paper-with-me

홈 › Papers

Tha3aroon at NSURL-2019 Task 8: Semantic Question Similarity in Arabic

2019-12-28 · NSURL 2019 9 · Ali Fadel, Ibraheem Tuffaha, Mahmoud Al-Ayyoub

In this paper, we describe our team's effort on the semantic text question similarity task of NSURL 2019. Our top performing system utilizes several innovative data augmentation techniques to enlarge the training data. Then, it takes ELMo pre-trained contextual embeddings of the data and feeds them into an ON-LSTM network with self-attention. This results in sequence representation vectors that are used to predict the relation between the question pairs. The model is ranked in the 1st place with 96.499 F1-score (same as the second place F1-score) and the 2nd place with 94.848 F1-score (differs by 1.076 F1-score from the first place) on the public and private leaderboards, respectively.

📄 PDF Abstract BibTeX arXiv:1912.12514

Code (1)

AliOsm/semantic-question-similarity 공식 구현

Tasks

Data AugmentationQuestion Similarity

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
ELMo Embeddings from Language Models, or ELMo, is a type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and…

Similar Papers 제목 키워드 기반

NSURL-2019 Shared Task 8: Semantic Question Similarity in Arabic

2019-09-12 · Haitham Seelawi, Ahmad Mustafa, Hesham Al-Bataineh, Wael Farhan 외

Question semantic similarity (Q2Q) is a challenging task that is very useful in many NLP applications, such as detecting duplicate questions and question answering systems. In this paper, we present the results and findi…

Question AnsweringQuestion SimilaritySemantic SimilaritySemantic Textual Similarity

The Inception Team at NSURL-2019 Task 8: Semantic Question Similarity in Arabic

2020-04-24 · NSURL 2019 9 · Hana Al-Theiabat, Aisha Al-Sadi

This paper describes our method for the task of Semantic Question Similarity in Arabic in the workshop on NLP Solutions for Under-Resourced Languages (NSURL). The aim is to build a model that is able to detect similar se…

Question Similarity

NSURL-2019 Task 8: Semantic Question Similarity in Arabic

2019-09-01 · NSURL 2019 9 · Haitham Seelawi, Ahmad Mustafa, Hesham Al-Bataineh, Wael Farhan 외
Question Similarity

ST NSURL 2019 Shared Task: Semantic Question Similarity in Arabic

2019-09-01 · NSURL 2019 9 · Mohamed Lichouri, Mourad Abbas, Besma Benaziz, Abed Alhakim Freihat
Question Similarity

AtyNegar at NSURL-2019 Task 8: Semantic Question Similarity in Arabic

2019-09-01 · NSURL 2019 9 · Atieh Sharifi, Hossein Hassanpoor, Najmeh Zare Maduyieh
Question Similarity