Search Results for author:
Found 14 papers, 10 papers with code
Hitachi at SemEval-2022 Task 10: Comparing Graph- and Seq2Seq-based Models Highlights Difficulty in Structured Sentiment Analysis
In this task, we have to parse opinions considering both structure- and context-dependent subjective aspects, which is different from typical dependency parsing.
Hitachi at SemEval-2022 Task 2: On the Effectiveness of Span-based Classification Approaches for Multilingual Idiomaticity Detection
In this paper, we describe our system for SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding.
Vocabulary Expansion of Chat Models with Unlabeled Target Language Data
In this paper, we investigate the impact of using unlabeled target language data for VE on chat models for the first time.
Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus
Large language models (LLMs) are capable of solving a wide range of tasks, yet they have struggled with reasoning.
How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?
Large language models (LLMs) have shown remarkable capabilities in many languages beyond English.
An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference
We also show that adapting LLMs that have been pre-trained on more balanced multilingual data results in downstream performance comparable to the original models.
appjsonify: An Academic Paper PDF-to-JSON Conversion Toolkit
We present appjsonify, a Python-based PDF-to-JSON conversion toolkit for academic papers.
Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic
We rethink this and adopt a well-grounded set of deduction rules based on formal logic theory, which can derive any other deduction rules when combined in a multistep way.
How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese
This paper investigates the effect of tokenizers on the downstream performance of pretrained language models (PLMs) in scriptio continua languages where no explicit spaces exist between words, using Japanese as a case study.
How does the task complexity of masked pretraining objectives affect downstream performance?
Masked language modeling (MLM) is a widely used self-supervised pretraining objective, where a model needs to predict an original token that is replaced with a mask given contexts.
Hitachi at SemEval-2023 Task 3: Exploring Cross-lingual Multi-task Strategies for Genre and Framing Detection in Online News
Based on the multilingual, multi-task nature of the task and the low-resource setting, we investigated different cross-lingual and multi-task strategies for training the pretrained language models.
Team Hitachi @ AutoMin 2021: Reference-free Automatic Minuting Pipeline with Argument Structure Construction over Topic-based Summarization
This paper introduces the proposed automatic minuting system of the Hitachi team for the First Shared Task on Automatic Minuting (AutoMin-2021).
Frustratingly Simple Pretraining Alternatives to Masked Language Modeling
Masked language modeling (MLM), a self-supervised pretraining objective, is widely used in natural language processing for learning text representations.
Dialogue Act-based Breakdown Detection in Negotiation Dialogues
Thanks to the success of goal-oriented negotiation dialogue systems, studies of negotiation dialogue have gained momentum in terms of both human-human negotiation support and dialogue systems.
