Search Results for author:
Found 88 papers, 31 papers with code
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 #2 on
Thai Word Segmentation
on BEST-2010
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.
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.
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.
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.
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 #5 on
Extractive Text Summarization
on CNN / Daily Mail
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.
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.
Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability
To address this, we propose Ordered CommonGen, a benchmark designed to evaluate the compositional generalization and instruction-following abilities of LLMs.
Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws
Their task-solving performance is improved by increasing parameter size, as shown in the recent studies on parameter scaling laws.
Long-Tail Crisis in Nearest Neighbor Language Models
The $k$-nearest-neighbor language model ($k$NN-LM), one of the retrieval-augmented language models, improves the perplexity for given text by directly accessing a large datastore built from any text data during inference.
Considering Length Diversity in Retrieval-Augmented Summarization
This study investigates retrieval-augmented summarization by specifically examining the impact of exemplar summary lengths under length constraints, not covered by previous work.
AdParaphrase: Paraphrase Dataset for Analyzing Linguistic Features toward Generating Attractive Ad Texts
This study aims to explore the linguistic features of ad texts that influence human preferences.
Tonguescape: Exploring Language Models Understanding of Vowel Articulation
In this study, we created video and image datasets from the existing real-time MRI dataset and investigated whether LMs can understand vowel articulation based on tongue positions using vision-based information.
Can Impressions of Music be Extracted from Thumbnail Images?
In recent years, there has been a notable increase in research on machine learning models for music retrieval and generation systems that are capable of taking natural language sentences as inputs.
Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical Domain
Retrieval Augmented Generation (RAG) complements the knowledge of Large Language Models (LLMs) by leveraging external information to enhance response accuracy for queries.
How Panel Layouts Define Manga: Insights from Visual Ablation Experiments
Today, manga has gained worldwide popularity.
CoAM: Corpus of All-Type Multiword Expressions
MWEs in CoAM are tagged with MWE types, such as Noun and Verb, to enable fine-grained error analysis.
Theoretical Aspects of Bias and Diversity in Minimum Bayes Risk Decoding
We also introduce a new MBR approach, Metric-augmented MBR (MAMBR), which increases diversity by adjusting the behavior of utility functions without altering the pseudo-references.
BQA: Body Language Question Answering Dataset for Video Large Language Models
To address this, we propose a dataset, BQA, a body language question answering dataset, to validate whether the model can correctly interpret emotions from short clips of body language comprising 26 emotion labels of videos of body language.
Exploring Intrinsic Language-specific Subspaces in Fine-tuning Multilingual Neural Machine Translation
Furthermore, we propose architecture learning techniques and introduce a gradual pruning schedule during fine-tuning to exhaustively explore the optimal setting and the minimal intrinsic subspaces for each language, resulting in a lightweight yet effective fine-tuning procedure.
Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models
As the performance of Large-scale Vision Language Models (LVLMs) improves, they are increasingly capable of responding in multiple languages, and there is an expectation that the demand for explanations generated by LVLMs will grow.
Toward the Evaluation of Large Language Models Considering Score Variance across Instruction Templates
In this study, we provide English and Japanese cross-lingual datasets for evaluating the NLU performance of LLMs, which include multiple instruction templates for fair evaluation of each task, along with regular expressions to constrain the output format.
How to Make the Most of LLMs' Grammatical Knowledge for Acceptability Judgments
The grammatical knowledge of language models (LMs) is often measured using a benchmark of linguistic minimal pairs, where LMs are presented with a pair of acceptable and unacceptable sentences and required to judge which is acceptable.
mbrs: A Library for Minimum Bayes Risk Decoding
We published our mbrs as an MIT-licensed open-source project, and the code is available on GitHub.
Multi-Frame Vision-Language Model for Long-form Reasoning in Driver Behavior Analysis
Identifying risky driving behavior in real-world situations is essential for the safety of both drivers and pedestrians.
Multi-label Learning with Random Circular Vectors
The extreme multi-label classification~(XMC) task involves learning a classifier that can predict from a large label set the most relevant subset of labels for a data instance.
Extreme Multi-Label Classification
MUlTI-LABEL-ClASSIFICATION
+1
Unified Interpretation of Smoothing Methods for Negative Sampling Loss Functions in Knowledge Graph Embedding
This paper provides theoretical interpretations of the smoothing methods for the NS loss in KGE and induces a new NS loss, Triplet Adaptive Negative Sampling (TANS), that can cover the characteristics of the conventional smoothing methods.
Are Data Augmentation Methods in Named Entity Recognition Applicable for Uncertainty Estimation?
This work investigates the impact of data augmentation on confidence calibration and uncertainty estimation in Named Entity Recognition (NER) tasks.
Efficient Nearest Neighbor based Uncertainty Estimation for Natural Language Processing Tasks
Trustworthy prediction in Deep Neural Networks (DNNs), including Pre-trained Language Models (PLMs) is important for safety-critical applications in the real world.
Towards Temporal Change Explanations from Bi-Temporal Satellite Images
Explaining temporal changes between satellite images taken at different times is important for urban planning and environmental monitoring.
Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters
Scaling the context size of large language models (LLMs) enables them to perform various new tasks, e. g., book summarization.
Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation
Maximum a posteriori decoding, a commonly used method for neural machine translation (NMT), aims to maximize the estimated posterior probability.
InstructCMP: Length Control in Sentence Compression through Instruction-based Large Language Models
For this purpose, we created new evaluation datasets by transforming traditional sentence compression datasets into an instruction format.
mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans
Constructed dataset is a benchmark for cross-lingual language-transfer capabilities of multilingual LMs, and experimental results showed high language-transfer capabilities for questions that LMs could easily solve, but lower transfer capabilities for questions requiring deep knowledge or commonsense.
Dependency-Aware Semi-Structured Sparsity of GLU Variants in Large Language Models
The rapid advancement in Large Language Models (LLMs) has markedly enhanced the capabilities of language understanding and generation.
Context-Aware Machine Translation with Source Coreference Explanation
Despite significant improvements in enhancing the quality of translation, context-aware machine translation (MT) models underperform in many cases.
Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Pair
In Simultaneous Machine Translation (SiMT) systems, training with a simultaneous interpretation (SI) corpus is an effective method for achieving high-quality yet low-latency systems.
Revealing Trends in Datasets from the 2022 ACL and EMNLP Conferences
NLP systems are on par or, in some cases, better than humans at accomplishing specific tasks.
Constructing Multilingual Visual-Text Datasets Revealing Visual Multilingual Ability of Vision Language Models
Our contribution is four-fold: 1) we introduced nine vision-and-language (VL) tasks (including object recognition, image-text matching, and more) and constructed multilingual visual-text datasets in four languages: English, Japanese, Swahili, and Urdu through utilizing templates containing \textit{questions} and prompting GPT4-V to generate the \textit{answers} and the \textit{rationales}, 2) introduced a new VL task named \textit{unrelatedness}, 3) introduced rationales to enable human understanding of the VLM reasoning process, and 4) employed human evaluation to measure the suitability of proposed datasets for VL tasks.
Introducing Syllable Tokenization for Low-resource Languages: A Case Study with Swahili
Tokenization is one such technique because it allows for the words to be split based on characters or subwords, creating word embeddings that best represent the structure of the language.
Cross-lingual Contextualized Phrase Retrieval
In our work, we propose a new task formulation of dense retrieval, cross-lingual contextualized phrase retrieval, which aims to augment cross-lingual applications by addressing polysemy using context information.
Distilling Named Entity Recognition Models for Endangered Species from Large Language Models
Natural language processing (NLP) practitioners are leveraging large language models (LLM) to create structured datasets from semi-structured and unstructured data sources such as patents, papers, and theses, without having domain-specific knowledge.
Can we obtain significant success in RST discourse parsing by using Large Language Models?
Recently, decoder-only pre-trained large language models (LLMs), with several tens of billion parameters, have significantly impacted a wide range of natural language processing (NLP) tasks.
Ranked #1 on
Discourse Parsing
on RST-DT
Artwork Explanation in Large-scale Vision Language Models
To address this issue, we propose a new task: the artwork explanation generation task, along with its evaluation dataset and metric for quantitatively assessing the understanding and utilization of knowledge about artworks.
Do LLMs Implicitly Determine the Suitable Text Difficulty for Users?
Experimental results on the Stack-Overflow dataset and the TSCC dataset, including multi-turn conversation show that LLMs can implicitly handle text difficulty between user input and its generated response.
IRR: Image Review Ranking Framework for Evaluating Vision-Language Models
We validate it using a dataset of images from 15 categories, each with five critic review texts and annotated rankings in both English and Japanese, totaling over 2, 000 data instances.
Centroid-Based Efficient Minimum Bayes Risk Decoding
Minimum Bayes risk (MBR) decoding achieved state-of-the-art translation performance by using COMET, a neural metric that has a high correlation with human evaluation.
Generating Diverse Translation with Perturbed kNN-MT
Generating multiple translation candidates would enable users to choose the one that satisfies their needs.
Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?
Knowledge Graph Completion (KGC) is a task that infers unseen relationships between entities in a KG.
Model-based Subsampling for Knowledge Graph Completion
Subsampling is effective in Knowledge Graph Embedding (KGE) for reducing overfitting caused by the sparsity in Knowledge Graph (KG) datasets.
Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language Models
This task consists of two parts: the first is to generate a table containing knowledge about an entity and its related image, and the second is to generate an image from an entity with a caption and a table containing related knowledge of the entity.
LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation
Our model employs the lattice structure to handle segmentation alternatives and utilizes graph neural networks along with an attention mechanism to attentively extract multi-granularity representation from the lattice for complementing character representations.
Ranked #1 on
Chinese Word Segmentation
on CTB6
(using extra training data)
Bidirectional Transformer Reranker for Grammatical Error Correction
Pre-trained seq2seq models have achieved state-of-the-art results in the grammatical error correction task.
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 #15 on
Link Prediction
on FB15k-237
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 #1 on
Discourse Parsing
on RST-DT
(RST-Parseval (Relation) metric, using extra
training data)
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.
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
(RST-Parseval (Span) metric)
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
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.
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.
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 #18 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).
