DeepAI AI Chat
Log In Sign Up

Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring

by   Xiyao Ma, et al.
University of Florida

Taking an answer and its context as input, sequence-to-sequence models have made considerable progress on question generation. However, we observe that these approaches often generate wrong question words or keywords and copy answer-irrelevant words from the input. We believe that lacking global question semantics and exploiting answer position-awareness not well are the key root causes. In this paper, we propose a neural question generation model with two general modules: sentence-level semantic matching and answer position inferring. Further, we enhance the initial state of the decoder by leveraging the answer-aware gated fusion mechanism. Experimental results demonstrate that our model outperforms the state-of-the-art (SOTA) models on SQuAD and MARCO datasets. Owing to its generality, our work also improves the existing models significantly.


page 1

page 2

page 3

page 4


A Question Type Driven and Copy Loss Enhanced Frameworkfor Answer-Agnostic Neural Question Generation

The answer-agnostic question generation is a significant and challenging...

Improving Question Generation With to the Point Context

Question generation (QG) is the task of generating a question from a ref...

Improving Neural Question Generation using Answer Separation

Neural question generation (NQG) is the task of generating a question fr...

Sequential Copying Networks

Copying mechanism shows effectiveness in sequence-to-sequence based neur...

Chinese Medical Question Answer Matching Based on Interactive Sentence Representation Learning

Chinese medical question-answer matching is more challenging than the op...

Tag and Correct: Question aware Open Information Extraction with Two-stage Decoding

Question Aware Open Information Extraction (Question aware Open IE) take...

Dynamic Feature Generation Network for Answer Selection

Extracting appropriate features to represent a corpus is an important ta...