HFL-RC System at SemEval-2018 Task 11: Hybrid Multi-Aspects Model for Commonsense Reading Comprehension
نویسندگان
چکیده
This paper describes the system which got the state-of-the-art results at SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge. In this paper, we present a neural network called Hybrid Multi-Aspects (HMA) model, which mimic the human’s intuitions on dealing with the multiple-choice reading comprehension. In this model, we aim to produce the predictions in multiple aspects by calculating attention among the text, question and choices, and combine these results for final predictions. Experimental results show that our HMA model could give substantial improvements over the baseline system and got the first place on the final test set leaderboard with the accuracy of 84.13%.
منابع مشابه
Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension
This paper describes our system for SemEval2018 Task 11: Machine Comprehension using Commonsense Knowledge. We use Threeway Attentive Networks (TriAN) to model interactions between the passage, question and answers. To incorporate commonsense knowledge, we augment input with relation embedding from the graph of general knowledge ConceptNet (Speer et al., 2017). As a result, our system achieves ...
متن کاملMCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge
We introduce a large dataset of narrative texts and questions about these texts, intended to be used in a machine comprehension task that requires reasoning using commonsense knowledge. Our dataset complements similar datasets in that we focus on stories about everyday activities, such as going to the movies or working in the garden, and that the questions require commonsense knowledge, or more...
متن کاملThe Comparative Impact of Content-Based and Task-Based Teaching in a Critical Thinking Setting on EFL Learners’ Reading Comprehension
This study was an attempt to investigate the comparative impact of two types of teaching approaches, namely content-based (CBI) and task-based (TBLT) instruction on the reading comprehension of Iranian EFL learners. For this purpose, sixty intermediate students from a pool of eighty five students studying at a private language school were chosen using a piloted PET. The students were then rando...
متن کاملPrerequisite Skills for Reading Comprehension: Multi-Perspective Analysis of MCTest Datasets and Systems
One of the main goals of natural language processing (NLP) is synthetic understanding of natural language documents, especially reading comprehension (RC). An obstacle to the further development of RC systems is the absence of a synthetic methodology to analyze their performance. It is difficult to examine the performance of systems based solely on their results for tasks because the process of...
متن کاملAttnConvnet at SemEval-2018 Task 1: Attention-based Convolutional Neural Networks for Multi-label Emotion Classification
In this paper, we propose an attention-based classifier that predict multiple emotions of a given sentence. Our model imitates human’s two-step procedure of sentence understanding and it can effectively represent and classify sentences. With emoji-to-meaning preprocessing and extra lexicon utilization, we further improve the model performance. We train and evaluate our model with data provided ...
متن کامل