Word Disambiguation Research Articles

Adjusting listening effort relative to expected value of listening

Listening effort is a commonly reported difficulty among those who have hearing loss. A person’s ability to engage or disengage mental resources at strategic times could be an important signature of a person’s capacity to guard against wasted effort. This experiment gave listeners an opportunity to voluntarily reduce effort at specific moments based on the expected value of the incoming signal. First, sentences presented in the clear were immediately repeated, inviting reduced attention to the first presentation. In a second condition, the immediate repetition was randomly dropped on some trials, inviting increased vigilance to the first presentation. In a third condition, the first sentence was presented with degraded quality, inviting increased attention to the repetition to disambiguate misperceived words. Pupillometry was used as an index of moment-to-moment changes in listening effort. Data showed elevated pupil dilations linked in time with the disambiguated words and diminished pupil size specifically when there was less value in attending to the signal. These results support the need to expand the concept of listening effort beyond a “more” or “less” framework, toward a framework of efficiency.

Regionally specific cortical lateralization of abstract and concrete verb processing: Magnetic mismatch negativity study

The neural underpinnings of processing concrete and abstract semantics remain poorly understood. Previous fMRI studies have shown that multimodal and amodal neural networks respond differentially to different semantic types; importantly, abstract semantics activates more left-lateralized networks, as opposed to more bilateral activity for concrete words. Due to the lack of temporal resolution, these fMRI results do not allow to easily separate language- and task-specific brain responses and to disentangle early processing stages from later post-comprehension phenomena. To tackle this, we used magnetoencephalography (MEG), a time-resolved neuroimaging technique, in combination with a task-free oddball mismatch negativity (MMN) paradigm, an established approach to tracking early automatic activation of word-specific memory traces in the brain. We recorded the magnetic MMN responses in 30 healthy adults to auditorily presented abstract and concrete action verbs to assess lateralization of word-specific lexico-semantic processing in a set of neocortical areas. We found that MMN responses to these stimuli showed different lateralization patterns of activity in the upper limb motor area (BA4) and parts of Broca's area (BA45/BA47) within ∼100–350 ms after the word disambiguation point. Importantly, the greater leftward response lateralization for abstract semantics was due to the lesser involvement of the right-hemispheric homologues, not increased left-hemispheric activity. These findings suggest differential region-specific involvement of bilateral sensorimotor systems already in the early automatic stages of processing abstract and concrete action semantics.

EnhancedBERT: A feature-rich ensemble model for Arabic word sense disambiguation with statistical analysis and optimized data collection

Accurate assignment of meaning to a word based on its context, known as Word Sense Disambiguation (WSD), remains challenging across languages. Extensive research aims to develop automated methods for determining word senses in different contexts. However, the literature lacks the presence of datasets generated for the Arabic language WSD. This paper presents a dataset comprising a hundred polysemous Arabic words. Each word in the dataset encompasses 3–8 distinct senses, with ten example sentences per sense. Some statistical operations are conducted to gain insights into the dataset, enlightening its characteristics and properties. Subsequently, a novel WSD approach is proposed to utilize similarity measures and find the overlap between contextual information and dictionary definitions. The proposed method uses the power of BERT, a pre-trained language model, to enable effective Arabic word disambiguation. In training, new features are integrated to improve the model's ability to differentiate between various senses of words. The proposed BERT models are combined to compose an ensemble model architecture to improve the classification performances. The performance of the WSD system outperforms state-of-the-art systems, achieving an approximate F1-score of 96 %. Statistical analyses are performed to evaluate the overall performance of the WSD approach by providing additional information on model predictions. A case study was implemented to test the effectiveness of WSD in sentiment analysis, a downstream task.

DomainNet: Homograph Detection and Understanding in Data Lake Disambiguation

Modern data lakes are heterogeneous in the vocabulary that is used to describe data. We study a problem of disambiguation in data lakes: How can we determine if a data value occurring more than once in the lake has different meanings and is therefore a homograph? While word and entity disambiguation have been well studied in computational linguistics, data management, and data science, we show that data lakes provide a new opportunity for disambiguation of data values, because tables implicitly define a massive network of interconnected values. We introduce DomainNet , which efficiently represents this network, and investigate to what extent it can be used to disambiguate values without requiring any supervision. DomainNet leverages network-centrality measures on a bipartite graph whose nodes represent data values and attributes to determine if a value is a homograph. A thorough experimental evaluation demonstrates that state-of-the-art techniques in domain discovery cannot be re-purposed to compete with our method. Specifically, using a domain discovery method to identify homographs achieves an F1-score of 0.38 versus 0.69 for DomainNet , which separates homographs well from data values that have a unique meaning. On a real data lake, our top-100 precision is 93%. Given a homograph, we also present a novel method for determining the number of meanings of the homograph and for assigning its data lake attributes to a meaning. We show the influence of homographs on two downstream tasks: entity-matching and domain discovery.

