arXiv subjects

Naoki Otani

Publications and source records attributed to Naoki Otani.

12 recordsLinked to original sources

arXiv2026

Do Agents Need to Plan Step-by-Step? Rethinking Planning Horizon in Data-Centric Tool Calling

Explicit planning is a critical capability for LLM-based agents solving complex data-centric tasks, which require precise tool calling over external data sources. Existing strategies fall into two paradigms based on planning horizon: (1) full-horizon (FH), which generates a complete plan before execution, and (2) single-step horizon (SH), which interleaves each action (tool call) with incremental reasoning and observation. While step-by-step execution is a common default under the assumption that eager execution monitoring is necessary for adaptability, we revisit this assumption for well-defined data-centric tasks. Our controlled empirical study isolates planning horizon as the key architectural feature and systematically analyzes the effects of topological complexity and tool robustness on both paradigms. Our experiments across Knowledge Base Question Answering and Multi-hop QA show that FH planning with lazy replanning achieves accuracy parity with SH across varying depths, breadths, and robustness levels, while using 2-3x fewer tokens. These findings suggest that for well-defined data-centric tasks, eager step-wise monitoring is often unnecessary, and full-horizon planning with on-demand replanning can offer a more efficient default.

cs.CL↗

arXiv2026

Blue Data Intelligence Layer: Streaming Data and Agents for Multi-source Multi-modal Data-Centric Applications

NL2SQL systems aim to address the growing need for natural language interaction with data. However, real-world information rarely maps to a single SQL query because (1) users express queries iteratively (2) questions often span multiple data sources beyond the closed-world assumption of a single database, and (3) queries frequently rely on commonsense or external knowledge. Consequently, satisfying realistic data needs require integrating heterogeneous sources, modalities, and contextual data. In this paper, we present Blue's Data Intelligence Layer (DIL) designed to support multi-source, multi-modal, and data-centric applications. Blue is a compound AI system that orchestrates agents and data for enterprise settings. DIL serves as the data intelligence layer for agentic data processing, to bridge the semantic gap between user intent and available information by unifying structured enterprise data, world knowledge accessible through LLMs, and personal context obtained through interaction. At the core of DIL is a data registry that stores metadata for diverse data sources and modalities to enable both native and natural language queries. DIL treats LLMs, the Web, and the User as source 'databases', each with their own query interface, elevating them to first-class data sources. DIL relies on data planners to transform user queries into executable query plans. These plans are declarative abstractions that unify relational operators with other operators spanning multiple modalities. DIL planners support decomposition of complex requests into subqueries, retrieval from diverse sources, and finally reasoning and integration to produce final results. We demonstrate DIL through two interactive scenarios in which user queries dynamically trigger multi-source retrieval, cross-modal reasoning, and result synthesis, illustrating how compound AI systems can move beyond single database NL2SQL.

cs.AI↗

arXiv2026

Design and Performance of a Monolithic Plastic Scintillator Tracker with Embedded Scatterers

We propose a new scintillator-based tracker concept based on a monolithic plastic scintillator plate with embedded scatterers and wavelength-shifting fiber readout. The embedded scatterers localize scintillation light so that channels closer to the charged-particle crossing point collect more light. The particle crossing position is reconstructed from the channel-to-channel light yield distribution with a position resolution well below the readout pitch. We performed a positron beam test with prototypes to validate the reconstruction principle and to evaluate the detection efficiency and position resolution. The beam test validated the position reconstruction principle, and demonstrated a near-100% detection efficiency and a position resolution of 1.47 mm for normal incidence and 1.85 mm for an incidence angle of 45{\deg}, with a 10-mm readout pitch. In this paper, we describe the detector concept, the reconstruction method, and the results of the beam test.

physics.ins-det↗

arXiv2025

Wasserstein projection estimators for circular distributions

For statistical models on circles, we investigate performance of estimators defined as the projections of the empirical distribution with respect to the Wasserstein distance. We develop algorithms for computing the Wasserstein projection estimators based on a formula of the Wasserstein distances on circles. Numerical results on the von Mises, wrapped Cauchy, and sine-skewed von Mises distributions show that the Wasserstein projection estimators attain estimation accuracy comparable to the maximum likelihood estimator. In addition, the Wasserstein projection estimators are found to be robust against noise contamination.

math.ST↗

arXiv2025

The Preparation Status and Plan for the Next Physics Run of the NINJA Experiment

The NINJA experiment aims to precisely measure neutrino-nucleus interactions using a nuclear emulsion detector to reduce systematic errors in neutrino oscillation experiments. The nuclear emulsion has a sub-micron positional resolution, enabling the detection of low-momentum charged particles such as protons with a threshold of 200 MeV/c. In the NINJA experiment, a muon detector placed downstream of the emulsion detector is used to identify muons from $\nu_{\mu}$ charged-current interactions. The majority of the tracks accumulated in the nuclear emulsion are from cosmic rays. Although the emulsion detector provides highly accurate positional information, it lacks timing information. Therefore, the positional resolution of the muon detector is not enough to identify neutrino interaction tracks that match between the muon detector and the emulsion detector from the enormous background of cosmic rays recorded in the emulsion detector. To address this, a scintillation tracker is used to provide both timing and positional information for the tracks. The NINJA experiment is planning a third physics run with about 130 kg water target from the autumn of 2025 to the spring of 2026. Since the target mass is larger than previous runs, a larger scintillation tracker covering 1.3 m $\times$ 1.4 m is needed. We are developing a newly designed scintillation tracker, consisting of a monolithic plastic scintillator plane including scatterers. In this paper, we will show the preparation status and plan for the next physics run, focusing particularly on the development of the new scintillation tracker.

