Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems

2019-11-18 · Qiang Huang, Jianhui Bu, Weijian Xie, Shengwen Yang, Weijia Wu, Li-Ping Liu

Question Answering (QA) systems are used to provide proper responses to users' questions automatically. Sentence matching is an essential task in the QA systems and is usually reformulated as a Paraphrase Identification (PI) problem. Given a question, the aim of the task is to find the most similar question from a QA knowledge base. In this paper, we propose a Multi-task Sentence Encoding Model (MSEM) for the PI problem, wherein a connected graph is employed to depict the relation between sentences, and a multi-task learning model is applied to address both the sentence matching and sentence intent classification problem. In addition, we implement a general semantic retrieval framework that combines our proposed model and the Approximate Nearest Neighbor (ANN) technology, which enables us to find the most similar question from all available candidates very quickly during online serving. The experiments show the superiority of our proposed method as compared with the existing sentence matching models.

📄 PDF Abstract BibTeX arXiv:1911.07405

Code (0)

등록된 구현이 없습니다.

Tasks

intent-classification Intent Classification Multi-Task Learning Paraphrase Identification Question Answering Retrieval Semantic RetrievalSentence

Multilingual Universal Sentence Encoder for Semantic Retrieval

2019-07-09 · ACL 2020 6 · Yinfei Yang, Daniel Cer, Amin Ahmad, Mandy Guo 외

We introduce two pre-trained retrieval focused multilingual sentence encoding models, respectively based on the Transformer and CNN model architectures. The models embed text from 16 languages into a single semantic spac…

Question Answering Retrieval Semantic Retrieval Sentence+4

Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval

2017-08-08 · ICCV 2017 10 · Yuming Shen, Li Liu, Ling Shao, Jingkuan Song

Cross-modal hashing is usually regarded as an effective technique for large-scale textual-visual cross retrieval, where data from different modalities are mapped into a shared Hamming space for matching. Most of the trad…

Cross-Modal Retrieval Descriptive Retrieval

SEAGLE: A Platform for Comparative Evaluation of Semantic Encoders for Information Retrieval

2019-11-01 · IJCNLP 2019 11 · Fabian David Schmidt, Markus Dietsche, Simone Paolo Ponzetto, Goran Glava{\v{s}}

We introduce Seagle, a platform for comparative evaluation of semantic text encoding models on information retrieval (IR) tasks. Seagle implements (1) word embedding aggregators, which represent texts as algebraic aggreg…

Information Retrieval Retrieval Sentence Sentence Retrieval+1

ConTextual Masked Auto-Encoder for Dense Passage Retrieval

2022-08-16 · Xing Wu, Guangyuan Ma, Meng Lin, Zijia Lin 외

Dense passage retrieval aims to retrieve the relevant passages of a query from a large corpus based on dense representations (i.e., vectors) of the query and the passages. Recent studies have explored improving pre-train…

Decoder Passage Retrieval Retrieval Sentence

A Multi-level Distillation based Dense Passage Retrieval Model

2023-12-28 · Haifeng Li, Mo Hai, Dong Tang

Ranker and retriever are two important components in dense passage retrieval. The retriever typically adopts a dual-encoder model, where queries and documents are separately input into two pre-trained models, and the vec…

Passage Retrieval Retrieval Sentence