Unsupervised Word Sense Disambiguation

This paper describes our participation in the Robust WSD Task within the CLEF 2008. The aim of this pilot task is exploring methods which can take profit of WSD information in order to improve the IR systems. In our approach we have used a passage based system jointly with a WordNet based expansion method for the collection documents and the queries using the two WSD systems runs provided by the organization. Furthermore we have experimented with two well known relevance feedback methods -LCA and PRF -, in order to figure out which is more suitable to take profit of the WSD query expansion based on Wordnet. Our best run has obtained a 4th place in the competition with a value of 0.4008 MAP. We conclude that LCA fits better than PRF to this task. And that our WSD expansion is useful for some query subsets. In future works we will study the features of the query subsets for which the performance of our system decreases.

Word sense disambiguation (WSD) is a problem to determine a word according to the context in which it occurs. There are plenty amount of works done in WSD for some languages such as English, but research work on Assamese WSD remains limited. It is a more exigent task because Assamese has an intrinsic complexity in its writing structure and ambiguity, such as syntactic, semantic, and anaphoric ambiguity levels. A novel unsupervised genetic word sense disambiguation algorithm is proposed in this paper. The algorithm first uses WordNet to extract all possible senses for a given ambiguous word, then a genetic algorithm is used taking Wu-Palmer’s similarity measure as the fitness function and calculating the similarity measure for all extracted senses. The winner sense which will have the highest score declared as the winner sense.

In natural language processing (NLP), word sense disambiguation (WSD) is defined as the task of assigning the appropriate meaning (sense) to a given word in a text or discourse. Natural language is ambiguous, so that many words can be interpreted in multiple ways depending on the context in which they occur. The computational identification of meaning for words in context is called word sense disambiguation (WSD). In this paper we will discuss about the ambiguity and some important measures to deal with ambiguous statements.

Distributional semantic methods to approximate word meaning with context vectors have been very successful empirically, and the last years have seen a surge of interest in their compositional extension to phrases and sentences. We present here a new model that, like those of Coecke et al. (2010) and Baroni and Zamparelli (2010), closely mimics the standard Montagovian semantic treatment of composition in distributional terms. However, our approach avoids a number of issues that have prevented the application of the earlier linguistically-motivated models to full-fledged, real-life sentences. We test the model on a variety of empirical tasks, showing that it consistently outperforms a set of competitive rivals.

The intelligent tutoring sytems (ITS) are generations of computer based educational sysems that supports the teaching and learning processes with the aim of helpping students to achieve maximum learning goals. A major advanage of these systems is that they can be implemented in all kinds of educational environments either in the normal school environments in the form of stand-alone applications or as programs that remotely deliever knowledge through computers over the internet. The underline idea behind building intelligent tutoring systems is to integrate modern technological advancements with artificial intelligence techniques in the field of education with a view to making the teaching and learning activities highly advanced and more effective. An important feature that enhance the effectiveness of the teaching and learning processes with the ITS is the ability of the system to adapt to each individual student based on his/her characteristics, through making observations on the student's activities while they interct with the system. This phenomenum for observing student's actions while interacting with the ITS in order to build their profiles is known as student modeling. The aim of this paper therefore, is to review the state of art in student modeling in an intelligent tutoring system.

Search engines are based on models to index documents, match queries and documents and rank documents. Research in Information Retrieval (IR) aims at defining these models and their parameters in order to optimize the results. Using benchmark collections, it has been shown that there is not a best system configuration that works for any query, but rather that performance varies from one query to another. It would be interesting if a meta-system could decide which system configuration should process a new query by learning from the context of previousqueries. This paper reports a deep analysis considering more than 80,000 search engine config- urations applied to 100 queries and the corresponding performance. The goal of the analysis is to identify which configuration responds best to a certain type of query. We considered two approaches to define query types: one is post-evaluation, based on query clustering according to the performance measured with Average Precision, while the sec...

Word sense disambiguation (WSD) is a problem to determine a word according to the context in which it occurs. There are plenty amount of works done in WSD for some languages such as English, but research work on Assamese WSD remains limited. It is a more exigent task because Assamese has an intrinsic complexity in its writing structure and ambiguity, such as syntactic, semantic, and anaphoric ambiguity levels. A novel unsupervised genetic word sense disambiguation algorithm is proposed in this paper. The algorithm first uses WordNet to extract all possible senses for a given ambiguous word, then a genetic algorithm is used taking Wu-Palmer’s similarity measure as the fitness function and calculating the similarity measure for all extracted senses. The winner sense which will have the highest score declared as the winner sense.

