A Comparative Study of Word Embeddings for Reading Comprehension
Explore this paper's citation graph
Summary
It is shown that seemingly minor choices made on the use of pre-trained word embeddings, and the representation of out-of-vocabulary tokens at test time, can turn out to have a larger impact than architectural choices on the final performance.
- Type
- preprint
- Published
- 2017-03-02
- Cited by
- 42
- References
- 30
- Access
- Open access
- OpenAlex
- https://openalex.org/W2605058246
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:15742031
Keywords
Word (group theory), Linguistics, Reading (process), Computer science, Comprehension
References
- Teaching Machines to Read and Comprehend
- Improving Distributional Similarity with Lessons Learned from Word Embeddings
- Long Short-Term Memory
- The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
- Distributed Representations of Words and Phrases and their Compositionality
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
- GloVe: Global Vectors for Word Representation
- Text Understanding with the Attention Sum Reader Network
- Gated-Attention Readers for Text Comprehension
- Dynamic Entity Representation with Max-pooling Improves Machine Reading
- Neural Semantic Encoders
- Attention-over-Attention Neural Networks for Reading Comprehension
- Machine Comprehension Using Match-LSTM and Answer Pointer
- ReasoNet: Learning to Stop Reading in Machine Comprehension
- Embracing data abundance: BookTest Dataset for Reading Comprehension
- End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
- NewsQA: A Machine Comprehension Dataset
- MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
- Tracking the World State with Recurrent Entity Networks
- Multi-Perspective Context Matching for Machine Comprehension
Cited by
- Learning to Compute Word Embeddings On the Fly
- Deep Learning for Entity Matching: A Design Space Exploration
- Solving Data Sparsity for Aspect Based Sentiment Analysis Using Cross-Linguality and Multi-Linguality
- Distributed representation of melodic contours
- An Investigation of the Interactions Between Pre-Trained Word Embeddings, Character Models and POS Tags in Dependency Parsing
- Essay-Anchor Attentive Multi-Modal Bilinear Pooling for Textbook Question Answering
- Improving Word Embedding Coverage in Less-Resourced Languages Through Multi-Linguality and Cross-Linguality
- Context and Embeddings in Language Modelling - an Exploration
- Enhancing Semantic Word Representations by Embedding Deep Word Relationships
- R-Trans: RNN Transformer Network for Chinese Machine Reading Comprehension
- Adapting Word Embeddings to Traceability Recovery
- Document Gated Reader for Open-Domain Question Answering
- Legal Query Reformulation using Deep Learning
- First-principle study on honeycomb fluorated-InTe monolayer with large Rashba spin splitting and direct bandgap
- CASM: A Deep-Learning Approach for Identifying Collective Action Events with Text and Image Data from Social Media
- Enhancing Text Mining Using Deep Learning Models
- Exploring Benefits of Transfer Learning in Neural Machine Translation
- A Survey on Machine Reading Comprehension Systems
- Enhancing natural language understanding using meaning representation and deep learning
- Neural Machine Reading Comprehension: Methods and Trends
Related papers
- Moving From Paper to E-Book Reading
- Ways of Not Reading Gertrude Stein
- On the Reading Features of Mao Zedong and Zeng Guofan
- Revitalizing Close Reading
- Reading Clubs, Workshops, Reading in the Park
- A comparative study of four reading journals' contributions to comprehension instruction methodology
- Teaching Language Clues to Reading Comprehension.
- Comprehension Instruction in Content Area Classes
- Comprehension Zone: Caution! Teaching Required