Machine Reading Comprehension (MRC) is the task of answering a question over a paragraph of text.
In this paper, we propose Answer-Clue-Style-aware Question Generation (ACS-QG), which aims at automatically generating high-quality and diverse question-answer pairs from unlabeled text corpus at scale by imitating the way a human asks questions.
Instead of treating the task of NER as a sequence labeling problem, we propose to formulate it as a machine reading comprehension (MRC) task.
SOTA for Nested Named Entity Recognition on ACE 2004 (using extra training data)
We analyze BiPaR in depth and find that BiPaR offers good diversification in prefixes of questions, answer types and relationships between questions and passages.
The latest work on language representations carefully integrates contextualized features into language model training, which enables a series of success especially in various machine reading comprehension and natural language inference tasks.
SOTA for Natural Language Inference on SNLI
Existing machine reading comprehension (MRC) models do not scale effectively to real-world applications like web-level information retrieval and question answering (QA).
In detail, for self-attention network (SAN) sponsored Transformer-based encoder, we introduce syntactic dependency of interest (SDOI) design into the SAN to form an SDOI-SAN with syntax-guided self-attention.
#4 best model for Question Answering on SQuAD2.0 dev
In addition, visualization experiments show that our proposed model can better mimic the human reasoning process for conversational MRC compared to existing models.