physics.ins-det↗

arXiv2024

Snippet-based Conversational Recommender System

Conversational Recommender Systems (CRS) engage users in interactive dialogues to gather preferences and provide personalized recommendations. While existing studies have advanced conversational strategies, they often rely on predefined attributes or expensive, domain-specific annotated datasets, which limits their flexibility in handling diverse user preferences and adaptability across domains. We propose SnipRec, a novel resource-efficient approach that leverages user-generated content, such as customer reviews, to capture a broader range of user expressions. By employing large language models to map reviews and user responses into concise snippets, SnipRec represents user preferences and retrieves relevant items without the need for intensive manual data collection or fine-tuning. Experiments across the restaurant, book, and clothing domains show that snippet-based representations outperform document- and sentence-based representations, achieving Hits@10 of 0.25-0.55 with 3,000 to 10,000 candidate items while successfully handling free-form user responses.

cs.IR↗

arXiv2024

Natural Language Processing for Human Resources: A Survey

Advances in Natural Language Processing (NLP) have the potential to transform HR processes, from recruitment to employee management. While recent breakthroughs in NLP have generated significant interest in its industrial applications, a comprehensive overview of how NLP can be applied across HR activities is still lacking. This paper discovers opportunities for researchers and practitioners to harness NLP's transformative potential in this domain. We analyze key fundamental tasks such as information extraction and text classification, and their roles in downstream applications like recommendation and language generation, while also discussing ethical concerns. Additionally, we identify gaps in current research and encourage future work to explore holistic approaches for achieving broader objectives in this field.

cs.CL↗

arXiv2023

Contextualized Word Vector-based Methods for Discovering Semantic Differences with No Training nor Word Alignment

In this paper, we propose methods for discovering semantic differences in words appearing in two corpora based on the norms of contextualized word vectors. The key idea is that the coverage of meanings is reflected in the norm of its mean word vector. The proposed methods do not require the assumptions concerning words and corpora for comparison that the previous methods do. All they require are to compute the mean vector of contextualized word vectors and its norm for each word type. Nevertheless, they are (i) robust for the skew in corpus size; (ii) capable of detecting semantic differences in infrequent words; and (iii) effective in pinpointing word instances that have a meaning missing in one of the two corpora for comparison. We show these advantages for native and non-native English corpora and also for historical corpora.

cs.CL↗

arXiv2023

Construction Grammar Provides Unique Insight into Neural Language Models

Construction Grammar (CxG) has recently been used as the basis for probing studies that have investigated the performance of large pretrained language models (PLMs) with respect to the structure and meaning of constructions. In this position paper, we make suggestions for the continuation and augmentation of this line of research. We look at probing methodology that was not designed with CxG in mind, as well as probing methodology that was designed for specific constructions. We analyse selected previous work in detail, and provide our view of the most important challenges and research questions that this promising new field faces.

cs.CL↗

arXiv2020

Neural Polysynthetic Language Modelling

Research in natural language processing commonly assumes that approaches that work well for English and and other widely-used languages are "language agnostic". In high-resource languages, especially those that are analytic, a common approach is to treat morphologically-distinct variants of a common root as completely independent word types. This assumes, that there are limited morphological inflections per root, and that the majority will appear in a large enough corpus, so that the model can adequately learn statistics about each form. Approaches like stemming, lemmatization, or subword segmentation are often used when either of those assumptions do not hold, particularly in the case of synthetic languages like Spanish or Russian that have more inflection than English. In the literature, languages like Finnish or Turkish are held up as extreme examples of complexity that challenge common modelling assumptions. Yet, when considering all of the world's languages, Finnish and Turkish are closer to the average case. When we consider polysynthetic languages (those at the extreme of morphological complexity), approaches like stemming, lemmatization, or subword modelling may not suffice. These languages have very high numbers of hapax legomena, showing the need for appropriate morphological handling of words, without which it is not possible for a model to capture enough word statistics. We examine the current state-of-the-art in language modelling, machine translation, and text prediction for four polysynthetic languages: Guaraní, St. Lawrence Island Yupik, Central Alaskan Yupik, and Inuktitut. We then propose a novel framework for language modelling that combines knowledge representations from finite-state morphological analyzers with Tensor Product Representations in order to enable neural language models capable of handling the full range of typologically variant languages.

cs.CL↗

arXiv2019

The ARIEL-CMU Systems for LoReHLT18

This paper describes the ARIEL-CMU submissions to the Low Resource Human Language Technologies (LoReHLT) 2018 evaluations for the tasks Machine Translation (MT), Entity Discovery and Linking (EDL), and detection of Situation Frames in Text and Speech (SF Text and Speech).

cs.CL↗

arXiv2018

Unsupervised Cross-lingual Transfer of Word Embedding Spaces

Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem would benefit many downstream tasks such as to translate text classification models from resource-rich languages (e.g. English) to low-resource languages. Supervised methods for this problem rely on the availability of cross-lingual supervision, either using parallel corpora or bilingual lexicons as the labeled data for training, which may not be available for many low resource languages. This paper proposes an unsupervised learning approach that does not require any cross-lingual labeled data. Given two monolingual word embedding spaces for any language pair, our algorithm optimizes the transformation functions in both directions simultaneously based on distributional matching as well as minimizing the back-translation losses. We use a neural network implementation to calculate the Sinkhorn distance, a well-defined distributional similarity measure, and optimize our objective through back-propagation. Our evaluation on benchmark datasets for bilingual lexicon induction and cross-lingual word similarity prediction shows stronger or competitive performance of the proposed method compared to other state-of-the-art supervised and unsupervised baseline methods over many language pairs.

cs.CL↗