The role of syntactic cues in monolingual and bilingual two-year-olds’ novel word disambiguation

Although linguistic and nonlinguistic cues help young children infer meaning when presented with unfamiliar words, little is known about how syntactic information and early bilingual experience shape word learning. This study examined how monolingual and bilingual 24- to 30-month-olds’ disambiguation of novel words during a mutual exclusivity task differs as a function of syntactic cues, age, and productive vocabulary. English monolinguals and Spanish-English bilinguals were presented with familiar and novel objects within a syntactic context (e.g., “Give me the blick!”) or in isolation (e.g., “Blick!”). Results showed that monolinguals and bilinguals adhered to mutual exclusivity more often when provided with syntactic cues than when those cues were absent. Furthermore, bilinguals’ mutually exclusive disambiguation of novel words increased with age, but only when syntactic cues were available. These results provide insight into factors that influence children’s disambiguation of novel words. The theoretical implications of these findings are discussed.

Sentiment Analysis of Chinese E-Commerce Product Reviews Using ERNIE Word Embedding and Attention Mechanism

The development of e-commerce has ushered in a golden age. E-commerce product reviews are remarks initiated by online shopping users to evaluate the quality and service of the products they purchase; these reviews help consumers learn the reality of the product. The sentiment polarity of e-commerce product reviews is the best way to obtain customer feedback on products. Therefore, sentiment analysis of product reviews on e-commerce platforms is greatly significant. However, the challenges of sentiment analysis of Chinese e-commerce product reviews lie in dimension mapping, disambiguation of sentiment words, and polysemy of Chinese words. To solve the above problems, this paper proposes a sentiment analysis model ERNIE-BiLSTM-Att (EBLA). Here, the dynamic word vector generated using the Enhanced Representation through Knowledge Integration (ERNIE) word embedding model is input into the Bidirectional Long Short-term Memory (BiLSTM) to extract text features. Then, the Attention Mechanism (Att) is used to optimize the weight of the hidden layer. Finally, softmax is used as the output layer for sentiment classification. The experimental results on the JD.com Chinese e-commerce product review dataset show that the proposed model achieves more than 0.87 in precision, recall, and F1 values, which is superior to classic deep learning models proposed by other researchers; it has strong practicability in sentiment analysis of Chinese e-commerce product reviews.

Construction Grammar Conceptual Network: Coordination-based graph method for semantic association analysis

AbstractIn this article, we present the Construction Grammar Conceptual Network method, developed for identifying lexical similarity and word sense discrimination in a syntactically tagged corpus, based on the cognitive linguistic assumption that coordination construction instantiates conceptual relatedness. This graph analysis method projects a semantic value onto a given coordinated syntactic dependency and constructs a second-order lexical network of lexical collocates with a high co-occurrence measure. The subsequent process of clustering and pruning the graph reveals lexical communities with high conceptual similarity, which are interpreted as associated senses of the source lexeme. We demonstrate the theory and its application to the task of identifying the conceptual structure and different meanings of nouns, adjectives and verbs using examples from different corpora, and explain the modulating effects of linguistic and graph parameters. This graph approach is based on syntactic dependency processing and can be used as a complementary method to other contemporary natural language processing resources to enrich semantic tasks such as word disambiguation, domain relatedness, sense structure, identification of synonymy, metonymy, and metaphoricity, as well as to automate comprehensive meta-reasoning about languages and identify cross/intra-cultural discourse variations of prototypical conceptualization patterns and knowledge representations. As a contribution, we provide a web-based app at http://emocnet.uniri.hr/.

Nonverbal Action Interpretation Guides Novel Word Disambiguation in 12-Month-Olds.

Whether young infants can exploit sociopragmatic information to interpret new words is a matter of debate. Based on findings and theories from the action interpretation literature, we hypothesized that 12-month-olds should distinguish communicative object-directed actions expressing reference from instrumental object-directed actions indicative of one's goals, and selectively use the former to identify referents of novel linguistic expressions. This hypothesis was tested across four eye-tracking experiments. Infants watched pairs of unfamiliar objects, one of which was first targeted by either a communicative action (e.g., pointing) or an instrumental action (e.g., grasping) and then labeled with a novel word. As predicted, infants fast-mapped the novel words onto the targeted objects after pointing (Experiments 1 and 4) but not after grasping (Experiment 2) unless the grasping action was preceded by an ostensive signal (Experiment 3). Moreover, whenever infants mapped a novel word onto the object indicated by a communicative action, they tended to map a different novel word onto the distractor object, displaying a mutual exclusivity effect. This reliance on nonverbal action interpretation in the disambiguation of novel words indicates that sociopragmatic inferences about reference likely supplement associative and statistical learning mechanisms from the outset of word learning.

