Search Results for author:
Found 105 papers, 25 papers with code
Towards Grounding of Formulae
Our results indicate that it is worthwhile to grow the techniques for the proposed task to contribute to the further progress of mathematical language processing.
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.
Bayesian Argumentation-Scheme Networks: A Probabilistic Model of Argument Validity Facilitated by Argumentation Schemes
We propose a methodology for representing the reasoning structure of arguments using Bayesian networks and predicate logic facilitated by argumentation schemes.
Building Dataset for Grounding of Formulae — Annotating Coreference Relations Among Math Identifiers
Therefore, coreference relations between symbols need to be identified for grounding, and the task has aspects of both description alignment and coreference analysis.
Collection and Analysis of Travel Agency Task Dialogues with Age-Diverse Speakers
This paper provides details of the dialogue task, the collection procedure and annotations, and the analysis on the characteristics of the dialogues and facial expressions focusing on the age of the speakers.
Development of a Multilingual CCG Treebank via Universal Dependencies Conversion
This paper introduces an algorithm to convert Universal Dependencies (UD) treebanks to Combinatory Categorial Grammar (CCG) treebanks.
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.
Leveraging Partial Dependency Trees to Control Image Captions
Controlling the generation of image captions attracts lots of attention recently.
Modeling Syntactic-Semantic Dependency Correlations in Semantic Role Labeling Using Mixture Models
In this paper, we propose a mixture model-based end-to-end method to model the syntactic-semantic dependency correlation in Semantic Role Labeling (SRL).
How Much Do Large Language Models Know about Human Motion? A Case Study in 3D Avatar Control
We explore Large Language Models (LLMs)' human motion knowledge through 3D avatar control.
Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models
The purpose of speech tokenization is to transform a speech signal into a sequence of discrete representations, serving as the foundation for speech language models (SLMs).
How LLMs Learn: Tracing Internal Representations with Sparse Autoencoders
Large Language Models (LLMs) demonstrate remarkable multilingual capabilities and broad knowledge.
A Statistical and Multi-Perspective Revisiting of the Membership Inference Attack in Large Language Models
The lack of data transparency in Large Language Models (LLMs) has highlighted the importance of Membership Inference Attack (MIA), which differentiates trained (member) and untrained (non-member) data.
Does it Chug? Towards a Data-Driven Understanding of Guitar Tone Description
In this work, we pursue a data-driven approach to further our understanding of such adjectives in the context of guitar tone.
Improving Unsupervised Constituency Parsing via Maximizing Semantic Information
In this paper, we introduce a novel objective for training unsupervised parsers: maximizing the information between constituent structures and sentence semantics (SemInfo).
Distilling Analysis from Generative Models for Investment Decisions
Professionals' decisions are the focus of every field.
GADFA: Generator-Assisted Decision-Focused Approach for Opinion Expressing Timing Identification
To address this deficit, our study introduces an innovative task - the identification of news-triggered opinion expressing timing.
Hierarchical Organization Simulacra in the Investment Sector
This paper explores designing artificial organizations with professional behavior in investments using a multi-agent simulation.
Enhancing Financial Sentiment Analysis with Expert-Designed Hint
This paper investigates the role of expert-designed hint in enhancing sentiment analysis on financial social media posts.
Enhancing Investment Opinion Ranking through Argument-Based Sentiment Analysis
Our research introduces a dual-pronged argument mining technique to improve recommendation system effectiveness, considering both professional and amateur investor perspectives.
Analyzing Correlations Between Intrinsic and Extrinsic Bias Metrics of Static Word Embeddings With Their Measuring Biases Aligned
An intrinsic bias metric measures bias by examining a characteristic of vectors, while an extrinsic bias metric checks whether an NLP system trained with a word embedding is biased.
Self-Emotion Blended Dialogue Generation in Social Simulation Agents
When engaging in conversations, dialogue agents in a virtual simulation environment may exhibit their own emotional states that are unrelated to the immediate conversational context, a phenomenon known as self-emotion.
Textless Dependency Parsing by Labeled Sequence Prediction
This paper proposes a textless method for dependency parsing, examining its effectiveness and limitations.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs
This paper introduces LLM-jp, a cross-organizational project for the research and development of Japanese large language models (LLMs).
FinGen: A Dataset for Argument Generation in Finance
Based on our empirical results, we further point out several unresolved issues and challenges in this research direction.
A Multi-Perspective Analysis of Memorization in Large Language Models
One of those behaviors is memorization, in which LLMs can generate the same content used to train them.
Unsupervised Parsing by Searching for Frequent Word Sequences among Sentences with Equivalent Predicate-Argument Structures
Linguists identify the constituent by evaluating a set of Predicate-Argument Structure (PAS) equivalent sentences where we find the constituent appears more frequently than non-constituents (i. e., the constituent corresponds to a frequent word sequence within the sentence set).
Mind the Gap Between Conversations for Improved Long-Term Dialogue Generation
Knowing how to end and resume conversations over time is a natural part of communication, allowing for discussions to span weeks, months, or years.
Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models
We propose the "Ask an Expert" framework in which the model is trained with access to an "expert" which it can consult at each turn.