An attempt is made in this paper to report how a supervised methodology has been adopted for the task of Word Sense Disambiguation (WSD) in Bengali with necessary modifications. At the initial stage, four commonly used supervised methods, Decision Tree (DT), Support Vector Machine (SVM), Artificial Neural Network (ANN) and Naïve Bayes (NB), are developed at the baseline. These algorithms are applied individually on a data set of 13 most frequently used Bengali ambiguous words. On experimental basis, the baseline strategy is modified with two extensions: (a) inclusion of lemmatization process into the system and (b) bootstrapping of the operational process. As a result, the levels of accuracy of the baseline methods are slightly improved, which is a positive signal for the whole process of disambiguation as it opens scope for further modification of the existing method for better result. In this experiment, the data sets are prepared from the Bengali corpus, developed in the Technology Development for Indian Languages (TDIL) project of the Government of India and from the Bengali WordNet, which is developed at the Indian Statistical Institute, Kolkata. The paper reports the challenges and pitfalls of the work that have been closely observed during the experiment.

An attempt is made in this paper to report how a supervised methodology has been adopted for the task of Word Sense Disambiguation (WSD) in Bengali with necessary modifications. At the initial stage, four commonly used supervised methods, Decision Tree (DT), Support Vector Machine (SVM), Artificial Neural Network (ANN) and Naïve Bayes (NB), are developed at the baseline. These algorithms are applied individually on a data set of 13 most frequently used Bengali ambiguous words. On experimental basis, the baseline strategy is modified with two extensions: (a) inclusion of lemmatization process into the system and (b) bootstrapping of the operational process. As a result, the levels of accuracy of the baseline methods are slightly improved, which is a positive signal for the whole process of disambiguation as it opens scope for further modification of the existing method for better result. In this experiment, the data sets are prepared from the Bengali corpus, developed in the Technology Development for Indian Languages (TDIL) project of the Government of India and from the Bengali WordNet, which is developed at the Indian Statistical Institute, Kolkata. The paper reports the challenges and pitfalls of the work that have been closely observed during the experiment.

Vector space representations of words capture many aspects of word similarity, but such methods tend to make vector spaces in which antonyms (as well as synonyms) are close to each other. We present a new signed spectral normalized graph cut algorithm, signed clustering, that overlays existing thesauri upon distributionally derived vector representations of words, so that antonym relationships between word pairs are represented by negative weights. Our signed clustering algorithm produces clusters of words which simultaneously capture distributional and synonym relations. We evaluate these clusters against the SimLex-999 dataset (Hill et al., 2014) of human judgments of word pair similarities, and also show the benefit of using our clusters to predict the sentiment of a given text.

Much as the social landscape in which languages are spoken shifts, language too evolves to suit the needs of its users. Lexical semantic change analysis is a burgeoning field of semantic analysis which aims to trace changes in the meanings of words over time. This paper presents an approach to lexical semantic change detection based on Bayesian word sense induction suitable for novel word sense identification. This approach is used for a submission to SemEval-2020 Task 1, which shows the approach to be capable of the SemEval task. The same approach is also applied to a corpus gleaned from 15 years of Twitter data, the results of which are then used to identify words which may be instances of slang. 2 Related Work Approaches to lexical semantic change detection collect co-occurrence information on words, represented in most approaches by pointwise mutual information scores (Tahmasebi et al., 2018). This information may be used as the basis of an approach, as is used by Sagi et al. (2009) and Gulordava and Baroni

Despite the incremental nature of Dynamic Syntax (DS), the semantic grounding of it remains that of predicate logic, itself grounded in set theory, so is poorly suited to expressing the rampantly context-relative nature of word meaning, and related phenomena such as incremental judgements of similarity needed for the modelling of disambiguation. Here, we show how DS can be assigned a compositional distributional semantics which enables such judgements and makes it possible to incrementally disambiguate language constructs using vector space semantics. Building on a proposal in our previous work, we implement and evaluate our model on real data, showing that it outperforms a commonly used additive baseline. In conclusion, we argue that these results set the ground for an account of the non-determinism of lexical content, in which the nature of word meaning is its dependence on surrounding context for its construal.

