Self-Attention Architectures for Answer-Agnostic Neural Question Generation
Neural architectures based on self-attention, such as Transformers, recently attracted interest from the research community, and obtained significant improvements over the state of the art in several tasks. We explore how Transformers can be adapted to the task of Neural Question Generation without constraining the model to focus on a specific answer passage. We study the effect of several strategies to deal with out-of-vocabulary words such as copy mechanisms, placeholders, and contextual word embeddings. We report improvements obtained over the state-of-the-art on the SQuAD dataset according to automated metrics (BLEU, ROUGE), as well as qualitative human assessments of the system outputs.
Code (0)
등록된 구현이 없습니다.
Tasks
Question GenerationQuestion-GenerationWord EmbeddingsSimilar Papers 제목 키워드 기반
Attention-Based Methods For Audio Question Answering
Audio question answering (AQA) is the task of producing natural language answers when a system is provided with audio and natural language questions. In this paper, we propose neural network architectures based on self-a…
Audio Question AnsweringBinary ClassificationQuestion AnsweringQuestion-Agnostic Attention for Visual Question Answering
Visual Question Answering (VQA) models employ attention mechanisms to discover image locations that are most relevant for answering a specific question. For this purpose, several multimodal fusion strategies have been pr…
Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering
The dominant neural architectures in question answer retrieval are based on recurrent or convolutional encoders configured with complex word matching layers. Given that recent architectural innovations are mostly new wor…
Efficient Neural NetworkFeature EngineeringQuestion AnsweringRepresentation Learning+1Spatially Aware Multimodal Transformers for TextVQA
Textual cues are essential for everyday tasks like buying groceries and using public transport. To develop this assistive technology, we study the TextVQA task, i.e., reasoning about text in images to answer a question. …
Optical Character Recognition (OCR)Spatial ReasoningTextVQAVisual Grounding+1Gated Group Self-Attention for Answer Selection
Answer selection (answer ranking) is one of the key steps in many kinds of question answering (QA) applications, where deep models have achieved state-of-the-art performance. Among these deep models, recurrent neural net…
Answer SelectionMachine TranslationQuestion AnsweringTranslation