Text Indexation with INTEX

Aiming at the problem that the visual SLAM algorithm is easily disturbed by complex environmental factors, resulting in poor closed-loop accuracy and real-time performance. An improved closed-loop detection algorithm based on a dynamic increase or decrease mechanism is proposed. The algorithm can dynamically increase or decrease the number of words in the visual bag of words in real time according to the complexity of the scene; and optimize the selected keyframes through a double-threshold keyframe selection strategy to reduce the redundancy of keyframes, thus improving the system's real-time performance. The algorithm in this paper can achieve localization and position correction in complex environments. Test results in public datasets and real scenes demonstrate the advantages of the proposed algorithm in terms of accuracy, real-time performance, and adaptability to the environment.

The increasing demand for real-time language translation in multilingual societies highlights the need for efficient speech translation systems. This research proposes the development of an English-to-Marathi speech translation framework leveraging a dictionary-based dataset to enhance linguistic accuracy and contextual understanding. Marathi, being a morphologically rich language with unique syntactic and semantic structures, poses significant challenges when paired with English, a structurally divergent language. The proposed system will integrate automatic speech recognition (ASR), machine translation (MT), and text-to-speech synthesis (TTS) to achieve seamless speech-to-speech conversion. A dictionary-based dataset will serve as the foundation, enriched with linguistic rules and context-aware mappings to address lexical and syntactic divergences. By incorporating rule-based techniques alongside advanced neural network models, such as sequence-to- sequence transformers and attention mechanisms, the system aims to capture the nuances of Marathi grammar, idiomatic expressions, and gendered verb forms. The hybrid approach will ensure both robustness and adaptability across diverse linguistic inputs. The research will evaluate translation accuracy, fluency, and contextual relevance using metrics such as BLEU and TER. This study aspires to contribute to the growing field of low-resource language translation by enabling effective communication between English and Marathi speakers, thus fostering inclusivity in education, commerce, and digital communication. In the proposed research work the focus will be given to translation of English language video to Marathi language. Considering the strong grammar and variety of word dictionaries of the Marathi language, a strong algorithm based on deep learning techniques is required. Speech to Speech machine translation using deep learning focuses on the language conversion from English to Marathi which allows for seamless communication between people who speak Marathi languages. Speech-to speech translation solves this problem by translating spoken words in real time, allowing people who speak Marathi languages to communicate with one another.

Time resolved imaging techniques, such as MEG and EEG, are unique in their ability to reveal the rich dynamic spatiotemporal patterning of neural activities. Here we propose a technique based on spatiotemporal searchlight Representational Similarity Analysis (RSA) of combined MEG and EEG (EMEG) data to directly analyze the multivariate pattern of information flow across the brain. This novel technique can recognize fine-grained dynamic neural computations both in space and in time. A prime example of such neural computations is our ability to understand spoken words in real time. A computational approach to these processes is suggested by the Cohort Model of spoken-word recognition. Here we show how spatiotemporal searchlight RSA applied to source estimations of EMEG data can provide insights into the neural correlates of the cohort model within bilateral front temporal brain regions.

A new single-chip microprocessor for speech recognition, the SRP, has been developed, utilizing a multiprocessor architecture and a pipelined structure. It can recognize up to 340 isolated words or 40 connected words in real time. The SRP contains a vector distance calculator, a DP-equation calculator, and an I/O controller operating in a pipelined manner. Algorithm variations and operation parameters are user programmable, and the total size of the SRP program for a typical speech recognition system is about 700 words. The device has been fabricated with n-channel Si-gate E/D MOS technology with 2.5 μm design rules and employs 7296 three-transistor dynamic RAM cells for a total of more than 40 000 transistors.

