Arrow Research search

Author name cluster

Ken Satoh

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

33 papers
2 author rows

Possible papers

33

NMR Workshop 2025 Conference Paper

Evaluating Novel Arguments in Case Models: Lessons from Belief Change and Abstract Argumentation for Case-based Reasoning

  • Wachara Fungwacharakorn
  • Guilherme Paulino-Passos
  • Bart Verheij
  • Ken Satoh

In the intersection between case-based reasoning and non-monotonic reasoning, case models serve as frameworks to evaluate arguments with respect to cases. The evaluation is based on their coherence, presumptive validity, and conclusiveness, in which all valid arguments must be at least coherent, meaning that those arguments must be grounded in at least one case. This paper, on the other hand, attempts to explore new evaluations for novel arguments, which are not required to ground in any case. To develop the new evaluation, we introduce revision operators in case models and associated properties based on AGM postulates. We then de! ne a conclusively adherent evaluation, in which novel arguments can be valid. After that, we relate their application to the understanding of abstract argumentation for case-based reasoning (AA-CBR). We demonstrate how the translation of AA-CBR case bases into case models can be described through revision sequences; and analyse the properties of conclusively adherent evaluation related to evaluation and attacks in AA-CBR.

Details

LORI Conference 2025 Conference Paper

Intentionally Anonymous Public Announcements

  • Thomas Ågotnes
  • Rustam Galimullin
  • Ken Satoh
  • Satoshi Tojo

Abstract We formalise the notion of an intentionally anonymous public announcement in the tradition of public announcement logic. An anonymous announcement can be seen as in-between a public announcement from “the outside” (an announcement of \(\varphi \) ) and a public announcement by one of the agents a (an announcement of \(K_a\varphi \) ): we get more information than just \(\varphi \), but not (necessarily) about exactly who made it. In this paper we assume that it is common knowledge that the announcer intended to be anonymous. Like in the Russian Cards puzzle, with that assumption, anonymous announcements in fact reveal more information than without. We introduce an operator for intentionally anonymous announcements, and show that in several ways it all boils down to the notion of a “safe” announcement (again, similarly to Russian Cards). We model safety via a fixed-point operator that is similar to common knowledge. Main formal results include comparisons of expressivity and axiomatic completeness for a language expressing safety.

Details

AILAW Journal 2025 Journal Article

Leveraging LLMs for legal terms extraction with limited annotated data

  • Julien Breton
  • Mokhtar Mokhtar Billami
  • Max Chevalier
  • Ha Thanh Nguyen
  • Ken Satoh
  • Cassia Trojahn
  • May Myo Zin

Abstract The legal industry is characterized by the presence of dense and complex documents, which necessitate automatic processing methods to manage and analyse large volumes of data. Traditional methods for extracting legal information depend heavily on substantial quantities of annotated data during the training phase. However, a question arises on how to extract information effectively in contexts that do not favour the utilization of annotated data. This study investigates the application of Large Language Models (LLMs) as a transformative solution for the extraction of legal terms, presenting a novel approach to overcome the constraints associated with the need for extensive annotated datasets. Our research delved into methods such as prompt-engineering and fine-tuning to enhance their performance. We evaluated and compared, to a rule-based and BERT systems, the performance of four LLMs: GPT-4, Miqu-1-70b, Mixtral-8x7b, and Mistral-7b, within the scope of limited annotated data availability. We implemented and assessed our methodologies using Luxembourg’s traffic regulations as a case study. Our findings underscore the capacity of LLMs to successfully deal with legal terms extraction, emphasizing the benefits of one-shot and zero-shot learning capabilities in reducing reliance on annotated data by reaching 0.690 F1 Score. Moreover, our study sheds light on the optimal practices for employing LLMs in the processing of legal information, offering insights into the challenges and limitations, including issues related to terms boundary extraction.

