Multiple Linguistic Features Research Articles

Automatic Extractive Text Summarization using Multiple Linguistic Features

Automatic text summarization (ATS) provides a summary of distinct categories of information using natural language processing (NLP). Low-resource languages like Hindi have restricted applications of these techniques. This study proposes a method for automatically generating summaries of Hindi documents using extractive technique. The approach retrieves pertinent sentences from the source documents by employing multiple linguistic features and machine learning (ML) using maximum likelihood estimation (MLE) and maximum entropy (ME). We conducted pre-processing on the input documents, such as eliminating Hindi stop words and stemming. We have obtained 15 linguistic feature scores from each document to identify the phrases with high scores for summary generation. We have performed experiments over BBC News articles, CNN News, DUC 2004, Hindi Text Short Summarization Corpus, Indian Language News Text Summarization Corpus, and Wikipedia Articles for the proposed text summarizer. The Hindi Text Short Summarization Corpus and Indian Language News Text Summarization Corpus datasets are in Hindi, whereas BBC News articles, CNN News, and the DUC 2004 datasets have been translated into Hindi using Google, Microsoft Bing, and Systran translators for experiments. The summarization results have been calculated and shown for Hindi as well as for English to compare the performance of a low and rich-resource language. Multiple ROUGE metrics, along with precision, recall, and F-measure, have been used for the evaluation, which shows the better performance of the proposed method with multiple ROUGE scores. We compare the proposed method with the supervised and unsupervised machine learning methodologies, including support vector machine (SVM), Naive Bayes (NB), decision tree (DT), latent semantic analysis (LSA), latent Dirichlet allocation (LDA), and K-means clustering, and it was found that the proposed method outperforms these methods.

Research on fault diagnosis of patient monitor based on text mining

The conventional fault diagnosis of patient monitors heavily relies on manual experience, resulting in low diagnostic efficiency and ineffective utilization of fault maintenance text data. To address these issues, this paper proposes an intelligent fault diagnosis method for patient monitors based on multi-feature text representation, improved bidirectional gate recurrent unit (BiGRU) and attention mechanism. Firstly, the fault text data was preprocessed, and the word vectors containing multiple linguistic features was generated by linguistically-motivated bidirectional encoder representation from Transformer. Then, the bidirectional fault features were extracted and weighted by the improved BiGRU and attention mechanism respectively. Finally, the weighted loss function is used to reduce the impact of class imbalance on the model. To validate the effectiveness of the proposed method, this paper uses the patient monitor fault dataset for verification, and the macro F1 value has achieved 91.11%. The results show that the model built in this study can realize the automatic classification of fault text, and may provide assistant decision support for the intelligent fault diagnosis of the patient monitor in the future.

Real-time computer vision-based gestures recognition system for bangla sign language using multiple linguistic features analysis

Real-time computer vision-based gestures recognition system for bangla sign language using multiple linguistic features analysis

Joint, distributed and hierarchically organized encoding of linguistic features in the human auditory cortex.

The precise role of the human auditory cortex in representing speech sounds and transforming them to meaning is not yet fully understood. Here we used intracranial recordings from the auditory cortex of neurosurgical patients as they listened to natural speech. We found an explicit, temporally ordered and anatomically distributed neural encoding of multiple linguistic features, including phonetic, prelexical phonotactics, word frequency, and lexical-phonological and lexical-semantic information. Grouping neural sites on the basis of their encoded linguistic features revealed a hierarchical pattern, with distinct representations of prelexical and postlexical features distributed across various auditory areas. While sites with longer response latencies and greater distance from the primary auditory cortex encoded higher-level linguistic features, the encoding of lower-level features was preserved and not discarded. Our study reveals a cumulative mapping of sound to meaning and provides empirical evidence for validating neurolinguistic and psycholinguistic models of spoken word recognition that preserve the acoustic variations in speech.

Ablation Study On Feature Group Importance For Automated Essay Scoring

Grading of written academic essays by humans requires significant effort. It is a time-consuming task and is vulnerable to human biases. Ever since the introduction of modern computing, this has been one of the many automations being explored. Researches in automated essay scoring have been on-going, where the majority of the researches in recent years are based on extracting multiple linguistic features and using them to build a classification model for automated essay scoring. The 3 main types of features used are lexical, grammatical, and semantic. In our work, we conducted an ablation study to discover the engineered features that has the weakest influence. We did this using a generic feature engineering and classification approach that was used by the winners of the Automated Student Assessment Prize (ASAP). This is to mitigate biases that may have addressed specific feature engineering or models. Our results show that a semantic feature called the prompt has been the weakest feature in influencing the models. From further investigations, this was due to it being over-fitted in the classification model.

