Together we stand: Siamese Networks for Similar Question Retrieval

Abstract

Community Question Answering (cQA) services like Yahoo! Answers 1 , Baidu Zhidao 2 , Quora 3 , StackOverflow 4 etc. provide a platform for interaction with experts and help users to obtain precise and accurate answers to their questions. The time lag between the user posting a question and receiving its answer could be reduced by retrieving similar historic questions from the cQA archives. The main challenge in this task is the "lexicosyntactic" gap between the current and the previous questions. In this paper, we propose a novel approach called "Siamese Convolutional Neural Network for cQA (SCQA)" to find the semantic similarity between the current and the archived questions. SCQA consist of twin convolutional neural networks with shared parameters and a contrastive loss function joining them. SCQA learns the similarity metric for question-question pairs by leveraging the question-answer pairs available in cQA forum archives. The model projects semantically similar question pairs nearer to each other and dissimilar question pairs farther away from each other in the semantic space. Experiments on large scale reallife "Yahoo! Answers" dataset reveals that SCQA outperforms current state-of-theart approaches based on translation models, topic models and deep neural network https://answers.yahoo.com/

A Mention-Ranking Model for Abstract Anaphora Resolution

“…Siamese Nets distinguish between similar and dissimilar pairs of samples by optimizing a loss over the metric induced by the representations. It is widely used in vision (Chopra et al, 2005), and in NLP for semantic similarity, entailment, query normalization and QA (Mueller and Thyagarajan, 2016;Neculoiu et al, 2016;Das et al, 2016).…”

Principle-to-Program: Neural Methods for Similar Question Retrieval in Online Communities

“…- [5] learns shared parameters and similarity metric minimizing contrastive-loss energy function connecting twin networks, - [7] preserves local neighborhood structure of and mirrors semantic similarity among question and answer spaces, - [9] represents hierarchical structures of word and concept information with layer-by-layer composition and pooling leading to question embedding that captures semantics/syntax.…”

Learning Disentangled Representations of Texts with Application to Biomedical Abstracts

“…Models combining similarity with neural networks mainly revolve around Siamese networks (Chopra et al, 2005) which use pairwise distances to learn embeddings (Schroff et al, 2015), a tactic we have followed here. Similarity judgments have also been used to generate document embeddings for IR tasks (Shen et al, 2014;Das et al, 2016).…”