natural-language-processing-7

Question Similarity

3260 papers • 126 benchmarks • 313 datasets

This is the problem of detecting duplicate questions in forums, which is an important step towards automating the process of answering new questions

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in question-similarity-7

Trend

Dataset

Best Model

Actions

Q2Q Arabic Benchmark

Libraries

i

Use these libraries to find question-similarity-7 models and implementations

Datasets

LCQMC

Subtasks

Medical question pair similarity computation

Most implemented papers

A question-entailment approach to question answering

Asma Ben Abacha, Dina Demner-Fushman•Tue Jan 22 2019

This work proposes a novel QA approach based on Recognizing Question Entailment (RQE) and describes the QA system and resources that are built and evaluated on real medical questions and finds that this approach exceeds the best results of the medical task with a 29.8% increase over the best official score.

251

Content

0

Paper Graph

Deep Learning Models for Multilingual Hate Speech Detection

Binny Mathew, Punyajoy Saha, Animesh Mukherjee, Sai Saket Aluru•Mon Apr 13 2020

A large scale analysis of multilingual hate speech in 9 languages from 16 different sources shows that in low resource setting, simple models such as LASER embedding with logistic regression performs the best, while in high resource setting BERT based models perform better.

173 0

Paper Graph

IIT-UHH at SemEval-2017 Task 3: Exploring Multiple Features for Community Question Answering and Implicit Dialogue Identification

Asif Ekbal, P. Bhattacharyya, Seid Muhie Yimam, Chris Biemann, D. Gupta, T. Nandi, S. Kohail•Mon Jul 31 2017

A Support Vector Machine (SVM) based system that makes use of textual, domain-specific, word-embedding and topic-modeling features, and a novel method for dialogue chain identification in comment threads is proposed.

13 0

Paper Graph

SwissAlps at SemEval-2017 Task 3: Attention-based Convolutional Neural Network for Community Question Answering

Jan Deriu, Mark Cieliebak•Mon Jul 31 2017

The method builds on a siamese CNN architecture which is extended by two attention mechanisms and achieves 7th place obtaining a MAP score of 86:24 points on the Question-Comment Similarity subtask.

10 0

Paper Graph

Learning Semantic Textual Similarity from Conversations

Daniel Matthew Cer, Yinfei Yang, Noah Constant, Yun-Hsuan Sung, Sheng-yi Kong, Steve Yuan, B. Strope, R. Kurzweil, Petr Pilar, Heming Ge•Thu Apr 19 2018

A novel approach to learn representations for sentence-level semantic similarity using conversational data and achieves the best performance among all neural models on the STS Benchmark and is competitive with the state-of-the-art feature engineered and mixed systems for both tasks.

165 0

Paper Graph

Injecting Relational Structural Representation in Neural Networks for Question Similarity

Alessandro Moschitti, Antonio Uva, Daniele Bonadiman•Tue Jun 19 2018

This paper proposes to inject structural representations in NNs by learning a model with Tree Kernels on relatively few pairs of questions as gold standard training data is typically scarce, and predicting labels on a very large corpus of question pairs.

10 0

Paper Graph

FAQ Retrieval using Query-Question Similarity and BERT-Based Query-Answer Relevance

Tomohide Shibata, S. Kurohashi, Wataru Sakata, Ribeka Tanaka•Tue May 07 2019

A FAQ retrieval system that considers the similarity between a user's query and a question as well as the relevance between the query and an answer, and demonstrates that the proposed method outperforms baseline methods on these datasets.

113 0

Paper Graph

Adversarial Domain Adaptation for Duplicate Question Detection

Preslav Nakov, Alessandro Moschitti, Darsh J. Shah, Tao Lei, Salvatore Romeo•Thu Sep 06 2018

This work addresses the problem of detecting duplicate questions in forums, and focuses on adversarial domain adaptation, deriving important findings about when it performs well and what properties of the domains are important in this regard.

81 0

Paper Graph

SemEval-2017 Task 3: Community Question Answering

Hamdy Mubarak, Preslav Nakov, Karin M. Verspoor, Alessandro Moschitti, Timothy Baldwin, Doris Hoogeveen, Lluís Màrquez i Villodre•Mon Jul 31 2017

SemEval–2017 Task 3 on Community Question Answering reran the four subtasks from SemEval-2016, providing all the data from 2015 and 2016 for training, and fresh data for testing, and added a new subtask E in order to enable experimentation with Multi-domain Question Duplicate Detection in a larger-scale scenario, using StackExchange subforums.

231 0

Paper Graph

Question Similarity in Community Question Answering: A Systematic Exploration of Preprocessing Methods and Models

Antal van den Bosch, Thiago Castro Ferreira, Emiel Krahmer, Florian Kunneman•Mon Oct 21 2019

This paper systematically combines and compares the two approaches to automatically detect question-similarity, and analyzes the impact of preprocessing steps and word meaning similarity based on different distributions on the performance of the task.

11 0

Paper Graph

Adding a benchmark result helps the community track progress.