Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference

@inproceedings{Pan2018DiscourseMA,
  title={Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference},
  author={Boyuan Pan and Yazheng Yang and Zhou Zhao and Yueting Zhuang and Deng Cai and Xiaofei He},
  booktitle={ACL},
  year={2018}
}
Natural Language Inference (NLI), also known as Recognizing Textual Entailment (RTE), is one of the most important problems in natural language processing. It requires to infer the logical relationship between two given sentences. While current approaches mostly focus on the interaction architectures of the sentences, in this paper, we propose to transfer knowledge from some important discourse markers to augment the quality of the NLI model. We observe that people usually use some discourse… Expand
Learning Entailment-Based Sentence Embeddings from Natural Language Inference
TLDR
This work proposes a simple interaction layer based on predefined entailment and contradiction scores applied directly to the sentence embeddings, which achieves results on natural language inference competitive with MLP-based models and directly represents the information needed for textual entailment. Expand
Adapting BERT to Implicit Discourse Relation Classification with a Focus on Discourse Connectives
TLDR
This paper performs additional pre-training on text tailored to discourse classification and tests three methods of adaptation of BERT to exploit implicit connectives given by treebank annotators, demonstrating that they can be combined straightforwardly in a single training pipeline. Expand
Gaussian Transformer: A Lightweight Approach for Natural Language Inference
TLDR
An efficient RNN/CNN-free architecture named Gaussian Transformer for NLI, which consists of encoding blocks modeling both local and global dependency, high-order interaction blocks collecting the evidence of multi-step inference, and a lightweight comparison block saving lots of parameters. Expand
Representation learning in discourse parsing: A survey
TLDR
This survey covers text-level discourse parsing, shallow discourse parsing and coherence assessment, and introduces a trend of discourse structure aware representation learning that is to exploit discourse structures or discourse objectives for learning representations of sentences and documents for specific applications or for general purpose. Expand
Explicit Contextual Semantics for Text Comprehension
TLDR
This paper makes the first attempt to let SRL enhance text comprehension and inference through specifying verbal predicates and their corresponding semantic roles, and shows that the salient labels can be conveniently added to existing models and significantly improve deep learning models in challenging text comprehension tasks. Expand
Knowledge-Enhanced Natural Language Inference Based on Knowledge Graphs
TLDR
A novel Knowledge Graph-enhanced NLI (KGNLI) model is proposed to leverage the usage of background knowledge stored in knowledge graphs in the field of NLI and demonstrates the effectiveness of the model on four benchmarks. Expand
Deep bi-directional interaction network for sentence matching
TLDR
A Deep Bi-Directional Interaction Network (DBDIN) is proposed, which captures semantic relatedness from two directions and each direction employs multiple attention-based interaction units, and introduces a self-attention mechanism at last to enhance global matching information with smaller model complexity. Expand
Bi-Decoder Augmented Network for Neural Machine Translation
TLDR
This paper proposes a novel Bi-Decoder Augmented Network (BiDAN) for the neural machine translation task, and adds an auxiliary decoder to generate back the source language sequence at the training time. Expand
MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models
TLDR
Experiments on neural machine translation and abstractive text summarization show that the proposed framework can significantly improve the performance of the baseline models, and the method for the abstractiveText summarization achieves the state-of-the-art results on the Gigaword dataset. Expand
Natural Language Inference Based on the LIC Architecture with DCAE Feature
TLDR
A DCAE (Directly-Conditional-Attention-Encoding) feature based on Bi-L STM and a new architecture named LIC (LSTM-Interaction-CNN) is proposed to deal with the NLI task, which aims to identify the logical relationship between a premise and a hypothesis. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 43 REFERENCES
Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference
TLDR
This paper describes a model (alpha) that is ranked among the top in the Shared Task, on both the in- domain test set and on the cross-domain test set, demonstrating that the model generalizes well to theCross-domain data. Expand
Natural Language Inference over Interaction Space
TLDR
DIIN, a novel class of neural network architectures that is able to achieve high-level understanding of the sentence pair by hierarchically extracting semantic features from interaction space, shows that an interaction tensor (attention weight) contains semantic information to solve natural language inference. Expand
Enhanced LSTM for Natural Language Inference
TLDR
A new state-of-the-art result is presented, achieving the accuracy of 88.6% on the Stanford Natural Language Inference Dataset, and it is demonstrated that carefully designing sequential inference models based on chain LSTMs can outperform all previous models. Expand
DisSent: Sentence Representation Learning from Explicit Discourse Relations
TLDR
It is demonstrated that the automatically curated corpus allows a bidirectional LSTM sentence encoder to yield high quality sentence embeddings and can serve as a supervised fine-tuning dataset for larger models such as BERT. Expand
A large annotated corpus for learning natural language inference
TLDR
The Stanford Natural Language Inference corpus is introduced, a new, freely available collection of labeled sentence pairs, written by humans doing a novel grounded task based on image captioning, which allows a neural network-based model to perform competitively on natural language inference benchmarks for the first time. Expand
Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
TLDR
It is shown how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought vectors on a wide range of transfer tasks. Expand
A Compare-Propagate Architecture with Alignment Factorization for Natural Language Inference
TLDR
A new compare-propagate architecture is introduced where alignments pairs are compared and then propagated to upper layers for enhanced representation learning, and novel factorization layers are adopted for efficient compression of alignment vectors into scalar valued features, which are then used to augment the base word representations. Expand
Reasoning about Entailment with Neural Attention
TLDR
This paper proposes a neural model that reads two sentences to determine entailment using long short-term memory units and extends this model with a word-by-word neural attention mechanism that encourages reasoning over entailments of pairs of words and phrases, and presents a qualitative analysis of attention weights produced by this model. Expand
Reading and Thinking: Re-read LSTM Unit for Textual Entailment Recognition
TLDR
A new L STM unit called re-read LSTM (rLSTM) is designed to implement this “thinking” process, which means to read the premise again and again while reading the hypothesis to get a better understanding of the premise. Expand
A unified architecture for natural language processing: deep neural networks with multitask learning
We describe a single convolutional neural network architecture that, given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity tags, semanticExpand
...
1
2
3
4
5
...