Details DOI

AILAW Journal 2023 Journal Article

Compliance checking on first-order knowledge with conflicting and compensatory norms: a comparison among currently available technologies

  • Livio Robaldo
  • Sotiris Batsakis
  • Roberta Calegari
  • Francesco Calimeri
  • Megumi Fujita
  • Guido Governatori
  • Maria Concetta Morelli
  • Francesco Pacenza

Abstract This paper analyses and compares some of the automated reasoners that have been used in recent research for compliance checking. Although the list of the considered reasoners is not exhaustive, we believe that our analysis is representative enough to take stock of the current state of the art in the topic. We are interested here in formalizations at the first-order level. Past literature on normative reasoning mostly focuses on the propositional level. However, the propositional level is of little usefulness for concrete LegalTech applications, in which compliance checking must be enforced on (large) sets of individuals. Furthermore, we are interested in technologies that are freely available and that can be further investigated and compared by the scientific community. In other words, this paper does not consider technologies only employed in industry and/or whose source code is non-accessible. This paper formalizes a selected use case in the considered reasoners and compares the implementations, also in terms of simulations with respect to shared synthetic datasets. The comparison will highlight that lot of further research still needs to be done to integrate the benefits featured by the different reasoners into a single standardized first-order framework, suitable for LegalTech applications. All source codes are freely available at https://github.com/liviorobaldo/compliancecheckers, together with instructions to locally reproduce the simulations.

Details DOI

AILAW Journal 2022 Journal Article

SM-BERT-CR: a deep learning approach for case law retrieval with supporting model

  • Yen Thi-Hai Vuong
  • Quan Minh Bui
  • Ha-Thanh Nguyen
  • Thi-Thu-Trang Nguyen
  • Vu Tran
  • Xuan-Hieu Phan
  • Ken Satoh
  • Le-Minh Nguyen

Abstract Case law retrieval is the task of locating truly relevant legal cases given an input query case. Unlike information retrieval for general texts, this task is more complex with two phases ( legal case retrieval and legal case entailment ) and much harder due to a number of reasons. First, both the query and candidate cases are long documents consisting of several paragraphs. This makes it difficult to model with representation learning that usually has restriction on input length. Second, the concept of relevancy in this domain is defined based on the legal relation that goes beyond the lexical or topical relevance. This is a real challenge because normal text matching will not work. Third, building a large and accurate legal case dataset requires a lot of effort and expertise. This is obviously an obstacle to creating enough data for training deep retrieval models. In this paper, we propose a novel approach called supporting model that can deal with both phases. The underlying idea is the case–case supporting relation and the paragraph–paragraph as well as the decision-paragraph matching strategy. In addition, we propose a method to automatically create a large weak-labeling dataset to overcome the lack of data. The experiments showed that our solution has achieved the state-of-the-art results for both case retrieval and case entailment phases.

Details DOI

NMR Workshop 2022 Conference Paper

Towards Legally and Ethically Correct Online HTN Planning for Data Transfer

  • Hisashi Hayashi
  • Ken Satoh

Data transfer among servers is crucial for distributed data mining because many databases are distributed around the world. However, as data privacy is becoming more legally and ethically protected, it is necessary to abide by the laws and respect the ethical guidelines when transferring and utilizing data. Because information affecting legal/ethical decision making is often distributed, the data-transfer plan must be updated online when new information is obtained while transferring data among servers. In this study, we propose a dynamic hierarchical task network (HTN) planning method that considers legal and ethical norms while planning multihop data transfers and data analyses/transformations. In our knowledge representation, we show that data-transfer tasks can be represented by the task-decomposition rules of total-order HTN planning. We also show that legal norms can be expressed as the preconditions of tasks and actions, and ethical norms can be expressed as the costs of tasks and actions where legal norms cannot be violated, but ethical norms can be violated if necessary following the ethical theory of utilitarianism. In the middle of the plan execution, the online planner dynamically updates the plan based on new information obtained in accordance with laws and ethical guidelines.

