Person Name Recognition Research Articles

Exploring the Capabilities of ChatGPT in Ancient Chinese Translation and Person Name Recognition

Abstract This study examines the potential of ChatGPT, notable for its skill in standard modern languages, in the context of ancient Chinese. We focus on two fundamental tasks: translating ancient Chinese into modern Chinese and identifying ancient Chinese names. We conduct experiments on Shi Shuo Xin Yu, which is a collection of anecdotes, short conversations, and pithy observations on personalities who lived in China between about 150 and 420 A.D. We also include other methods, like Baidu Yiyan (ERNIE-Bot) for ancient-to-modern translation, and SIKU-RoBERTa for ancient Chinese name recognition. The results reveal that ChatGPT’s performance in ancient Chinese remains in need of enhancement, but it excels in the task of ancient-to-modern translation with the provision of a few context sentences. For the ancient Chinese name recognition, ChatGPT can outperform SIKU-RoBERTa model in terms of precision, but suffers from low recall.

Transliteration recognition of Tibetan person name based on Tibetan cultural knowledge

Institute of Computing Technology, Chinese Lexical Analysis System (ICTCLAS) is a common tool for Chinese word segmentation and named entity recognition. With this tool, the F1 value of person name recognition from Chinese texts in Tibetan culture is only 40%. We propose a method for transliteration recognition of Tibetan person name based on Tibetan cultural knowledge. Firstly, we leverage Tibetan cultural dictionary to improve the word segmentation performance of ICTCLAS. Then, special contextual features and naming rules of Tibetan person name in their culture are adopted to determine the boundary of Chinese transliteration of Tibetan person name. Finally, the transliteration candidates of Tibetan person name are filtered based on discrimination and reliability. Experiments on a 1.2 M Tibetan text in Tibetan culture show that the method can increase the F1 value of Chinese transliteration recognition of Tibetan person name from 40.08% to 87.92% in ICTCLAS.

Studying the impact of language-independent and language-specific features on hybrid Arabic Person name recognition

In this paper, extensive experiments are conducted to study the impact of features of different categories, in isolation and gradually in an incremental manner, on Arabic Person name recognition. We present an integrated system that employs the rule-based approach with the machine learning (ML)-based approach in order to develop a consolidated hybrid system. Our feature space is comprised of language-independent and language-specific features. The explored features are naturally grouped under six categories: Person named entity tags predicted by the rule-based component, word-level features, POS features, morphological features, gazetteer features, and other contextual features. As decision tree algorithm has proved comparatively higher efficiency as a classifier in current state-of-the-art hybrid Named Entity Recognition for Arabic, it is adopted in this study as the ML technique utilized by the hybrid system. Therefore, the experiments are focused on two dimensions: the standard dataset used and the set of selected features. A number of standard datasets are used for the training and testing of the hybrid system, including ACE (2003---2004) and ANERcorp. The experimental analysis indicates that both language-independent and language-specific features play an important role in overcoming the challenges posed by Arabic language and have demonstrated critical impact on optimizing the performance of the hybrid system.

Boosted Web Named Entity Recognition via Tri-Training

Named entity extraction is a fundamental task for many natural language processing applications on the web. Existing studies rely on annotated training data, which is quite expensive to obtain large datasets, limiting the effectiveness of recognition. In this research, we propose a semisupervised learning approach for web named entity recognition (NER) model construction via automatic labeling and tri-training. The former utilizes structured resources containing known named entities for automatic labeling, while the latter makes use of unlabeled examples to improve the extraction performance. Since this automatically labeled training data may contain noise, a self-testing procedure is used as a follow-up to remove low-confidence annotation and prepare higher-quality training data. Furthermore, we modify tri-training for sequence labeling and derive a proper initialization for large dataset training to improve entity recognition. Finally, we apply this semisupervised learning framework for person name recognition, business organization name recognition, and location name extraction. In the task of Chinese NER, an F-measure of 0.911, 0.849, and 0.845 can be achieved, for person, business organization, and location NER, respectively. The same framework is also applied for English and Japanese business organization name recognition and obtains models with performance of a 0.832 and 0.803 F-measure.