Semantic graph for word disambiguation in machine translation

Semantic graph for word disambiguation in machine translation

Children's disambiguation of novel words varies by the number and position of phonological contrasts.

Young children often make pragmatic assumptions when learning new words. For example, they assume that a speaker who uses different words intends to refer to different things - the so-called principle of contrast. We used a standard disambiguation task to explore whether children's assumptions about contrast depend on how much words differ. Three- to 6-year-olds heard pairs of words that differed in terms of the number, position, and types of phonological contrasts. Results indicate that children were less likely to disambiguate words differing by one phoneme than words differing by two or more phonemes, particularly when those one-phoneme differences were located at the beginning or end of the words (as in fim/vim). Overall, the findings suggest that children's pragmatic assumptions about two contrasting words depend not only on if words differ, but also on how they differ.

ADCSA-WSD: Adapted Discrete Crow Search Algorithm for Word Sense Disambiguation

In the field of natural language processing, the semantic disambiguation of words is beneficial to several applications, which helps us to identify the correct meaning of a word or a sequence of words according to the given context. It can be formulated as a combinatorial optimization problem where the goal is to find the set of meanings that contribute to improving the semantic relationship between target words. The Crow Search Algorithm (CSA) is a nature-inspired algorithm. It mimics the food foraging behavior of crow birds and their social interaction. CSA can deal with both continuous and discrete optimization problems. In this paper, the Word Sense Disambiguation (WSD) is modelled as a combinatorial optimization problem that is by nature a discrete problem. For this propose the discrete version of CSA has been adapted for solving the WSD problem and a DCSA-based WSD approach is proposed and called ADCSA-WSD. The proposed approach has been evaluated and compared with state-of-the-art approaches using three well-known benchmark datasets (SemCor 3.0, SensEval-02, SensEval-03). Experimental results show that ADCSA-WSD approach is performing better than other approaches.

Meaningful Translation and Transliteration for Marathi Language

Meaningful translation and transliteration is NP problem in case of languages like Marathi language as there are so many word disambiguation and multiple use and meaning of single word in different context is available. That is why identifying correct informational need and translating text into meaningful information is a tedious and error prone task. Google translate works on machine neuron network and WorldNet is an online reference system works on psycholinguistic theory of human memory. Both approaches are promising tools for language translation. Complete translation of Marathi text to English or English to Marathi also having problem of more complicated meaningless or tedious translation. Proposed algorithm is taking into consideration meaningful translation or transliteration as per user’s informational need. This novel approach consider machine neuron network for meaningful formation of translated sentence and morphological structure for correct translation of word based on ontological analysis of word.

Is 2-year-old children's referential disambiguation of a novel word primarily aimed at identifying the word meaning or at understanding their communicative partner?

During everyday conversations, young children are often challenged with the task of correctly identifying the referent of novel words. What is their primary aim when they try to do so? We propose that by being motivated to successfully participate in communicative interactions, children primarily aim at comprehending what the speaker intends to mean in the specific communicative context, rather than understanding what the word conventionally means. This proposal suggests that in the absence of clear referential cues, when referential disambiguation could be guided only by two distinct factors-the novelty of possible referents or the context in which the labeling occurs-children will rather rely on the pragmatic cues of the situation than on the novelty of the objects. To investigate this hypothesis, we tested 132 two-year-old Hungarian children (67 girls and 65 boys) in a referential disambiguation paradigm. Confirming our prediction, children identified the referent by inferring the intended meaning of the speaker, and not by relying on the novelty of the objects. Thus, when pragmatic cues are provided, children primarily rely on these cues to understand the intended meaning of the speaker. We suggest that this inference to the intended meaning of the speaker might serve most of the times as the input of children's word acquisition processes. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Lexical Sense Labeling and Sentiment Potential Analysis Using Corpus-Based Dependency Graph

