1 |
Multi-tasking Dialogue Comprehension with Discourse Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Smoothing Dialogue States for Open Conversational Machine Reading ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Dialogue Graph Modeling for Conversational Machine Reading ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Tracing Origins: Coreference-aware Machine Reading Comprehension ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Enhancing Pre-trained Language Model with Lexical Simplification ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
SG-Net: Syntax Guided Transformer for Language Representation ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Modeling Multi-turn Conversation with Deep Utterance Aggregation ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Subword-augmented Embedding for Cloze Reading Comprehension ...
|
|
|
|
Abstract:
Representation learning is the foundation of machine reading comprehension. In state-of-the-art models, deep learning methods broadly use word and character level representations. However, character is not naturally the minimal linguistic unit. In addition, with a simple concatenation of character and word embedding, previous models actually give suboptimal solution. In this paper, we propose to use subword rather than character for word embedding enhancement. We also empirically explore different augmentation strategies on subword-augmented embedding to enhance the cloze-style reading comprehension model reader. In detail, we present a reader that uses subword-level representation to augment word embedding with a short list to handle rare words effectively. A thorough examination is conducted to evaluate the comprehensive performance and generalization ability of the proposed reader. Experimental results show that the proposed approach helps the reader significantly outperform the state-of-the-art baselines ... : Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018) ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1806.09103 https://arxiv.org/abs/1806.09103
|
|
BASE
|
|
Hide details
|
|
15 |
One-shot Learning for Question-Answering in Gaokao History Challenge ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|