Details

AILAW Journal 2021 Journal Article

Abstract meaning representation for legal documents: an empirical research on a human-annotated dataset

  • Sinh Trong Vu
  • Minh Le Nguyen
  • Ken Satoh

Abstract Natural language processing techniques contribute more and more in analyzing legal documents recently, which supports the implementation of laws and rules using computers. Previous approaches in representing a legal sentence often based on logical patterns that illustrate the relations between concepts in the sentence, often consist of multiple words. Those representations cause the lack of semantic information at the word level. In our work, we aim to tackle such shortcomings by representing legal texts in the form of abstract meaning representation (AMR), a graph-based semantic representation that gains lots of polarity in NLP community recently. We present our study in AMR Parsing (producing AMR from natural language) and AMR-to-text Generation (producing natural language from AMR) specifically for legal domain. We also introduce JCivilCode, a human-annotated legal AMR dataset which was created and verified by a group of linguistic and legal experts. We conduct an empirical evaluation of various approaches in parsing and generating AMR on our own dataset and show the current challenges. Based on our observation, we propose our domain adaptation method applying in the training phase and decoding phase of a neural AMR-to-text generation model. Our method improves the quality of text generated from AMR graph compared to the baseline model. (This work is extended from our two previous papers: “An Empirical Evaluation of AMR Parsing for Legal Documents”, published in the Twelfth International Workshop on Juris-informatics (JURISIN) 2018; and “Legal Text Generation from Abstract Meaning Representation”, published in the 32nd International Conference on Legal Knowledge and Information Systems (JURIX) 2019.).

Details DOI

AILAW Journal 2021 Journal Article

Resolving counterintuitive consequences in law using legal debugging

  • Wachara Fungwacharakorn
  • Kanae Tsushima
  • Ken Satoh

Abstract There are cases in which the literal interpretation of statutes may lead to counterintuitive consequences. When such cases go to high courts, judges may handle these counterintuitive consequences by identifying problematic rule conditions. Given that the law consists of a large number of rule conditions, it is demanding and exhaustive to figure out which condition is problematic. For solving this problem, our work aims to assist judges in civil law systems to resolve counterintuitive consequences using logic program representation of statutes and Legal Debugging. The core principle of Legal Debugging is to cooperate with a user to find a culprit, a root cause of counterintuitive consequences. This article proposes an algorithm to resolve a culprit. Since the statutes are represented by logic rules but changes in law are initiated by cases, we adopt a prototypical case with judgement specified by a set of rules. Then, to resolve a culprit, we reconstruct a program so that it provides reasons as if we applied case-based reasoning to a new set of prototypical cases with judgement, which include a new set of facts relevant to a considering case.

Details DOI

IJCAI Conference 2020 Conference Paper

BERT-PLI: Modeling Paragraph-Level Interactions for Legal Case Retrieval

  • Yunqiu Shao
  • Jiaxin Mao
  • Yiqun Liu
  • Weizhi Ma
  • Ken Satoh
  • Min Zhang
  • Shaoping Ma

Legal case retrieval is a specialized IR task that involves retrieving supporting cases given a query case. Compared with traditional ad-hoc text retrieval, the legal case retrieval task is more challenging since the query case is much longer and more complex than common keyword queries. Besides that, the definition of relevance between a query case and a supporting case is beyond general topical relevance and it is therefore difficult to construct a large-scale case retrieval dataset, especially one with accurate relevance judgments. To address these challenges, we propose BERT-PLI, a novel model that utilizes BERT to capture the semantic relationships at the paragraph-level and then infers the relevance between two cases by aggregating paragraph-level interactions. We fine-tune the BERT model with a relatively small-scale case law entailment dataset to adapt it to the legal scenario and employ a cascade framework to reduce the computational cost. We conduct extensive experiments on the benchmark of the relevant case retrieval task in COLIEE 2019. Experimental results demonstrate that our proposed method outperforms existing solutions.