This paper describes a graph method for labeling word senses and identifying lexical sentiment potential by integrating the corpus-based syntactic-semantic dependency graph layer, lexical semantic and sentiment dictionaries. The method, implemented as ConGraCNet application on different languages and corpora, projects a semantic function onto a particular syntactical dependency layer and constructs a seed lexeme graph with collocates of high conceptual similarity. The seed lexeme graph is clustered into subgraphs that reveal the polysemous semantic nature of a lexeme in a corpus. The construction of the WordNet hypernym graph provides a set of synset labels that generalize the senses for each lexical cluster. By integrating sentiment dictionaries, we introduce graph propagation methods for sentiment analysis. Original dictionary sentiment values are integrated into ConGraCNet lexical graph to compute sentiment values of node lexemes and lexical clusters, and identify the sentiment potential of lexemes with respect to a corpus. The method can be used to resolve sparseness of sentiment dictionaries and enrich the sentiment evaluation of lexical structures in sentiment dictionaries by revealing the relative sentiment potential of polysemous lexemes with respect to a specific corpus. The proposed approach has the potential to be used as a complementary method to other NLP resources and tasks, including word disambiguation, domain relatedness, sense structure, metaphoricity, as well as a cross- and intra-cultural discourse variations of prototypical conceptualization patterns and knowledge representations.

Twelve-month-olds disambiguate new words using mutual-exclusivity inferences

Representing objects in terms of their kinds enables inferences based on the long-term knowledge made available through kind concepts. For example, children readily use lexical knowledge linked to familiar kind concepts to disambiguate new words (e.g., “find the toma”): they exclude members of familiar kinds falling under familiar kind labels (e.g., a ball) as potential referents and link new labels to available unfamiliar objects (e.g., a funnel), a phenomenon dubbed as ‘mutual exclusivity’. Younger infants' failure in mutual exclusivity tasks has been commonly interpreted as a limitation of early word-learning or inferential abilities. Here, we investigated an alternative explanation, according to which infants do not spontaneously represent familiar objects under kind concepts, hence lacking access to the information necessary for rejecting them as referents of novel labels. Building on findings about conceptual development and communication, we hypothesized that nonverbal communication could prompt infants to set up kind-based representations which, in turn, would promote mutual exclusivity inferences. This hypothesis was tested in a looking-while-listening task involving novel word disambiguation. Twelve-month-olds saw pairs of objects, one familiar and one unfamiliar, and heard familiar kind labels or novel words. Across two experiments providing a cross-lab replication in two different languages, infants successfully disambiguated novel words when the familiar object had been pointed at before labeling, but not when it had been highlighted in a non-communicative manner (Experiment 1) or not highlighted at all (Experiment 2). Nonverbal communication induced infants to recruit kind-based representations of familiar objects that they failed to recruit in its absence and that, once activated, supported mutual-exclusivity inferences. Developmental changes in children's appreciation of communicative contexts may modulate the expression of early inferential and word learning competences.

In search of a suitable method for disambiguation of word senses in Bengali

The paper presents a study on word sense disambiguation (WSD) in Bengali, one of the less resourced Indian languages. The overall work is carried out in two sequential phases. In the first phase, four well-known approaches, which are often applied for sense disambiguation of words, are studied using the traditional methods. In the course of application, suitable modifications are made as well as implemented for eliciting desired results. In the second stage, a combined approach is proposed based on the results obtained from initial experiments. Within ‘supervised module’ the four commonly used methods, namely, the Decision Tree (DT) method, Support Vector Machine (SVM) method, Artificial Neural Network (ANN) method, and the Naive Bayes (NB) method are used at the baseline for the purpose of classification of senses. These baseline strategies produced 63.84%, 76.9%, 76.23%, and 80.23% accurate results, respectively, when these methods are tested on 13 mostly used Bengali ambiguous words retrieved from a Bengali text corpus. Next, two major modifications are applied on these baseline strategies to increase the level of accuracy: (a) incorporation of Lemmatization process in the system (that produces 68.30%, 79%, 78.23%, and 82.30% accurate results, respectively), and (b) operation of Bootstrapping on the systems (including lemmatization feature), which produces 70.92%, 79.15%, 79.53%, and 83% accuracy, respectively. Next, in a knowledge-based method, the traditional Lesk algorithm is implemented at the baseline which produces 31% accurate result in sense disambiguation. This strategy is further modified by Context Expansion (CE) method in the sentences using the Bengali WordNet to produce 75% accuracy. Within ‘unsupervised module’, the baseline strategy produced a 36.2% accurate result in sense disambiguation task. To enhance the level of performance, two modifications are adopted over this baseline strategy: (a) Principal Component Analysis (PCA) over the feature vector, which produces 51.2% accuracy in WSD task, and (b) Context Expansion of the sentences using the Bengali WordNet with PCA, which produces 61% accuracy in sense disambiguation task. Finally, a combined approach is adopted after considering all the effective aspects of the three methods, and it produces the highest level accuracy (92%) in the task of sense disambiguation.