Empirical Analysis of the Inductive Bias of Recurrent Neural Networks by Discrete Fourier Transform of Output Sequences
A unique feature of Recurrent Neural Networks (RNNs) is that it incrementally processes input sequences.
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.
Rethinking Offensive Text Detection as a Multi-Hop Reasoning Problem
We introduce the task of implicit offensive text detection in dialogues, where a statement may have either an offensive or non-offensive interpretation, depending on the listener and context.
Multilingual Syntax-aware Language Modeling through Dependency Tree Conversion
On average, the performance of our best model represents a 19 \% increase in accuracy over the worst choice across all languages.
Code Generation for Unknown Libraries via Reading API Documentations
Moreover, to evaluate code generation for unknown libraries and our framework, we extend an existing dataset of open-domain code generation and resplit it so that the evaluation data consist of only examples using the libraries that do not appear in the training data.
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.
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.
Predicting Event Time by Classifying Sub-Level Temporal Relations Induced from a Unified Representation of Time Anchors
Another contribution of this work is to construct a larger event time corpus (256 news documents) with a reasonable Inter-Annotator Agreement (IAA), for the purpose of overcoming the data shortage of the existing event time corpus (36 news documents).
A System for Worldwide COVID-19 Information Aggregation
The global pandemic of COVID-19 has made the public pay close attention to related news, covering various domains, such as sanitation, treatment, and effects on education.
Utterance-Unit Annotation for the JSL Dialogue Corpus: Toward a Multimodal Approach to Corpus Linguistics
This paper describes a method for annotating the Japanese Sign Language (JSL) dialogue corpus.
Analyzing Word Embedding Through Structural Equation Modeling
Many researchers have tried to predict the accuracies of extrinsic evaluation by using intrinsic evaluation to evaluate word embedding.
Comparing Neural Network Parsers for a Less-resourced and Morphologically-rich Language: Amharic Dependency Parser
In this paper, we compare four state-of-the-art neural network dependency parsers for the Semitic language Amharic.
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.
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.
Does My Rebuttal Matter? Insights from a Major NLP Conference
We then focus on the role of the rebuttal phase, and propose a novel task to predict after-rebuttal (i. e., final) scores from initial reviews and author 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.
Coordinate Structures in Universal Dependencies for Head-final Languages
This paper discusses the representation of coordinate structures in the Universal Dependencies framework for two head-final languages, Japanese and Korean.
An Empirical Investigation of Error Types in Vietnamese Parsing
Syntactic parsing plays a crucial role in improving the quality of natural language processing tasks.
Inducing Temporal Relations from Time Anchor Annotation
Conventional annotation of judging temporal relations puts a heavy load on annotators.
Consensus-based Sequence Training for Video Captioning
First we show that, by replacing model samples with ground-truth sentences, RL training can be seen as a form of weighted cross-entropy loss, giving a fast, RL-based pre-training algorithm.
Learning to Generate Market Comments from Stock Prices
This paper presents a novel encoder-decoder model for automatically generating market comments from stock prices.
Classifying Temporal Relations by Bidirectional LSTM over Dependency Paths
In this work, we borrow a state-of-the-art method in relation extraction by adopting bidirectional long short-term memory (Bi-LSTM) along dependency paths (DP).
On-demand Injection of Lexical Knowledge for Recognising Textual Entailment
We approach the recognition of textual entailment using logical semantic representations and a theorem prover.
Video Event Detection by Exploiting Word Dependencies from Image Captions
We conduct extensive experiments to analyze the effectiveness of using the new dependency representation for event detection on two large-scale TRECVID Multimedia Event Detection 2013 and 2014 datasets.
Generating Video Description using Sequence-to-sequence Model with Temporal Attention
Automatic video description generation has recently been getting attention after rapid advancement in image caption generation.
Universal Dependencies for Japanese
We present an attempt to port the international syntactic annotation scheme, Universal Dependencies, to the Japanese language in this paper.
Typed Entity and Relation Annotation on Computer Science Papers
In our scheme, mentions of entities are annotated with ontology-based types, and the roles of the entities are annotated as relations with other entities described in the text.
Towards Comparability of Linguistic Graph Banks for Semantic Parsing
We announce a new language resource for research on semantic parsing, a large, carefully curated collection of semantic dependency graphs representing multiple linguistic traditions.
Challenges and Solutions for Consistent Annotation of Vietnamese Treebank
However, the quality of this treebank is not satisfactory and is a possible source for the low performance of Vietnamese language processing.
Overview of Todai Robot Project and Evaluation Framework of its NLP-based Problem Solving
We introduce the organization of the Todai Robot Project and discuss its achievements.
Annotation of Computer Science Papers for Semantic Relation Extrac-tion
We designed a new annotation scheme for formalising relation structures in research papers, through the investigation of computer science papers.
Building Japanese Predicate-argument Structure Corpus using Lexical Conceptual Structure
In this paper, we report our framework for creating the corpus and the current status of creating an LCS dictionary for Japanese predicates.
Annotating Factive Verbs
These embedded presuppositions provide implicit information about facts assumed to be true in the world, and are thus potentially valuable in areas of research such as textual entailment.
