Search Results for author:
Found 64 papers, 14 papers with code
Revisiting Statistical Laws of Semantic Shift in Romance Cognates
This article revisits statistical relationships across Romance cognates between lexical semantic shift and six intra-linguistic variables, such as frequency and polysemy.
Generating Racing Game Commentary from Vision, Language, and Structured Data
In this study, we introduce a new large-scale dataset that contains aligned video data, structured numerical data, and transcribed commentaries that consist of 129, 226 utterances in 1, 389 races in a game.
Market Comment Generation from Data with Noisy Alignments
On top of this, we employ a copy mechanism that is suitable for referring to the content of data records in the market price data.
Text-to-Text Pre-Training Model with Plan Selection for RDF-to-Text Generation
We report our system description for the RDFto-Text task in English on the WebNLG 2020 Challenge.
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.
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.
Prompting for Numerical Sequences: A Case Study on Market Comment Generation
Large language models (LLMs) have been applied to a wide range of data-to-text generation tasks, including tables, graphs, and time-series numerical data-to-text settings.
Contextualized Word Vector-based Methods for Discovering Semantic Differences with No Training nor Word Alignment
In this paper, we propose methods for discovering semantic differences in words appearing in two corpora based on the norms of contextualized word vectors.
FinTech for Social Good: A Research Agenda from NLP Perspective
Making our research results positively impact on society and environment is one of the goals our community has been pursuing recently.
StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning
Existing automatic story evaluation methods place a premium on story lexical level coherence, deviating from human preference.
Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding
This paper explores the task of Temporal Video Grounding (TVG) where, given an untrimmed video and a natural language sentence query, the goal is to recognize and determine temporal boundaries of action instances in the video described by the query.
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.
LocFormer: Enabling Transformers to Perform Temporal Moment Localization on Long Untrimmed Videos With a Feature Sampling Approach
We propose LocFormer, a Transformer-based model for video grounding which operates at a constant memory footprint regardless of the video length, i. e. number of frames.
SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation
Generating texts in scientific papers requires not only capturing the content contained within the given input but also frequently acquiring the external information called \textit{context}.
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.
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.
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.
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.
GraphPlan: Story Generation by Planning with Event Graph
In this paper, we focus on planning a sequence of events assisted by event graphs, and use the events to guide the generator.
Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling
To enrich the candidate concepts, a commonsense knowledge graph is created for each image sequence from which the concept candidates are proposed.
Ranked #19 on
Visual Storytelling
on VIST
Metric-Type Identification for Multi-Level Header Numerical Tables in Scientific Papers
Numerical tables are widely used to present experimental results in scientific papers.
An empirical analysis of existing systems and datasets toward general simple question answering
Our analysis, including shifting of training and test datasets and training on a union of the datasets, suggests that our progress in solving SimpleQuestions dataset does not indicate the success of more general simple question answering.
Learning with Contrastive Examples for Data-to-Text Generation
Existing models for data-to-text tasks generate fluent but sometimes incorrect sentences e. g., {``}Nikkei gains{''} is generated when {``}Nikkei drops{''} is expected.
A Neural Model for Aggregating Coreference Annotation in Crowdsourcing
To ensure high-quality data, it is crucial to infer the correct labels by aggregating the noisy labels.
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.
mgsohrab at WNUT 2020 Shared Task-1: Neural Exhaustive Approach for Entity and Relation Recognition Over Wet Lab Protocols
In relation extraction task, we achieved 80. 46% in terms of F-score as the top system in the relation extraction or recognition task.
Ranked #1 on
Named Entity Recognition (NER)
on WNUT 2020
An Analysis of the Utility of Explicit Negative Examples to Improve the Syntactic Abilities of Neural Language Models
Neural language models are commonly trained only on positive examples, a set of sentences in the training data, but recent studies suggest that the models trained in this way are not capable of robustly handling complex syntactic constructions, such as long-distance agreement.
A Neural Pipeline Approach for the PharmaCoNER Shared Task using Contextual Exhaustive Models
We present a neural pipeline approach that performs named entity recognition (NER) and concept indexing (CI), which links them to concept unique identifiers (CUIs) in a knowledge base, for the PharmaCoNER shared task on pharmaceutical drugs and chemical entities.
Coreference Resolution in Full Text Articles with BERT and Syntax-based Mention Filtering
Additionally, the proposed model is able to detect coreferent pairs in long distances, even with a distance of more than 200 sentences.
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.
Controlling Contents in Data-to-Document Generation with Human-Designed Topic Labels
We propose a data-to-document generator that can easily control the contents of output texts based on a neural language model.
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.
Learning to Select, Track, and Generate for Data-to-Text
We propose a data-to-text generation model with two modules, one for tracking and the other for text generation.
Numeracy-600K: Learning Numeracy for Detecting Exaggerated Information in Market Comments
In this paper, we attempt to answer the question of whether neural network models can learn numeracy, which is the ability to predict the magnitude of a numeral at some specific position in a text description.
Global Optimization under Length Constraint for Neural Text Summarization
The experimental results show that a state-of-the-art neural summarization model optimized with GOLC generates fewer overlength summaries while maintaining the fastest processing speed; only 6. 70{\%} overlength summaries on CNN/Daily and 7. 8{\%} on long summary of Mainichi, compared to the approximately 20{\%} to 50{\%} on CNN/Daily Mail and 10{\%} to 30{\%} on Mainichi with the other optimization methods.
Stylistically User-Specific Generation
Recent neural models for response generation show good results in terms of general responses.
Generating Market Comments Referring to External Resources
Comments on a stock market often include the reason or cause of changes in stock prices, such as {``}Nikkei turns lower as yen{'}s rise hits exporters.
Semi-supervised Learning with Multi-Domain Sentiment Word Embeddings
Word embeddings are known to boost performance of many NLP tasks such as text classification, meanwhile they can be enhanced by labels at the document level to capture nuanced meaning such as sentiment and topic.
Exploring the Influence of Spelling Errors on Lexical Variation Measures
This paper introduces and examines the hypothesis that lexical richness measures become unstable in learner English because of spelling errors.
Neural Machine Translation Incorporating Named Entity
To alleviate these problems, the encoder of the proposed model encodes the input word on the basis of its NE tag at each time step, which could reduce the ambiguity of the input word.
Supervised Attention for Sequence-to-Sequence Constituency Parsing
The sequence-to-sequence (Seq2Seq) model has been successfully applied to machine translation (MT).
Distinguishing Japanese Non-standard Usages from Standard Ones
Our experimental results show that the model leveraging the context embedding outperforms other methods and provide us with findings, for example, on how to construct context embeddings and which corpus to use.
UINSUSKA-TiTech at SemEval-2017 Task 3: Exploiting Word Importance Levels for Similarity Features for CQA
We exploit words importance levels in sentences or questions for similarity features, for classification and ranking with machine learning.
Learning to Generate Market Comments from Stock Prices
This paper presents a novel encoder-decoder model for automatically generating market comments from stock prices.
Japanese Sentence Compression with a Large Training Dataset
In English, high-quality sentence compression models by deleting words have been trained on automatically created large training datasets.
Analyzing Semantic Change in Japanese Loanwords
We analyze semantic changes in loanwords from English that are used in Japanese (Japanese loanwords).
Controlling Output Length in Neural Encoder-Decoders
Neural encoder-decoder models have shown great success in many sequence generation tasks.
Discriminative Analysis of Linguistic Features for Typological Study
We address the task of automatically estimating the missing values of linguistic features by making use of the fact that some linguistic features in typological databases are informative to each other.