The intelligent tutoring sytems (ITS) are generations of computer based educational sysems that supports the teaching and learning processes with the aim of helpping students to achieve maximum learning goals. A major advanage of these systems is that they can be implemented in all kinds of educational environments either in the normal school environments in the form of stand-alone applications or as programs that remotely deliever knowledge through computers over the internet. The underline idea behind building intelligent tutoring systems is to integrate modern technological advancements with artificial intelligence techniques in the field of education with a view to making the teaching and learning activities highly advanced and more effective. An important feature that enhance the effectiveness of the teaching and learning processes with the ITS is the ability of the system to adapt to each individual student based on his/her characteristics, through making observations on the student's activities while they interct with the system. This phenomenum for observing student's actions while interacting with the ITS in order to build their profiles is known as student modeling. The aim of this paper therefore, is to review the state of art in student modeling in an intelligent tutoring system.

Language is dynamic and constantly evolving: both the usage context and the meaning of words change over time. Identifying words that acquired new meanings and the point in time at which new word senses emerged is elementary for word sense disambiguation and entity linking in historical texts. For example, cloud once stood mostly for the weather phenomenon and only recently gained the new sense of cloud computing. We propose a clustering-based approach that computes sense trees, showing how meanings of words change over time. The produced results are easy to interpret and explain using a drill down mechanism. We evaluate our approach qualitatively on the Corpus of Historic American English (COHA), which spans two hundred years. 1 The Evolution of Language As language evolves, words develop new senses. Detecting these new senses over time is useful for several uses, such as word sense disambiguation and entity linking in historic texts. Current machine learning models that represent ...

We present a state-of-the-art algorithm for measuring the semantic similarity of word pairs using novel combinations of word embeddings, WordNet, and the concept dictionary 4lang. We evaluate our system on the SimLex-999 benchmark data. Our top score of 0.76 is higher than any published system that we are aware of, well beyond the average inter-annotator agreement of 0.67, and close to the 0.78 average correlation between a human rater and the average of all other ratings, suggesting that our system has achieved nearhuman performance on this benchmark.

Despite the incremental nature of Dynamic Syntax (DS), the semantic grounding of it remains that of predicate logic, itself grounded in set theory, so is poorly suited to expressing the rampantly context-relative nature of word meaning, and related phenomena such as incremental judgements of similarity needed for the modelling of disambiguation. Here, we show how DS can be assigned a compositional distributional semantics which enables such judgements and makes it possible to incrementally disambiguate language constructs using vector space semantics. Building on a proposal in our previous work, we implement and evaluate our model on real data, showing that it outperforms a commonly used additive baseline. In conclusion, we argue that these results set the ground for an account of the non-determinism of lexical content, in which the nature of word meaning is its dependence on surrounding context for its construal.

The lexicon of any natural language encodes a huge number of distinct word meanings. Just to understand this article, you will need to know what thousands of words mean. The space of possible sentential meanings is infinite: In this article alone, you will encounter many sentences that express ideas you have never heard before, we hope. Statistical semantics has addressed the issue of the vastness of word meaning by proposing methods to harvest meaning automatically from large collections of text (corpora). Formal semantics in the Fregean tradition has developed methods to account for the infinity of sentential meaning based on the crucial insight of compositionality, the idea that meaning of sentences is built incrementally by combining the meanings of their constituents. This article sketches a new approach to semantics that brings together ideas from statistical and formal semantics to account, in parallel, for the richness of lexical meaning and the combinatorial power of senten...

This article proposes a system based on the interpretation on the Quranic text that has been translated into English language using word sense disambiguation. This system is based on a combination of three traditional semantic similarity measurements, which are Wu-Palmer (WUP), Lin (LIN), and Jiang-Conrath (JCN) for word sense disambiguation on the English Al-Quran. The experiment was performed to obtain the best overall similarity score. The empirical results demonstrate that the combination of the three mentioned semantic similarity techniques obtained competitive results when compared with using individual similarity measurements.

