Results 11 to 20 of about 13,115 (136)
Humaniora, 2016 The research problems in this research are 1) how lexicogrammar takes role in determining polarity of F-Word1 and 2) how to formalize it for corpus processing. The data is obtained from the Contemporary American English Corpus (COCA).
Prihantoro Prihantoro
doaj +1 more source
, 2020 Automatic speech recognition (ASR) via call is essential for various applications, including AI for contact center (AICC) services. Despite the advancement of ASR, however, most publicly available call-based speech corpora such as Switchboard are old ...
Doh, Kyoungtae +13 more
core +1 more source
Selective Attention for Context-aware Neural Machine Translation
, 2019 Despite the progress made in sentence-level NMT, current systems still fall short at achieving fluent, good quality translation for a full document. Recent works in context-aware NMT consider only a few previous sentences as context and may not scale to ...
Haffari, Gholamreza +2 more
core +1 more source
Density Matching for Bilingual Word Embedding
, 2019 Recent approaches to cross-lingual word embedding have generally been based on linear transformations between the sets of embedding vectors in the two languages.
Ma, Xuezhe +3 more
core +1 more source
MAG: A Multilingual, Knowledge-base Agnostic and Deterministic Entity Linking Approach
, 2017 Entity linking has recently been the subject of a significant body of research. Currently, the best performing approaches rely on trained mono-lingual models. Porting these approaches to other languages is consequently a difficult endeavor as it requires
Bryl Volha +14 more
core +1 more source
An Offline Corpus for Legal Translations into Italian: a Case Study with a Land Lease Agreement
Altre Modernità, 2020 Offline corpora are claimed to be helpful in technical translations. This paper explores whether a corpus of Italian land lease agreement samples and the civil code can be supportive in legal translations.
Patrizia Giampieri
doaj
UD Annotatrix: An Annotation Tool For Universal Dependencies [PDF]
, 2017 In this paper we introduce the UD Annotatrix annotation tool for manual annotation of Universal Dependencies. This tool has been designed with the aim that it should be tailored to the needs of the Universal Dependencies (UD) community, including that it
Sheyanova, M. +2 more
core +1 more source
Multimodal Human–Robot Interaction Using Human Pose Estimation and Local Large Language Models
Advanced Robotics Research, EarlyView.A multimodal human–robot interaction framework integrates human pose estimation (HPE) and a large language model (LLM) for gesture‐ and voice‐based robot control. Speech‐to‐text (STT) enables voice command interpretation, while a safety‐aware arbitration mechanism prioritizes gesture input for rapid intervention.
Nasiru Aboki +2 more
wiley +1 more source
Watermarking Fine-Tuning Datasets for Robust Provenance
Applied SciencesLarge Language Models are often fine-tuned on proprietary corpora, motivating reliable provenance signals. A corpus-level watermark method is proposed for fine-tuning datasets that survives training and common text transformations.
Ivo Gergov, Georgi Tsochev
doaj +1 more source
AI in chemical engineering: From promise to practice
AIChE Journal, EarlyView.Abstract Artificial intelligence (AI) in chemical engineering has moved from promise to practice: physics‐aware (gray‐box) models are gaining traction, reinforcement learning complements model predictive control (MPC), and generative AI powers documentation, digitization, and safety workflows.
Jia Wei Chew +4 more
wiley +1 more source