Large Scale Question Paraphrase Retrieval with Smoothed Deep Metric Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Community Question AnsweringInformation RetrievalMetric LearningQuestion AnsweringRetrievalSentenceTripletMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Interpretable Question Answering with Knowledge Graphs
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 GraphsSemantic Search as Extractive Paraphrase Span Detection
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+3Semantic Search as Extractive Paraphrase Span Detection
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+3A Deep Generative Framework for Paraphrase Generation
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+2Fine-tuning CLIP Text Encoders with Two-step Paraphrasing
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