A foundational assumption of human communication is that speakers should say as much as necessary, but no more. Yet, people routinely produce redundant adjectives and their propensity to do so varies cross-linguistically. Here, we propose a computational theory, whereby speakers create referential expressions designed to facilitate listeners' reference resolution, as they process words in real time. We present a computational model of our account, the Incremental Collaborative Efficiency (ICE) model, which generates referential expressions by considering listeners' real-time incremental processing and reference identification. We apply the ICE framework to physical reference, showing that listeners construct expressions designed to minimize listeners' expected visual search effort during online language processing. Our model captures a number of known effects in the literature, including cross-linguistic differences in speakers' propensity to over-specify. Moreover, the ICE model predicts graded acceptability judgments with quantitative accuracy, systematically outperforming an alternative, brevity-based model. Our findings suggest that physical reference production is best understood as driven by a collaborative goal to help the listener identify the intended referent, rather than by an egocentric effort to minimize utterance length. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Korean language has different structural properties which are controlled by semantic constraints of verbs. Also, most of Korean sentences are complex sentences which consisted of main clause and embedded clause. Therefore it is difficult to describe appropriate syntactic grammar or constraint for the Korean language and the Korean parsing causes various syntactic ambiguities. In this paper, we suggest how to describe CFG-based grammar using sentence patterns as syntactic constraint and solve syntactic ambiguities. To solve this, we classified 44 sentence patterns including complex sentences which have subordinate clause in Korean sentences and used it to reduce syntactic ambiguity. However, it is difficult to solve every syntactic ambiguity using the information of sentence patterns. So, we used semantic markers with semantic constraint. Semantic markers can be used to solve ambiguity by auxiliary particle or comitative case particle.

In this paper we will show how Italian electronic dictionaries have been built within the methodological framework of Lexicon-grammar. We will see the structure of electronic dictionaries of simple and compound words, and we will show how to analyse texts employing these linguistic tools within INTEX, a morphological analyser. INTEX contains a tool which allows to construct local grammars on the model of finite state automata. These grammars can be based not only on words but also on the non-terminal symbols contained in the dictionaries. Finally, we will show how electronic grammars (built with INTEX) interact with dictionaries and allow recognition of sequences of simple and compound words.

In this paper, we introduce the Chinese FrameNet project which is creating a FrameNet style lexicon for Chinese, based on the principles of frame semantics, in which lexical units are described in the frames evoked by them with other constituents which express the participants (frame elements) in these frames. Our lexicon also contains detailed information about the possible syntactic realizations of frame elements, derived from annotated corpus examples. Chinese and English lexical units that involve describing events of cognition are compared and differences between the lexicalization patterns and syntactic realization patterns in both languages are described. Finally, we suggest that the existing descriptions of English language based frames can be used to describe the conceptual structures of Chinese lexicon, but the frame membership (lexical units) and syntactic realization patterns must be determined in terms of Chinese syntactic and semantic properties.

The intex lexical parser processes linguistic units of four formal types: morphemes, simple words, compound words and frozen expressions. Frozen expressions are units spelled in the form of non-contiguous sequences of tokens (eg. take ... into account), and their recognition requires computation traditionally performed by syntactic parsers. Over 30,000 French frozen expressions have been described in the tables Cxx of the lexicon-grammar. We show how to use these tables to automatically construct FSTs that are capable of recognizing and tagging frozen expressions in texts. Representing the result as tags poses some formal problems that we discuss.

Language is an important mean of communication and it is constantly changing. During the language change a lot of words become out of use and many other new words become part of lexicon . The lexicon of the language is constantly enlarging and one important way to enlarge a language is by word formation. In German and Albanian Languages word formation is defined as a process of forming new words. In both, German and Albanian Languages an important contribution in word formation is given by compounding. In German Language compound words make up 2/3 of lexical language. The dominant part of compound words is the formation of compound nouns. German Language has got a lot of compound nouns so it has the ability to create new compounds between the connection of nouns or the connection of a noun with the other parts of discourse. In most cases the compounds of German Language find their equivalent in Albanian Language in simple words or phrases. In both languages a compound noun consists of two or more (lexical parts) components; they can have subordinate and coordinate relations. The majority of compounds is done by coordinate relations (determinate compositions). The composition components have a strict word order. If the word order changes in German Language, the meaning of composition will change, it will take a new meaning. (Of course there are exceptions in a few cases). If the word order changes in Albanian Language, the word becomes meaningless. In Albanian language the components of a compound noun are connected without fugues. Compound nouns with connecting vowels (o / a) are very few, while in German linking elements (fugues : e-, -s-, -es-, -n-, -en-, -er-, -ens-, -o-, ) are typical.

A linguistic method for using the Web consists in making requests on strings of characters as long as possible between quotation marks, then confronting the obtained results with other sources. One knows that the Web is “transitory” and is “varying greatly in value”; nonetheless using this method will be efficient. Useful requests are made through classes of objects and sets of predicates (Gross & Guenthner 2002). Comparing frequencies is a good means of evaluating the respective vitality of concurrent terminological phrases and their social uses (official, technical, professional or journalistic texts). So neologisms and archaisms become obvious. If terminology ’s aim is to work on specialized names, professional contents and linguistic knowledge about terms, the Web is a very good tool to validate technical translations, provided philological precautions.