A Hybrid Approach Using Maximum Entropy Model and Conditional Random Fields to Identify Tibetan Person Names

Tibetan person name recognition is one of the most difficult tasks in the area of Tibetan information processing, and the effect of recognition impacts directly on the precision of Tibetan word segmentation and the performance of relative application systems, including Tibetan-Chinese machine translation, Tibetan informationretrieval, text categorization, etc. Based on the analysis of wording rules and features of Tibetan person names, this paper proposes a method which combines maximum entropy and conditional random fields to identify Tibetan person names. The experiment shows that this approach works quite well, with the value of F1-measure reaching 93.29%. Copyright Information:

Automatic Recognition of Chinese Personal Name Using Conditional Random Fields and Knowledge Base

According to the features of Chinese personal name, we present an approach for Chinese personal name recognition based on conditional random fields (CRF) and knowledge base in this paper. The method builds multiple features of CRF model by adopting Chinese character as processing unit, selects useful features based on selection algorithm of knowledge base and incremental feature template, and finally implements the automatic recognition of Chinese personal name from Chinese document. The experimental results on open real corpus demonstrated the effectiveness of our method and obtained high accuracy rate and high recall rate of recognition.

A Pre-Identification Method for Chinese Named Entity Recognition

In this paper, a pre-identification method for Chinese named entity recognition is proposed. Internal information of entity name like family name, first name in person name, feature word in place name and organization name do not needed. Through entity name guessing based on context keywords, pre-identification is realized. Definition of bidirectional potential entity name recognition, rough confirmation of potential entity name, segmentation word is proposed. To solve the possible ambiguity in entity name identification, the degree of segmentation and conjunction is presented as well as cascade recognition and final confirmation. Combining with this pre-processing method, performance will be improved by using internal information of entity name. Experiment proves that the method have a special advantage in recognition special entity name, ambiguity name and irregular name. In this paper, Chinese person name is taken as an example for entity name recognition. Nevertheless, the method is not limit to person name recognition but also a pre-identification method for other entity name.

Multilingual person name recognition and transliteration

Nous présentons ici un outil de repérage des noms de personnes, à partir d’articles de la presse internationale, capable de reconnaître les différentes variantes d’un même nom. L’originalité de notre approche vient de l’identification des variantes de noms à travers les langues et systèmes d’écriture, grec, cyrillique et arabe compris. Étant donné notre contexte multilingue, nous utilisons une représentation interne standard de chaque nom ainsi qu’une même mesure de similarité (au lieu d’adopter l’approche bilingue habituelle de la translittération). Ce module fait partie d’un outil plus général qui analyse en moyenne 15.000 articles de journaux chaque jour, afin de regrouper les documents similaires, aussi bien dans une même langue que dans des langues différentes.

Famous personal names and the right hemisphere: the link keeps missing

In this reply to the comment by VanLancker and Ohnesorge (2002), we present the case that current evidence supports the role of left hemisphere in the recognition of famous personal names. We argue that this conclusion is in line not only with the results of Schweinberger, Landgrebe, Mohr, and Kaufmann (2002), but also with the evidence from methods other than divided visual field studies (e.g., PET and ERP studies). We show that our view is also supported by a new set of experiments that address a major concern raised by VanLancker and Ohnesorge in their comment and discuss why the evidence they present does not provide conclusive support to their right hemisphere hypothesis. One of the several possible reasons for this failure is that famous name stimuli may be less suitable than personally familiar stimuli to elicit personally relevant, affective aspects of recognition.

Personal Names and the Human Right Hemisphere: An Illusory Link?

Names are thought to be represented in the brain differently from common nouns. Although this idea is supported by both theoretical and empirical arguments, the brain areas that are relevant for the recognition of personal names—and in particular the extent of right hemisphere involvement—remain controversial. We investigated the hypothesis that, unlike common nouns, personal names are represented preferentially by the right hemisphere (D. Van Lancker, 1991; D. Van Lancker et al., 1991; C. Ohnesorge & D. Van Lancker, 1999). Participants performed lexical decisions to common nouns and pseudowords (Experiment 1) or familiarity decisions to personal names (Experiment 2), which were presented briefly to the left or right visual fields. Asymmetries were small or absent for both pseudowords and unfamiliar names. For familiar names, both reaction times and error rates revealed strong advantages for the right visual field/left hemisphere (RVF/LH), which were comparable to the asymmetries for nouns. Familiar personal names may be represented by brain systems that differ from those representing common nouns, but current evidence does not suggest a distinct contribution of the right hemisphere to these brain systems.