An aggregate approach to diachronic variation in modern Chinese writings and translations

Abstract Modern Chinese took the place of classical Chinese and has been the standard form of writing since the early 1920s. While several studies have been carried out on diachronic variation in modern written Chinese, these include few aggregate investigations. This study examines the diachronic variation in modern Chinese writings and translations from the 1900s to the 2000s. Frequencies of multiple linguistic features sensitive to historical change were drawn from a multi-genre comparable corpus, ‘DCMCWT’, containing five periods: 1900–1911, 1919–1930, 1931–1949, 1950–1966, and 1978–2012. Hierarchical agglomerative clustering was employed for periodisation, while multidimensional scaling supplemented the developmental path. The results suggest that Chinese writings and translations fall into three broad periods: 1900–1911, 1919–1966, and 1978–2012. Chinese translations follow a similar evolutionary path as the writings, and the gap between them, narrowed from 1900 to 2012. This developmental path corresponds to the socio-historical backgrounds in Chinese history and shares similarities and differences with the development of English. Diachronic variation in early modern Chinese mirrors that of English in that both languages developed to be more colloquial and interactive. However, early modern Chinese is different from English, as diglossia has played a crucial evolutionary role.

Linguistic Portrait of Film Characters in Sci-Fi Movie "Chappie"

The paper features the way linguistic means represent character traits in modern films. The research was based on Neill Blomkamp’s sci-fi drama "Chappie" (2005). The research objective was to describe the phenomenon of multiple linguistic features that disclose the linguistic personality of film characters via their free speech. The author believes that the linguistic image of a film character includes categorization of entities aimed at solving creative tasks, which, in their turn, incorporate the genre, stylistic peculiarities, imagery, and emotivity. The method of continuous selection from a film script offered an ample exemplifying material, which underwent cognitive and stylistic analysis. Modern cinema uses genre stylization and imagery, e.g. children’s speech, parents’ speech, classroom language, streetwise discourse, etc. These features depend on the authenticity of a film character and the heuristic explanation of an unknown concept by means of metaphors. The linguistic image of a film character is formed within the genre-stylistic boundaries of the script, while imagery allows the characters to reach a consensus within the 120-minute chronotope.

Simultaneous Acquisition of Words and Syntax: Effects of Exposure Condition and Declarative Memory.

This study examined the simultaneous acquisition of vocabulary and grammar by adult learners and the role of exposure condition and declarative memory. Most experimental studies investigating the acquisition of artificial or natural languages focus on either vocabulary or grammar, but not both. However, a systematic investigation of the simultaneous learning of multiple linguistic features is important given that it mirrors language learning outside the lab. Native English speakers were exposed to an artificial language under either incidental or intentional exposure conditions. Participants had to learn both novel pseudowords and word order patterns while also processing stimulus sentences for meaning. The results showed that adult learners are able to rapidly acquire basic syntactic information of a novel language while processing the input for meaning (plausibility judgments) and attempting to learn novel vocabulary at the same time. The results further indicated that exposure condition (incidental versus intentional) made no difference in terms of either vocabulary or grammar learning gains. Findings also revealed that learners developed explicit, not implicit, knowledge of lexis and syntax. Finally, the results indicated that individuals’ declarative memory capacity was not related to vocabulary learning but only to grammar learning. Our study underscores the importance of studying the simultaneous acquisition of different language features and from different perspectives of comprehension versus production, incidental versus intentional learning conditions, implicit/explicit knowledge, and individual differences in cognitive abilities.

Variability and stability in native and non-native Japanese speech

The speech of second language learners is often characterized as more variable than the speech of native speakers (e.g., Baese-Berk and Morrill, 2015; Jongman and Wade, 2007; Jongman et al., 2007; Rogerset al., 2012). However, among the relatively few studies which have examined this question directly, the majority have focused on: learners of English, learners from one L1 background, and have examined one linguistic feature per study, leaving open the possibility that non-native speech may not be more variable than native speech in all cases. The present work examines the production of Japanese sentences by native Japanese speakers, and learners of Japanese from two language backgrounds (English and Chinese). Counter to previous results, we find several cases where non-native speakers are less variable than native speakers, including on various measures of vowel spectrum variability, and voiced stop realization. Thus, the relationship between variability and language background appears to be more complex than previously thought. Accurately characterizing variability across native and non-native speech has implications for models of second language acquisition, and speech perception. We suggest that future work on variability in non-native speech should examine factors such as speakers’ L1 and L2, and multiple linguistic features.

English

In this paper, a novel syllable duration modeling approach for Telugu speech is proposed. Duration of a syllable is influenced by positional and contextual variations of syllables. Multiple linguistic features of syllables at different levels like positional and contextual features are used from text. Duration values of syllables are extracted from speech analysis software PRAAT. Duration of a syllable is predicted by a Recurrent Neural Network (RNN) algorithm. A small speech database is considered as a preliminary work to predict syllable duration with proposed RNN algorithm. Experiments are conducted with different sets of features.