PDF Details DOI

AILAW Journal 2020 Journal Article

Encoded summarization: summarizing documents into continuous vector space for legal case retrieval

  • Vu Tran
  • Minh Le Nguyen
  • Satoshi Tojo
  • Ken Satoh

Abstract We present our method for tackling a legal case retrieval task by introducing our method of encoding documents by summarizing them into continuous vector space via our phrase scoring framework utilizing deep neural networks. On the other hand, we explore the benefits from combining lexical features and latent features generated with neural networks. Our experiments show that lexical features and latent features generated with neural networks complement each other to improve the retrieval system performance. Furthermore, our experimental results suggest the importance of case summarization in different aspects: using provided summaries and performing encoded summarization. Our approach achieved F1 of 65. 6% and 57. 6% on the experimental datasets of legal case retrieval tasks.

Details DOI

AILAW Journal 2018 Journal Article

Recurrent neural network-based models for recognizing requisite and effectuation parts in legal texts

  • Truong-Son Nguyen
  • Le-Minh Nguyen
  • Satoshi Tojo
  • Ken Satoh
  • Akira Shimazu

Abstract This paper proposes several recurrent neural network-based models for recognizing requisite and effectuation (RE) parts in Legal Texts. Firstly, we propose a modification of BiLSTM-CRF model that allows the use of external features to improve the performance of deep learning models in case large annotated corpora are not available. However, this model can only recognize RE parts which are not overlapped. Secondly, we propose two approaches for recognizing overlapping RE parts including the cascading approach which uses the sequence of BiLSTM-CRF models and the unified model approach with the multilayer BiLSTM-CRF model and the multilayer BiLSTM-MLP-CRF model. Experimental results on two Japan law RRE datasets demonstrated advantages of our proposed models. For the Japanese National Pension Law dataset, our approaches obtained an \(F_{1}\) score of 93. 27% and exhibited a significant improvement compared to previous approaches. For the Japan Civil Code RRE dataset which is written in English, our approaches produced an \(F_{1}\) score of 78. 24% in recognizing RE parts that exhibited a significant improvement over strong baselines. In addition, using external features and in-domain pre-trained word embeddings also improved the performance of RRE systems.

Details DOI

JAAMAS Journal 2016 Journal Article

A dynamic default revision mechanism for speculative computation

  • Tiago Oliveira
  • Ken Satoh
  • Hiroshi Hosobe

Abstract In this work a default revision mechanism is introduced into speculative computation to manage incomplete information. The default revision is supported by a method for the generation of default constraints based on Bayesian networks. The method enables the generation of an initial set of defaults which is used to produce the most likely scenarios during the computation, represented by active processes. As facts arrive, the Bayesian network is used to derive new defaults. The objective with such a new dynamic mechanism is to keep the active processes coherent with arrived facts. This is achieved by changing the initial set of default constraints during the reasoning process in speculative computation. A practical example in clinical decision support is described.

Details DOI

KR Conference 2016 Short Paper

Abstract Argumentation for Case-Based Reasoning

  • Kristijonas Cyras
  • Francesca Toni
  • Ken Satoh

We investigate case-based reasoning (CBR) problems where cases are represented by abstract factors and (positive or negative) outcomes, and an outcome for a new case, represented by abstract factors, needs to be established. To this end, we employ abstract argumentation (AA) and propose a novel methodology for CBR, called AA-CBR. The argumentative formulation naturally allows to characterise the computation of an outcome as a dialogical process between a proponent and an opponent, and can also be used to extract explanations for why an outcome for a new case is (not) computed. Example 1. Alice has bought a chair from an online retailer, but wants to return it and get a refund. The retailer has a system, where a customer can claim for a refund by providing factual information about the situation. In Alice’s case: she does not like the chair (factor A); she has used the chair (factor B); the chair shows no signs of wear and tear (C); Alice had the chair for more than 30 days (D). So an outcome for Alice’s case {A, B, C, D} needs to be established. By default, the retailer will provide no refund (−) when no factors are present. The retailer has a case base CB containing previous cases together with outcomes, e. g. consisting of: a case ({A}, +) with the outcome ‘refund’ (+) if the customer does not like the chair; ({A, B}, −) sustaining no refund if in addition the customer has used the chair; and ({A, B, C}, +) when in further addition the chair is in a good condition. The outcome of the new (Alice’s) case depends on the past cases most similar to the new case: since ({A, B, C}, +) is the only such case, Alice should get refunded (+). But what if the case base contained ({A, D}, −)? Then there would be two nearest cases, ({A, B, C}, +) and ({A, D}, −). Would Alice be entitled to a refund?

