paper-with-me

홈 › Papers

Large Scale Question Paraphrase Retrieval with Smoothed Deep Metric Learning

2019-05-29 · WS 2019 11 · Daniele Bonadiman, Anjishnu Kumar, Arpit Mittal

The goal of a Question Paraphrase Retrieval (QPR) system is to retrieve equivalent questions that result in the same answer as the original question. Such a system can be used to understand and answer rare and noisy reformulations of common questions by mapping them to a set of canonical forms. This has large-scale applications for community Question Answering (cQA) and open-domain spoken language question answering systems. In this paper we describe a new QPR system implemented as a Neural Information Retrieval (NIR) system consisting of a neural network sentence encoder and an approximate k-Nearest Neighbour index for efficient vector retrieval. We also describe our mechanism to generate an annotated dataset for question paraphrase retrieval experiments automatically from question-answer logs via distant supervision. We show that the standard loss function in NIR, triplet loss, does not perform well with noisy labels. We propose smoothed deep metric loss (SDML) and with our experiments on two QPR datasets we show that it significantly outperforms triplet loss in the noisy label setting.

📄 PDF Abstract BibTeX arXiv:1905.12786

Code (0)

등록된 구현이 없습니다.

Tasks

Community Question AnsweringInformation RetrievalMetric LearningQuestion AnsweringRetrievalSentenceTriplet

Methods 이 논문이 사용한 방법론

Triplet Loss The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its…

Similar Papers 제목 키워드 기반

Interpretable Question Answering with Knowledge Graphs

2025-10-22 · Kartikeya Aneja, Manasvi Srivastava, Subhayan Das, Nagender Aneja arxiv

This paper presents a question answering system that operates exclusively on a knowledge graph retrieval without relying on retrieval augmented generation (RAG) with large language models (LLMs). Instead, a small paraphr…

Question AnsweringKnowledge Graphs

Semantic Search as Extractive Paraphrase Span Detection

2021-10-16 · ACL ARR October 2021 10 · Anonymous

In this paper, we approach the problem of semantic search by framing the search task as paraphrase span detection, i.e. given a segment of text as a query phrase, the task is to identify its paraphrase in a given documen…

Extractive Question-AnsweringQuestion AnsweringRetrievalSentence+3

Semantic Search as Extractive Paraphrase Span Detection

2021-12-09 · Jenna Kanerva, Hanna Kitti, Li-Hsin Chang, Teemu Vahtola 외

In this paper, we approach the problem of semantic search by framing the search task as paraphrase span detection, i.e. given a segment of text as a query phrase, the task is to identify its paraphrase in a given documen…

Extractive Question-AnsweringQuestion AnsweringRetrievalSentence+3

A Deep Generative Framework for Paraphrase Generation

2017-09-15 · Ankush Gupta, Arvind Agarwal, Prawaan Singh, Piyush Rai

Paraphrase generation is an important problem in NLP, especially in question answering, information retrieval, information extraction, conversation systems, to name a few. In this paper, we address the problem of generat…

DecoderInformation RetrievalParaphrase GenerationQuestion Answering+2

Fine-tuning CLIP Text Encoders with Two-step Paraphrasing

2024-02-23 · Hyunjae Kim, Seunghyun Yoon, Trung Bui, Handong Zhao 외

Contrastive language-image pre-training (CLIP) models have demonstrated considerable success across various vision-language tasks, such as text-to-image retrieval, where the model is required to effectively process natur…

Image CaptioningImage RetrievalParaphrase GenerationRetrieval+1