An information-theoretic perspective of tf-idf measures
- Akiko Aizawa
- Computer ScienceInformation Processing & Management
- 2003
A Conditional Variational Framework for Dialog Generation
- Xiaoyu Shen, Hui Su, Guoping Long
- Computer ScienceAnnual Meeting of the Association for…
- 30 April 2017
This paper proposes a framework allowing conditional response generation based on specific attributes, which can be either manually assigned or automatically detected and validated on two different scenarios, where the attribute refers to genericness and sentiment states respectively.
Scheduling of Genetic Algorithms in a Noisy Environment
- Akiko Aizawa, B. Wah
- Computer ScienceEvolutionary Computation
- 1 June 1994
New methods for adjusting configuration parameters of genetic algorithms operating in a noisy environment by model the search process as a statistical selection process and derive equations useful for problems related to the scheduling of resources for tests performed in genetic algorithms are developed.
What Makes Reading Comprehension Questions Easier?
- Saku Sugawara, Kentaro Inui, S. Sekine, Akiko Aizawa
- Computer ScienceConference on Empirical Methods in Natural…
- 28 August 2018
This study proposes to employ simple heuristics to split each dataset into easy and hard subsets and examines the performance of two baseline models for each of the subsets, and observes that the baseline performances for thehard subsets remarkably degrade compared to those of entire datasets.
A Fast Linkage Detection Scheme for Multi-Source Information Integration
- Akiko Aizawa, K. Oyama
- Computer ScienceInternational Workshop on Challenges in Web…
- 8 April 2005
This paper proposes a fast and efficient method for linkage detection that exploits a suffix array structure that enables linkage detection using variable length n-grams and dynamically generates blocks of possibly associated records using ‘blocking keys’ extracted from already known reliable linkages.
A Language Model based Evaluator for Sentence Compression
- Yang Zhao, Zhiyuan Luo, Akiko Aizawa
- Computer ScienceAnnual Meeting of the Association for…
- 1 July 2018
A language-model-based evaluator for deletion-based sentence compression and an empirical study shows that the proposed model can effectively generate more readable compression, comparable or superior to several strong baselines.
Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
- Xanh Ho, A. Nguyen, Saku Sugawara, Akiko Aizawa
- Computer ScienceInternational Conference on Computational…
- 2 November 2020
This study presents a new multi-hop QA dataset, called 2WikiMultiHopQA, which uses structured and unstructured data and introduces the evidence information containing a reasoning path forMulti-hop questions, and demonstrates that the dataset is challenging formulti-hop models and it ensures that multi-Hop reasoning is required.
NTCIR-12 MathIR Task Overview
- R. Zanibbi, Akiko Aizawa, M. Kohlhase, I. Ounis, Goran Topic, Kenny Davila
- Computer ScienceNTCIR Conference on Evaluation of Information…
- 2016
This overview paper summarizes the task design, corpora, submitted runs, results, and the approaches used by participating groups of the NTCIR-12 MathIR Task.
NTCIR-11 Math-2 Task Overview
- Akiko Aizawa, M. Kohlhase, I. Ounis, M. Schubotz
- Computer ScienceNTCIR Conference on Evaluation of Information…
- 2014
An overview of the NTCIR-11 Math-2 Task is presented, which is dedicated to information access to mathematical content, and an introduction to the optional free Wikipedia subtask, a newly introduced mathematical retrieval task using Wikipedia articles.
Assessing the Benchmarking Capacity of Machine Reading Comprehension Datasets
- Saku Sugawara, Pontus Stenetorp, Kentaro Inui, Akiko Aizawa
- Computer ScienceAAAI Conference on Artificial Intelligence
- 21 November 2019
Results suggest that most of the questions already answered correctly by the model do not necessarily require grammatical and complex reasoning, and therefore, MRC datasets will need to take extra care in their design to ensure that questions can correctly evaluate the intended skills.
...
...