AAMAS Conference 2013 Conference Paper

Combining Event- and State-Based Norms

  • Marina De Vos
  • Tina Balke
  • Ken Satoh

Institutions offer a mechanism to regulate the behaviour of agents without the need for these agents to internalise the norms of the system. Current formalisms can be divided in two groups depending on whether norms are expressed on the state of the normative structure or the events that bring about normative change. This paper argues that for complex systems both types are needed. To this extend, we introduce ESI, a formal model for institutions incorporating the concepts for both event- and state-based normative modelling. We demonstrate our approach with a simplified legal case-study.

PDF

AAMAS Conference 2012 Conference Paper

Handling Change in Normative Specifications

  • Duangtida Athakravi
  • Domenico Corapi
  • Alessandra Russo
  • Marina De Vos
  • Julian Padget
  • Ken Satoh

Normative frameworks provide a means to address the governance of open systems, by offering a mechanism to express responsibilities and permissions of the individual participants with respect to the entire system without compromising their autonomy. Careful design is crucial if it is to meet its requirements. Tools that support the design process can be of great benefit. In this paper, we describe a method for choosing the appropriate change in the normative specification, using impact analysis of the critical consequences being preserved or rejected by the change.

PDF

TCS Journal 2010 Journal Article

On the complexities of consistency checking for restricted UML class diagrams

  • Ken Kaneiwa
  • Ken Satoh

Automatic debugging of UML class diagrams helps in the visual specification of software systems because users cannot detect errors in logical consistency easily. This study focuses on the tractable consistency checking of UML class diagrams. We accurately identify inconsistencies in these diagrams by translating them into first-order predicate logic that is generalized by counting quantifiers and classify their expressivities by eliminating certain components. We introduce optimized algorithms that compute the respective consistencies of class diagrams of different expressive powers in P, NP, PSPACE, or EXPTIME with respect to the size of the class diagrams. In particular, owing to the restrictions imposed on attribute value types, the complexities of consistency checking of class diagrams decrease from EXPTIME to P and PSPACE in two cases: (i) when the class diagrams contain disjointness constraints and overwriting/multiple inheritances and (ii) when the class diagrams contain both these components along with completeness constraints. Additionally, we confirm the existence of a restriction of class diagrams that prevents any logical inconsistency.

Details DOI

IJCAI Conference 2007 Conference Paper

  • Shin-ichi Minato
  • Ken Satoh
  • Taisuke Sato

Compiling Bayesian networks (BNs) is a hot topic within probabilistic modeling and processing. In this paper, we propose a new method for compiling BNs into Multi-Linear Functions (MLFs) based on Zero-suppressed Binary Decision Diagrams (ZBDDs), which are a graph-based representation of combinatorial item sets. Our method differs from the original approach of Darwiche et al. , which encodes BNs into Conjunctive Normal Forms (CNFs) and then translates CNFs into factored MLFs. Our approach directly translates a BN into a set of factored MLFs using a ZBDD-based symbolic probability calculation. The MLF may have exponential computational complexity, but our ZBDD-based data structure provides a compact factored form of the MLF, and arithmetic operations can be executed in a time almost linear with the ZBDD size. In our method, it is not necessary to generate the MLF for the whole network, as we can extract MLFs for only part of the network related to the query, avoiding unnecessary calculation of redundant MLF terms. We present experimental results for some typical benchmark examples. Although our algorithm is simply based on the mathematical definition of probability calculation, performance is competitive to existing state-of-the-art methods.