Natural language technology and query expansion: issues, state-of-the-art and perspectives

The availability of an abundance of knowledge sources has spurred a large amount of effort in the development and enhancement of Information Retrieval techniques. Users information needs are expressed in natural language and successful retrieval is very much dependent on the effective communication of the intended purpose. Natural language queries consist of multiple linguistic features which serve to represent the intended search goal. Linguistic characteristics that cause semantic ambiguity and misinterpretation of queries as well as additional factors such as the lack of familiarity with the search environment affect the users ability to accurately represent their information needs, coined by the concept intention gap. The latter directly affects the relevance of the returned search results which may not be to the users satisfaction and therefore is a major issue impacting the effectiveness of information retrieval systems. Central to our discussion is the identification of the significant constituents that characterize the query intent and their enrichment through the addition of meaningful terms, phrases or even latent representations, either manually or automatically to capture their intended meaning. Specifically, we discuss techniques to achieve the enrichment and in particular those utilizing the information gathered from statistical processing of term dependencies within a document corpus or from external knowledge sources such as ontologies. We lay down the anatomy of a generic linguistic based query expansion framework and propose its module-based decomposition, covering topical issues from query processing, information retrieval, computational linguistics and ontology engineering. For each of the modules we review state-of-the-art solutions in the literature categorized and analyzed under the light of the techniques used.

Identification of Soundbite and Its Speaker Name Using Transcripts of Broadcast News Speech

This article presents a pipeline framework for identifying soundbite and its speaker name from Mandarin broadcast news transcripts. Both of the two modules, soundbite segment detection and soundbite speaker name recognition, are based on a supervised classification approach using multiple linguistic features. We systematically evaluated performance for each module as well as the entire system, and investigated the effect of using speech recognition (ASR) output and automatic sentence segmentation. We found that both of the two components impact the pipeline system, with more degradation in the entire system performance due to automatic speaker name recognition errors than soundbite segment detection. In addition, our experimental results show that using ASR output degrades the system performance significantly, and that using automatic sentence segmentation greatly impacts soundbite detection, but has much less effect on speaker name recognition.

Semantic passage segmentation based on sentence topics for question answering

We propose a semantic passage segmentation method for a Question Answering (QA) system. We define a semantic passage as sentences grouped by semantic coherence, determined by the topic assigned to individual sentences. Topic assignments are done by a sentence classifier based on a statistical classification technique, Maximum Entropy (ME), combined with multiple linguistic features. We ran experiments to evaluate the proposed method and its impact on application tasks, passage retrieval and template-filling for question answering. The experimental result shows that our semantic passage retrieval method using topic matching is more useful than fixed length passage retrieval. With the template-filling task used for information extraction in the QA system, the value of the sentence topic assignment method was reinforced.

"I Read the Nikkei, Too": Crafting Positions of Authority and Masculinity in a Japanese Conversation

This article investigates how Japanese men use terms of address and sentence-final particles to create ongoing positions of superiority, seniority, and masculinity in their conversations. Data are drawn from conversations by all-male groups who are speakers of the Hanshinkan dialect of western Japan. An examination of real linguistic practices shows deft use of multiple linguistic features, including first-person pronouns, address terms, and sentence-final particles, to carve out particular identities vis-a-vis specific interlocutors. These forms and their subsequent stances are interpreted by other speakers in ways that indicate their access to larger discourses of ideological gender and hierarchy relations.

A corpus-based analysis of Involved aspects of student writing

Previous research on student writing in South Africa, particularly Black South African English (BSAE) speakers, tends to focus on differences between BSAE writing and Standard varieties of English, and to fail to notice similarities. There is also a trend to focus on multiple linguistic features, but usually in isolation, without attempting an analysis of features as coherent subsets or subsystems. This article adopts the multifunctional-multidimensional approach of Biber, examining a set of linguistic features that form a coherent set for the expression of involvement in different registers. The Tswana Learner English Corpus (TLEC) and the Louvain Corpus of Native English Student Essays (LOCNESS) are used for the analysis. Results indicate that the TLEC, compared to LOCNESS, is characterised by writing that is less formal and more colloquial; it exhibits more reduction phenomena typically associated with conversation; is less integrated and more fragmented in terms of information presentation; uses more general and potentially more ambiguous cohesive devices; and is more cautious and polite when claims are made. Using Correspondence Analysis, the comparison is extended to include five other registers from the original study by Biber (1988). The analysis indicates that the differences between the two student writing corpora are relatively slight in terms of this overall perspective. As a set, the TLEC and LOCNESS exhibit many similarities to academic writing, but the student writing differs in that it reveals also similarities with spoken registers, rather than other written registers.