Semantic similarity between pairs is then learned discriminatively as an optimal transport distance metric (Wasserstein 2) with our novel variational siamese framework. Among known models that can read sentences individually, our proposed framework achieves competitive results on Quora duplicate questions dataset. Our work sheds light on how deep generative models can approximate distributions (semantic representations) to effectively measure semantic similarity with meaningful distance metrics from Information Theory.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic SimilaritySemantic Textual Similarity

Similar Papers 제목 키워드 기반

Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations

2023-05-24 · James Y. Huang, Wenlin Yao, Kaiqiang Song, Hongming Zhang 외

Traditional sentence embedding models encode sentences into vector representations to capture useful properties such as the semantic similarity between sentences. However, in addition to similarity, sentence semantics ca…

DecoderRepresentation LearningSemantic SimilaritySemantic Textual Similarity+5

Vectorial Semantic Spaces Do Not Encode Human Judgments of Intervention Similarity

2018-10-01 · CONLL 2018 10 · Paola Merlo, Francesco Ackermann

Despite their practical success and impressive performances, neural-network-based and distributed semantics techniques have often been criticized as they remain fundamentally opaque and difficult to interpret. In a vein …

Word Embeddings

Deep Metric Learning Beyond Binary Supervision

2019-04-21 · CVPR 2019 6 · Sungyeon Kim, Minkyo Seo, Ivan Laptev, Minsu Cho 외

Metric Learning for visual similarity has mostly adopted binary supervision indicating whether a pair of images are of the same class or not. Such a binary indicator covers only a limited subset of image relations, and i…

Image CaptioningImage RetrievalMetric LearningRetrieval+3

Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables

2022-11-07 · Erxin Yu, Lan Du, Yuan Jin, Zhepei Wei 외

Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in…

Language ModelingLanguage ModellingQuantizationRepresentation Learning+3

Beyond Post-Quantization: Native Hash Learning with a Dedicated HASH Token

2026-07-03 · Xinze Liu, Ding Wang, Hengjie Zhu, Dayan Wu arxiv

Efficient large-scale image retrieval requires compact representations that preserve semantic similarity under fast Hamming-space search. Deep hashing is appealing, but most existing CNN- and ViT-based methods still foll…

Semantic SimilarityCode GenerationImage Retrieval