ABSTARCT-The intelligent tutoring systems (ITS) is the most recent alternative advancement to human tutors in the teaching and learning processes in today's educational environments that started over the past three decades. The main goal of an ITS is to help students to achieve maximum learning gain and improve their skills acquisition in a particular domain. For an intelligent tutoring system to be very effective in accomplishing these tasks, the system must be equipped with an explicit representation of the domain knowledge that is the subject of the learning activity (Domain model). But the task of acquiring and designing an effective domain knowledge representation is always challenging and difficult that has been the main concern of so many research projects in the fields of ITS and other artificial intelligence (AI) domains.

As the web is increasing exponentially, so it is very much difficult to provide relevant information to the information seekers. While searching some information on the web, users can easily fade out in rich hypertext. The existing techniques provide the results that are not up to the mark. This paper focuses on the technique that helps in offering more accurate results, especially in case of Homographs. Homograph is a word that shares the same written form but has different meanings. The technique that shows how senses of words can play an important role in offering accurate search results, is described in following sections. While adopting this technique user can receive only relevant pages on the top of the search result.

There has recently been a lot of interest in unsupervised methods for learning sense distributions, particularly in applications where sense distinctions are needed. This paper analyses a state-of-the-art method for sense distribution learning, and optimises it for application to the entire vocabulary of a given language. The optimised method is then used to produce LEXSEMTM: a sense frequency and semantic dataset of unprecedented size, spanning approximately 88% of polysemous, English simplex lemmas, which is released as a public resource to the community. Finally, the quality of this data is investigated, and the LEXSEMTM sense distributions are shown to be superior to those based on the WORDNET first sense for lemmas missing from SEMCOR, and at least on par with SEMCOR-based distributions otherwise.

The process of identifying the meaning of a polysemous word correctly from a given context is known as the Word Sense Disambiguation (WSD) in natural language processing (NLP). Adapted Lesk algorithm based system is proposed which makes use of knowledge based approach. This work utilizes WordNet as the knowledge source (lexical database). The proposed system has three units-Input query, Pre-Processing and WSD classifier. Task of input query is to take the inputs sentence (which is an unstructured query) from the user and render it to the pre-processing unit. Pre-processing unit will convert the received unstructured query into a structured query by adding some features such as Part of Speech (POS) tagging, grammatical identification (Subject, Verb, and Object) and this structured query is transferred to the WSD classifier. WSD classifier uniquely identifies the sense of the polysemous word using the context information of the query and the lexical database.

We provide a comparative study between neural word representations and traditional vector spaces based on cooccurrence counts, in a number of compositional tasks. We use three different semantic spaces and implement seven tensor-based compositional models, which we then test (together with simpler additive and multiplicative approaches) in tasks involving verb disambiguation and sentence similarity. To check their scalability, we additionally evaluate the spaces using simple compositional methods on larger-scale tasks with less constrained language: paraphrase detection and dialogue act tagging. In the more constrained tasks, co-occurrence vectors are competitive, although choice of compositional method is important; on the largerscale tasks, they are outperformed by neural word embeddings, which show robust, stable performance across the tasks.

In natural language processing (NLP), word sense disambiguation (WSD) is defined as the task of assigning the appropriate meaning (sense) to a given word in a text or discourse. Natural language is ambiguous, so that many words can be interpreted in multiple ways depending on the context in which they occur. The computational identification of meaning for words in context is called word sense disambiguation (WSD). In this paper we will discuss about the ambiguity and some important measures to deal with ambiguous statements.

An attempt is made in this paper to report how a supervised methodology has been adopted for the task of Word Sense Disambiguation (WSD) in Bengali with necessary modifications. At the initial stage, four commonly used supervised methods, Decision Tree (DT), Support Vector Machine (SVM), Artificial Neural Network (ANN) and Naïve Bayes (NB), are developed at the baseline. These algorithms are applied individually on a data set of 13 most frequently used Bengali ambiguous words. On experimental basis, the baseline strategy is modified with two extensions: (a) inclusion of lemmatization process into the system and (b) bootstrapping of the operational process. As a result, the levels of accuracy of the baseline methods are slightly improved, which is a positive signal for the whole process of disambiguation as it opens scope for further modification of the existing method for better result. In this experiment, the data sets are prepared from the Bengali corpus, developed in the Technology Development for Indian Languages (TDIL) project of the Government of India and from the Bengali WordNet, which is developed at the Indian Statistical Institute, Kolkata. The paper reports the challenges and pitfalls of the work that have been closely observed during the experiment.