PDF Details

TCS Journal 2005 Journal Article

Learning taxonomic relation by case-based reasoning

  • Ken Satoh

In this paper, we propose a learning method of minimal casebase to represent taxonomic relation in a tree-structured concept hierarchy. We firstly propose case-based taxonomic reasoning and show an upper bound of necessary positive cases and negative cases to represent a relation. Then, we give a learning method of a minimal casebase with sampling and membership queries. We analyze this learning method by sample complexity and query complexity in the framework of PAC learning.

Details DOI

NMR Workshop 2004 Conference Paper

"All's well that ends well" - a proposal of global abduction

  • Ken Satoh

This paper presents a new form of abduction called global abduction. Usual abduction in logic programming is used to complement unknown information and used in one derivation path in a search tree. We call this kind of abduction local abduction. In this paper, we propose another abduction which is used over paths in a search tree for search control. As far as we know, this is the first attempt to formalize a search control in a logical way. We discuss applications of global abduction by using examples; a formalization of don’t-care nondeterminism and a formalization of reuse of the previously obtained result in a different search path. Then, we give a correct proof procedure for global abduction. The correctness is defined as “all’s well that ends well” principle meaning that the results obtained from a global abduction proof procedure are exactly the same as the ones which are logically true from the augmented program with the last set of abduced atoms.

Details

NMR Workshop 2002 Conference Paper

Speculative computation and abduction for an autonomous agent

  • Ken Satoh

In this paper, we propose an agent architecture for a combination of speculative computation and abduction. Speculative computation is a tentative computation when complete information for performing computation is not obtained. We use a default value to complement such incomplete information. Unlike usual default reasoning, the real value for the information can be obtained during the computation and the computation can be revised on the fly. In the previous work, we applied this technique to handling distributed problem solving under incomplete communication environments in the context of multi-agent systems and proposed correct procedures in abductive logic programming in terms of perfect model semantics. In the previous work, however, we regard assumptions as defaults and therefore, we could not perform a hypothetical reasoning which is the original usage of abduction. In this paper, we extend our framework so that speculative computation and abduction can be both performed. As a result, our procedure becomes an extension of the abductive procedure developed by Kakas and Mancarella augmented by dynamic belief revision mechanism about outside world.

Details

IJCAI Conference 1997 Conference Paper

Compiling Prioritized Circumscription into Extended Logic Programs

  • Toshiko Wakaki
  • Ken Satoh

We propose a method of compiling circumscription into Extended Logic Programs which is widely applicable to a class of parallel circumscription as well as a class of prioritized circumscription. In this paper, we show theoretically that any circumscription whose theory contains both the domain closure axiom and the uniqueness of names axioms can always be compiled into an extended logic program II, so that, whether a ground literal is provable from circumscription or not, can always be evaluated by deciding whether the literal is true in all answer sets of II, which can be computed by running II under the existing logic programming interpreter.

PDF

AAAI Conference 1990 Conference Paper

A Probabilistic Interpretation for Lazy Nonmonotonic Reasoning

  • Ken Satoh

This paper presents a formal relationship Ken Satoh Generation Computer Technology Minato-ku, Tokyo 108, Japan ksatoh@icot. jp for. probability theory and a class of nonmonotomc reasoning which we call daxynonmonotonic reusoning. In lazy nonmonotonic reasoning, nonmonotonicity emerges only when new added knowledge is contradictory to the previous belief. In this paper, we consider nonmonotonic reasoning in terms of consequence relation. A consequence relation is a binary relation over formulas which expresses that a formula is derivable from another formula under inference rules of a considered system. A consequence relation which has lazy nonmonotonicity is called a rutionad consequence relation studied by Lehmann and Magidor (1988). We provide a probabilistic semantics which characterizes a rational consequence relation exactly. Then, we show a relationship between propositional circumscription and consequence relation, and apply this semantics to a consequence relation defined by propositional circumscription which has lazy nonmonotonicity.

PDF Details