Neural Paraphrase Identification of Questions with Noisy Pretraining
نویسندگان
چکیده
We present a solution to the problem of paraphrase identification of questions. We focus on a recent dataset of question pairs annotated with binary paraphrase labels and show that a variant of the decomposable attention model (Parikh et al., 2016) results in accurate performance on this task, while being far simpler than many competing neural architectures. Furthermore, when the model is pretrained on a noisy dataset of automatically collected question paraphrases, it obtains the best reported performance on the dataset.
منابع مشابه
Identification of Cement Rotary Kiln in Noisy Condition using Takagi-Sugeno Neuro-fuzzy System
Cement rotary kiln is the main part of cement production process that have always attracted many researchers’ attention. But this complex nonlinear system has not been modeled efficiently which can make an appropriate performance specially in noisy condition. In this paper Takagi-Sugeno neuro-fuzzy system (TSNFS) is used for identification of cement rotary kiln, and gradient descent (GD) algori...
متن کاملCMU OAQA at TREC 2017 LiveQA: A Neural Dual Entailment Approach for Question Paraphrase Identification
In this paper, we present CMU’s question answering system that was evaluated in the TREC 2017 LiveQA Challenge. Our overall approach this year is similar to the one used in 2015 and 2016. This system answers real-user submitted questions from Yahoo! Answers website and medical questions, which involves retrieving relevant web pages, extracting answer candidate texts, ranking and selecting final...
متن کاملA Deep Network Model for Paraphrase Detection in Short Text Messages
This paper is concerned with paraphrase detection. The ability to detect similar sentences written in natural language is crucial for several applications, such as text mining, text summarization, plagiarism detection, authorship authentication and question answering. Given two sentences, the objective is to detect whether they are semantically identical. An important insight from this work is ...
متن کاملSpeech restoration based on deep learning autoencoder with layer-wised pretraining
Neural network can be used to “remember” speech patterns by encoding speech statistical regularity in network parameters. Clean speech can be “recalled” when noisy speech is input to the network. Adding more hidden layers can increase network capacity. But when the hidden layer size increases (deep network), the network is easily to be trapped to a local solution when traditional training strat...
متن کاملBidirectional Long Short-Term Memory with Gated Relevance Network for Paraphrase Identification
Semantic interaction between text segments, which has been proven to be very useful for detecting the paraphrase relations, is often ignored in the study of paraphrase identification. In this paper, we adopt a neural network model for paraphrase identification, called as bidirectional Long Short-Term Memory-Gated Relevance Network (BiLSTM+GRN). According to this model, a gated relevance network...
متن کامل