The World Wide Web includes semantic relations of numerous types that exist among different entities. Extracting the relations that exist between two entities is an important step in various Web-related tasks such as information retrieval (IR), information extraction, and social network extraction. A supervised relation extraction system that is trained to extract a particular relation type (source relation) might not accurately extract a new type of a relation (target relation) for which it has not been trained. However, it is costly to create training data manually for every new relation type that one might want to extract. We propose a method to adapt an existing relation extraction system to extract new relation types with minimum supervision. Our proposed method comprises two stages: learning a lower dimensional projection between different relations, and learning a relational classifier for the target relation type with instance sampling. First, to represent a semantic relation that exists between two entities, we extract lexical and syntactic patterns from contexts in which those two entities co-occur. Then, we construct a bipartite graph between relation-specific (RS) and relation-independent (RI) patterns. Spectral clustering is performed on the bipartite graph to compute a lower dimensional projection. Second, we train a classifier for the target relation type using a small number of labeled instances. To account for the lack of target relation training instances, we present a one-sided under sampling method. We evaluate the proposed method using a data set that contains 2,000 instances for 20 different relation types. Our experimental results show that the proposed method achieves a statistically significant macroaverage F-score of 62.77. Moreover, the proposed method outperforms numerous baselines and a previously proposed weakly supervised relation extraction method.

User Generated Categories (UGCs) are short but informative phrases that reflect how people describe and organize entities. UGCs express semantic relations among entities implicitly hence serve as a rich data source for knowledge harvesting. However, most UGC relation extraction methods focus on English and heavily rely on lexical and syntactic patterns. Applying them directly to Chinese UGCs poses significant challenges because Chinese is an analytic language with flexible language expressions. In this paper, we aim at harvesting fine-grained relations from Chinese UGCs automatically. Based on neural networks and negative sampling, we introduce two word embedding projection models to identify is-a relations. The accuracy of prediction results is improved via a collective refinement algorithm and a hypernym expansion method. We further propose a graph clique mining algorithm to harvest non-taxonomic relations from UGCs, together with their textual patterns. Two experiments are conducted to validate our approach based on Chinese Wikipedia. The first experiment verifies the is-a relation extraction approach achieves high accuracy, outperforming state-of-the-art methods. The second experiment shows that the proposed method can harvest non-taxonomic relations of large quantity and high accuracy, with minimal human intervention.

The empirical study of syntactic, stylistic, and lexical patterns through corpora has frequently revealed a tendency towards standardisation, as Toury (1995/2012) defines it, in translated texts. In this vein, some studies have found that diatopy tends to become blurred in translations, particularly into transnational languages. In the case of Spanish, it has been stated that the enormous geographical richness of the language is not really reflected in translated Spanish. This paper argues that the translation of the work Rootless by Chris Howard into Colombian Spanish exhibits traits more typical of the European Spanish than of the Colombian Spanish variety. For this purpose, diatopic distribution of verb + noun (object) collocations extracted from a parallel corpus and a monolingual corpus of Rootless and its translations published in Colombian and European Spanish, is examined in a reference Spanish corpus.
 Keywords: parallel corpus; translated Spanish; Colombian Spanish; standardisation in translation; diatopic variation

The work discusses a connectionist approach to the construction of syntactic and semantic represenations. The need to handle symbol processing and heuristic search to process natural language in real time, has prompted the, search for an alternative approach to tackle these issues. This has led to the cycle-intensive approach using a large number of very simple processors to get around the limitations of conventional symbolic processing. The system described in this work uses a sort and scan approach to assign lexical details to words. During the training phase of the syntactic module an incremental learning method to establish weak connections to represent the syntax of the connections to represent the syntax of the natural language by exposing the system to example syntactic constituent patterns and sentence patterns. A bottom-up parsing strategy is used to progressively fire word nodes, syntactic constituent nodes, using a marker propagation and constraint decision technique to maintain the relative ordering. The approacli creates a distributed representation of the parse tree and allows selective retrieval of parts of the structure. The semantic representation phase also works from the word nodes and utilizes projection rules to propagate markers and establish semantic connections after satisfying the semantic selectional restrictions imposed by the semantic descriptions. This marker propagation continues until a semantic structure has been associated with the sentence node.