Cadres, scripts, registres — complexité de traduction des mots polysémiques

The article deals with issues related to the description of polysemic units for supervised automatic translation of texts from French to Polish based on the object-oriented method by W. Banyś (AOO). Applying to the description additional tools allowing for the disambiguation — frames, scripts and register analysis — the author focuses on presenting the complexity of the description of lexical units. It should be stressed that the decision to assign meanings of such words one or another equivalents in the target language is determined by the criterion of preference. Some of the meanings of the word are easy to describe in such a way that the program can make a correct translation into the target language with a high degree of probability. However, there are often such meanings whose description is much more complex. The closer the meanings of the disambiguated words in the original and target language and the more similar the communication situation in which they are used, the more difficult it is to clearly indicate the boundaries between the meanings. In such cases, there is a much greater range of preferential character of the translation, which we have to adopt The French noun conjunction (f), chosen for analysis, reflects this phenomenon very well.

Numerical Simulation of Ambiguity Resolution in Multiple Information Streams Based on Network Machine Translation

In natural language, the phenomenon of polysemy is widespread, which makes it very difficult for machines to process natural language. Word sense disambiguation is a key issue in the field of natural language processing. This paper introduces the more common statistical learning methods used in the field of word sense disambiguation. Using the naive Bayesian machine learning method and the feature vector set extracted and constructed by the Dice coefficient method, a semantic word disambiguation model based on semantics is realized. The results of comparative experiments show that the proposed method is better compared with known systems. This paper proposes a method for disambiguation of word segmentation in professional fields based on unsupervised learning. This method does not rely on professional domain knowledge and training corpus and only uses the frequency, mutual information, and boundary entropy information of the string in the test corpus to solve the problem of word segmentation ambiguity. The experimental results show that these three evaluation standards can solve the problem of word segmentation ambiguity in professional fields and improve the effect of word segmentation. Among them, the segmentation result using mutual information is the best, and the performance is stable.

Image Enhanced Event Detection in News Articles

Event detection is a crucial and challenging sub-task of event extraction, which suffers from a severe ambiguity issue of trigger words. Existing works mainly focus on using textual context information, while there naturally exist many images accompanied by news articles that are yet to be explored. We believe that images not only reflect the core events of the text, but are also helpful for the disambiguation of trigger words. In this paper, we first contribute an image dataset supplement to ED benchmarks (i.e., ACE2005) for training and evaluation. We then propose a novel Dual Recurrent Multimodal Model, DRMM, to conduct deep interactions between images and sentences for modality features aggregation. DRMM utilizes pre-trained BERT and ResNet to encode sentences and images, and employs an alternating dual attention to select informative features for mutual enhancements. Our superior performance compared to six state-of-art baselines as well as further ablation studies demonstrate the significance of image modality and effectiveness of the proposed architecture. The code and image dataset are avaliable at https://github.com/shuaiwa16/image-enhanced-event-extraction.

An Efficient Approach for Measuring Semantic Similarity Combining WordNet and Wikipedia

The measurement of semantic similarity between concepts is an important research topic in natural language processing. In the past, several approaches for measuring the semantic similarity between concepts have been proposed based on WordNet or Wikipedia. However, improvements in the measurement accuracy of most methods have led to a dramatic increase in time complexity, and the existing methods do not effectively integrate WordNet and Wikipedia. In this paper, we focus on designing an efficient semantic similarity method based on WordNet and Wikipedia. To improve the accuracy of WordNet edge-based measures, we propose an edge weight model for combining edge and density information, which assigns a weight to each edge adaptively based on the number of direct hyponyms of the subsumer. Second, to improve the computational efficiencies of the existing Wikipedia link vector-based measures, we propose a new Wikipedia link feature-based semantic similarity method that converts Wikipedia links into semantic knowledge and replaces the TF-IDF statistical weight model in the existing measures. In addition, we propose two new word disambiguation strategies to further improve the accuracy of Wikipedia link-based measures. Finally, to fully exploit the advantages of WordNet and Wikipedia, we propose two new aggregation schemas for combining WordNet “ is-a ” semantics and Wikipedia link semantics to replace the current aggregation schemas that combine WordNet “ is-a ” semantics with category semantics in Wikipedia. The experimental results show that our aggregation models are outstanding in terms of accuracy, efficiency and word coverage compared to state-of-the-art similarity measures.