Search Results for author:
Found 15 papers, 0 papers with code
Distinctive Slogan Generation with Reconstruction
To generate a slogan, we apply an encoder–decoder model which has shown effectiveness in many kinds of natural language generation tasks, such as abstractive summarization.
Aspect-Similarity-Aware Historical Influence Modeling for Rating Prediction
Previous laboratory studies have indicated that the ratings recorded by these systems differ from the actual evaluations of the users, owing to the influence of historical ratings in the system.
Quantifying Appropriateness of Summarization Data for Curriculum Learning
We conduct experiments on three summarization models; one pretrained model and two non-pretrained models, and verify our method improves the performance.
Identifying Implicit Quotes for Unsupervised Extractive Summarization of Conversations
The training task of the model is to predict whether a reply candidate is a true reply to a post.
Extractive Summarization
Unsupervised Extractive Summarization
A Large-Scale Corpus of E-mail Conversations with Standard and Two-Level Dialogue Act Annotations
To assess the difficulty of DA recognition on our corpus, we evaluate several models, including a pre-trained contextual representation model, as our baselines.
Reinforcement Learning with Imbalanced Dataset for Data-to-Text Medical Report Generation
We propose a novel reinforcement learning method with a reconstructor to improve the clinical correctness of generated reports to train the data-to-text module with a highly imbalanced dataset.
Keeping Consistency of Sentence Generation and Document Classification with Multi-Task Learning
The results show that our model generates more consistent headlines, key phrases and categories.
Relation Prediction for Unseen-Entities Using Entity-Word Graphs
Knowledge graphs (KGs) are generally used for various NLP tasks.
CLER: Cross-task Learning with Expert Representation to Generalize Reading and Understanding
This paper describes our model for the reading comprehension task of the MRQA shared task.
Integrating Entity Linking and Evidence Ranking for Fact Extraction and Verification
A simple entity linking approach with text match is used as the document selection component, this component identifies relevant documents for a given claim by using mentioned entities as clues.
Integrating Tree Structures and Graph Structures with Neural Networks to Classify Discussion Discourse Acts
We proposed a model that integrates discussion structures with neural networks to classify discourse acts.
Using Social Networks to Improve Language Variety Identification with Neural Networks
We propose a hierarchical neural network model for language variety identification that integrates information from a social network.
Unifying Text, Metadata, and User Network Representations with a Neural Network for Geolocation Prediction
We propose a novel geolocation prediction model using a complex neural network.
A Simple Scalable Neural Networks based Model for Geolocation Prediction in Twitter
In the test run of the task, the model achieved the accuracy of 40. 91{\%} and the median distance error of 69. 50 km in message-level prediction and the accuracy of 47. 55{\%} and the median distance error of 16. 13 km in user-level prediction.
