Share This Author
Do NLP Models Know Numbers? Probing Numeracy in Embeddings
- Eric Wallace, Yizhong Wang, Sujian Li, Sameer Singh, Matt Gardner
- Computer ScienceEMNLP
- 17 September 2019
This work investigates the numerical reasoning capabilities of a state-of-the-art question answering model on the DROP dataset and finds this model excels on questions that require numerical reasoning, i.e., it already captures numeracy.
Text Level Graph Neural Network for Text Classification
- Lianzhe Huang, Dehong Ma, Sujian Li, Xiaodong Zhang, Houfeng Wang
- Computer ScienceEMNLP
- 6 October 2019
This work proposes a new GNN based model that builds graphs for each input text with global parameters sharing instead of a single graph for the whole corpus, which removes the burden of dependence between an individual text and entire corpus which support online testing, but still preserve global information.
Joint Extraction of Entities and Relations Based on a Novel Decomposition Strategy
This paper decomposes the joint extraction task into two interrelated subtasks, namely HE extraction and TER extraction, and deconstructed into several sequence labeling problems based on the proposed span-based tagging scheme, which are conveniently solved by a hierarchical boundary tagger and a multi-span decoding algorithm.
Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension
This work introduces KT-NET, which employs an attention mechanism to adaptively select desired knowledge from KBs, and then fuses selected knowledge with BERT to enable context- and knowledge-aware predictions.
AttSum: Joint Learning of Focusing and Summarization with Neural Attention
A novel summarization system called AttSum is proposed, which automatically learns distributed representations for sentences as well as the document cluster and applies the attention mechanism to simulate the attentive reading of human behavior when a query is given.
Denoising based Sequence-to-Sequence Pre-training for Text Generation
Results on four datasets show that PoDA can improve model performance over strong baselines without using any task-specific techniques and significantly speed up convergence.
Tree-structured Decoding for Solving Math Word Problems
A tree-structured decoding method that generates the abstract syntax tree of the equation in a top-down manner and can automatically stop during decoding without a redundant stop token is proposed.
Enhanced-RCNN: An Efficient Method for Learning Sentence Similarity
- Shuang Peng, Hengbin Cui, Niantao Xie, Sujian Li, Jiaxing Zhang, Xiaolong Li
- Computer ScienceWWW
- 19 April 2020
Experimental results show that the enhanced recurrent convolutional neural network model (Enhanced-RCNN) outperforms the baselines and achieves the competitive performance on two real-world paraphrase identification datasets.
First Target and Opinion then Polarity: Enhancing Target-opinion Correlation for Aspect Sentiment Triplet Extraction
A novel two-stage method which enhances the correlation between targets and opinions through sequence tagging, and the experimental results show that the model outperforms the state-ofthe-art methods.
BASS: Boosting Abstractive Summarization with Unified Semantic Graph
BASS is presented, a novel framework for Boosting Abstractive Summarization based on a unified Semantic graph, which aggregates co-referent phrases distributing across a long range of context and conveys rich relations between phrases.