Neuropsychological Impairments in the Recognition of Faces, Voices, and Personal Names

In order to determine the dissociability of face, voice, and personal name recognition, we studied the performance of 36 brain-lesioned patients and 20 control subjects. Participants performed familiarity decisions for portraits, voice samples, and written names of celebrities and unfamiliar people. In those patients who displayed significant impairments in any of these tests, the specificity of these impairments was tested using corresponding object recognition tests (with pictures of objects, environmental sounds, or written common words as stimuli). The results showed that 58% of the patients were significantly impaired in at least one test of person recognition. Moreover, 28% of the patients showed impairments that appeared to be specific for people (i.e., performance was preserved in the corresponding object recognition test). Three patients showed a deficit that appeared to be confined to the recognition of familiar voices, a pattern that was not described previously. Results were generally consistent with the assumption that impairments in face, voice, and name recognition are dissociable from one another. In contrast, there was no clear evidence for a dissociability between deficits in face and voice naming. The results further suggest that (a) impairments in person recognition after brain lesions may be more common than was thought previously and (b) the patterns of impairment that were observed can be interpreted using current cognitive models of person recognition (Bruce & Young, 1986; Burton, Bruce, & Johnston, 1990).

Recognition of the familiar personal names: Event-related fMRI

Recognition of the familiar personal names: Event-related fMRI

Recognition of the familiar personal names: An event-related fMRI

Recognition of the familiar personal names: An event-related fMRI

Optimization of key character set for word recognition using genetic algorithm

In the context of word recognition, for a word set with high similarity between words, when using word matching based on key characters, a method is proposed for optimal selection of key characters so as to reduce the average number of candidate words while ensuring a high probability of success in the search for the right word. With the proposed method, the success probability of the word search and the average number of candidate words are calculated for all combinations of key characters, and the optimal combination is then selected. To implement this principle, a new method was developed to calculate the average number of candidate words. To make the proposed principle practicable in terms of computation requirements, a method for seeking an approximate solution using genetic algorithms was proposed. The validity of the proposed method was confirmed experimentally in the recognition of personal names written with katakana characters. © 1998 Scripta Technica. Syst Comp Jpn, 28(14): 33–40, 1997

Optimization of key character set for word recognition using genetic algorithm

In the context of word recognition, for a word set with high similarity between words, when using word matching based on key characters, a method is proposed for optimal selection of key characters so as to reduce the average number of candidate words while ensuring a high probability of success in the search for the right word. With the proposed method, the success probability of the word search and the average number of candidate words are calculated for all combinations of key characters, and the optimal combination is then selected. To implement this principle, a new method was developed to calculate the average number of candidate words. To make the proposed principle practicable in terms of computation requirements, a method for seeking an approximate solution using genetic algorithms was proposed. The validity of the proposed method was confirmed experimentally in the recognition of personal names written with katakana characters. © 1998 Scripta Technica. Syst Comp Jpn, 28(14): 33–40, 1997

Preserved recognition of familiar personal names in global aphasia

Preserved recognition of familiar personal names in global aphasia

Personal Name Recognition and Associative Priming in Patients with Unilateral Brain-Damage

This study investigated the performance of left- (LED) and right-brain-damaged (RBD) patients in recognizing personal names under different conditions of associative priming. Subjects performed speeded familiarity decisions for names of famous and unfamiliar persons, These target names were preceded by primes, either faces or names, which could be neutral, related (e.g. Gorbachev-Jelzin), or unrelated (e.g. Travolta-Carter), Overall impairments in name recognition were observed in both patient groups relative to controls but were more severe in LED than in RED patients, This suggests that, contrary to previous hypotheses, the recognition of personal names is more dependent on left hemisphere functioning. In controls and LED patients, associative priming effects did not differ significantly between face and name primes. In RED patients, however, associative priming from names was larger than priming from faces. This specificity of priming effects for names in RED patients was tentatively related to their impairments in face recognition.

Preserved recognition of familiar personal names in global aphasia

Recognition of proper and common nouns was compared in four patients diagnosed with global aphasia secondary to ischemic left-hemisphere infarction. For proper noun recognition, subjects matched the spoken or written name of a famous person to a photograph, and for common nouns, subjects were tested on standardized and special word recognition tests. As expected, common noun recognition was severely compromised in the aphasic patients. In contrast, familiar personal names, despite their greater length and complexity, were recognized equally well by aphasic and normal control subjects. The right hemisphere may mediate the ability to recognize personally familiar names, as it may be specialized for establishing personally relevant environmental stimuli.