Search Results for author:
Found 41 papers, 12 papers with code
Improving Character-Aware Neural Language Model by Warming up Character Encoder under Skip-gram Architecture
Character-aware neural language models can capture the relationship between words by exploiting character-level information and are particularly effective for languages with rich morphology.
SODA: Story Oriented Dense Video Captioning Evaluation Framework
This paper proposes a new evaluation framework, Story Oriented Dense video cAptioning evaluation framework (SODA), for measuring the performance of video story description systems.
Joint Learning-based Heterogeneous Graph Attention Network for Timeline Summarization
Previous studies on the timeline summarization (TLS) task ignored the information interaction between sentences and dates, and adopted pre-defined unlearnable representations for them.
Character-based Thai Word Segmentation with Multiple Attentions
These models estimate word boundaries from a character sequence.
Ranked #1 on
Thai Word Segmentation
on BEST-2010
A Language Model-based Generative Classifier for Sentence-level Discourse Parsing
Discourse segmentation and sentence-level discourse parsing play important roles for various NLP tasks to consider textual coherence.
Considering Nested Tree Structure in Sentence Extractive Summarization with Pre-trained Transformer
Sentence extractive summarization shortens a document by selecting sentences for a summary while preserving its important contents.
Ranked #3 on
Extractive Text Summarization
on CNN / Daily Mail
Generic Mechanism for Reducing Repetitions in Encoder-Decoder Models
Encoder-decoder models have been commonly used for many tasks such as machine translation and response generation.
Abstractive Document Summarization with Word Embedding Reconstruction
Neural sequence-to-sequence (Seq2Seq) models and BERT have achieved substantial improvements in abstractive document summarization (ADS) without and with pre-training, respectively.
Making Your Tweets More Fancy: Emoji Insertion to Texts
The results demonstrate that the position of emojis in texts is a good clue to boost the performance of emoji label prediction.
A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing
To promote and further develop RST-style discourse parsing models, we need a strong baseline that can be regarded as a reference for reporting reliable experimental results.
Ranked #1 on
Discourse Parsing
on Instructional-DT (Instr-DT)
Subsampling for Knowledge Graph Embedding Explained
In this article, we explain the recent advance of subsampling methods in knowledge graph embedding (KGE) starting from the original one used in word2vec.
Generating Repetitions with Appropriate Repeated Words
A repetition is a response that repeats words in the previous speaker's utterance in a dialogue.
Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning
To solve this problem, we theoretically analyzed NS loss to assist hyperparameter tuning and understand the better use of the NS loss in KGE learning.
Aspect-based Analysis of Advertising Appeals for Search Engine Advertising
Writing an ad text that attracts people and persuades them to click or act is essential for the success of search engine advertising.
Why does Negative Sampling not Work Well? Analysis of Convexity in Negative Sampling
On the other hand, properties of the NS loss function that are considered important for learning, such as the relationship between the noise distribution and the number of negative samples, have not been investigated theoretically.
Towards Table-to-Text Generation with Numerical Reasoning
In summary, our contributions are (1) a new dataset for numerical table-to-text generation using pairs of a table and a paragraph of a table description with richer inference from scientific papers, and (2) a table-to-text generation framework enriched with numerical reasoning.
Unified Interpretation of Softmax Cross-Entropy and Negative Sampling: With Case Study for Knowledge Graph Embedding
In knowledge graph embedding, the theoretical relationship between the softmax cross-entropy and negative sampling loss functions has not been investigated.
Ranked #10 on
Link Prediction
on FB15k-237
An Empirical Study of Generating Texts for Search Engine Advertising
Although there are many studies on neural language generation (NLG), few trials are put into the real world, especially in the advertising domain.
Improving Neural RST Parsing Model with Silver Agreement Subtrees
We then pre-train a neural RST parser with the obtained silver data and fine-tune it on the RST-DT.
Ranked #2 on
Discourse Parsing
on RST-DT
(using extra training data)
A New Surprise Measure for Extracting Interesting Relationships between Persons
We therefore propose a method for extracting interesting relationships between persons from natural language texts by focusing on their surprisingness.
One-class Text Classification with Multi-modal Deep Support Vector Data Description
This work presents multi-modal deep SVDD (mSVDD) for one-class text classification.
Generating Weather Comments from Meteorological Simulations
The task of generating weather-forecast comments from meteorological simulations has the following requirements: (i) the changes in numerical values for various physical quantities need to be considered, (ii) the weather comments should be dependent on delivery time and area information, and (iii) the comments should provide useful information for users.
Metric-Type Identification for Multi-Level Header Numerical Tables in Scientific Papers
Numerical tables are widely used to present experimental results in scientific papers.
Hierarchical Trivia Fact Extraction from Wikipedia Articles
Recently, automatic trivia fact extraction has attracted much research interest.
A Simple and Effective Usage of Word Clusters for CBOW Model
We propose a simple and effective method for incorporating word clusters into the Continuous Bag-of-Words (CBOW) model.
Pointing to Subwords for Generating Function Names in Source Code
We tackle the task of automatically generating a function name from source code.
Neural text normalization leveraging similarities of strings and sounds
We propose neural models that can normalize text by considering the similarities of word strings and sounds.
Top-Down RST Parsing Utilizing Granularity Levels in Documents
To obtain better discourse dependency trees, we need to improve the accuracy of RST trees at the upper parts of the structures.
Ranked #3 on
Discourse Parsing
on RST-DT
Syntactically Look-Ahead Attention Network for Sentence Compression
Sentence compression is the task of compressing a long sentence into a short one by deleting redundant words.
Ranked #1 on
Sentence Compression
on Google Dataset
Context-aware Neural Machine Translation with Coreference Information
We present neural machine translation models for translating a sentence in a text by using a graph-based encoder which can consider coreference relations provided within the text explicitly.
Split or Merge: Which is Better for Unsupervised RST Parsing?
The first one builds the optimal tree in terms of a dissimilarity score function that is defined for splitting a text span into smaller ones.
A Simple and Effective Method for Injecting Word-Level Information into Character-Aware Neural Language Models
Our injection method can also be used together with previous methods.
Discourse-Aware Hierarchical Attention Network for Extractive Single-Document Summarization
To incorporate the information of a discourse tree structure into the neural network-based summarizers, we propose a discourse-aware neural extractive summarizer which can explicitly take into account the discourse dependency tree structure of the source document.
Automatic Pyramid Evaluation Exploiting EDU-based Extractive Reference Summaries
This paper tackles automation of the pyramid method, a reliable manual evaluation framework.
An Empirical Study of Building a Strong Baseline for Constituency Parsing
This paper investigates the construction of a strong baseline based on general purpose sequence-to-sequence models for constituency parsing.
Ranked #15 on
Constituency Parsing
on Penn Treebank
Higher-Order Syntactic Attention Network for Longer Sentence Compression
To solve this problem, we propose a higher-order syntactic attention network (HiSAN) that can handle higher-order dependency features as an attention distribution on LSTM hidden states.
Ranked #3 on
Sentence Compression
on Google Dataset
Supervised Attention for Sequence-to-Sequence Constituency Parsing
The sequence-to-sequence (Seq2Seq) model has been successfully applied to machine translation (MT).