This paper investigates techniques for knowledge injection into word embeddings learned from large corpora of unannotated data. These representations are trained with word cooccurrence statistics and do not commonly exploit syntactic and semantic information from linguistic knowledge bases, which potentially limits their transferability to domains with differing language distributions or usages. We propose a novel approach for linguistic knowledge injection through data augmentation to learn word embeddings that enforce semantic relationships from the data, and systematically evaluate the impact it has on the resulting representations. We show our knowledge augmentation approach improves the intrinsic characteristics of the learned embeddings while not significantly altering their results on a downstream text classification task.

As mentioned in our Introduction, one of the first thorough analyses of ambiguity in IR is that performed in Reference 24. Of the several comments made by Krovetz and Croft 24 when concluding their study, we especially retain the one stating that "disambiguation has the potential for improving precision for low recall searches via the use of a sense-disambiguated thesaurus," one that will be indirectly validated in more modern times as well. These authors equally comment that "the senses of the words is only one factor affecting relevance. The relationships that these words have to one another is also important." When mentioning these relationships they refer 24 to syntactic relations among words, by invoking usage of a natural language parser. At this early stage, semantic relations between the concepts that these words lexicalize are not yet taken into account, as will be done soon after, in Reference 25. The automatic indexing process that is developed in Reference 25 uses the "is-a" relations from WordNet (WN) and constructs vectors of senses to represent documents and queries. As commented in Reference 2, the results show that the classical stem-based approach was superior overall, while the sense-based approach improved the results for some of the queries only. In addition, the results in another work by the same author 28 showed that WSD can even be harmful, confirming Sanderson's 16 conclusion that even low error rates for WSD can hurt IR performance. Voorhees 28 refers to "the pitfalls of linguistic processing," one of the strongest general conclusions that the author comes to being the fact that "linguistic techniques must be essentially perfect to help." Both References 29 and 30 make use of semantic indexing based on WN synsets. Mihalcea and Moldovan 30 come to the conclusion that semantic indexing, a new trend at the time, "offers an improvement over current IR techniques." Although both References 29 and 30 report positive results, one should notice that the corresponding tests were conducted on small datasets. ‖ As opposed to the approach described in Reference 16 that makes use of pseudowords. This approach 16 deals with artificial queries that, additionally, represent "broad topic codes, rather than precise statements of information need." 41 **In the experiments performed by Schütze and Pedersen, 41 the context vectors are computed by considering all content words in a symmetric 41-word context window centered on the target.

Over the last two decades, numerous algorithms have been developed that successfully capture something of the semantics of single words by looking at their distribution in text and comparing these distributions in a vector space model. However, it is not straightforward to construct meaning representations beyond the level of individual words-i.e. the combination of words into larger units-using distributional methods. Our contribution is twofold. First of all, we carry out a largescale evaluation, comparing different composition methods within the distributional framework for the cases of both adjectivenoun and noun-noun composition, making use of a newly developed dataset. Secondly, we propose a novel method for composition, which generalises the approach by Baroni and Zamparelli (2010). The performance of our novel method is also evaluated on our new dataset and proves competitive with the best methods.

Word Sense Disambiguation (WSD) is a significant issue in Natural Language Processing (NLP). WSD refers to the capacity of recognizing the correct sense of a word in a given context. It can improve numerous NLP applications such as machine translation, text summarization, information retrieval, or sentiment analysis. This paper proposes an approach named ShotgunWSD. Shotgun WSD is an unsupervised and knowledgebased algorithm for global word sense disambiguation. The algorithm is motivated by the Shotgun sequencing technique. Shotgun WSD is proposed to disambiguate the word senses of Telugu document with three functional phases. The Shotgun WSD achieves the better performance than other approaches of WSD in the disambiguating sense of ambiguous words in Telugu documents. The dataset is used in the Indo-WordNet.

Word Sense Disambiguation (WSD) is a significant issue in Natural Language Processing (NLP). WSD refers to the capacity of recognizing the correct sense of a word in a given context. It can improve numerous NLP applications such as machine translation, text summarization, information retrieval, or sentiment analysis. This paper proposes an approach named ShotgunWSD. Shotgun WSD is an unsupervised and knowledgebased algorithm for global word sense disambiguation. The algorithm is motivated by the Shotgun sequencing technique. Shotgun WSD is proposed to disambiguate the word senses of Telugu document with three functional phases. The Shotgun WSD achieves the better performance than other approaches of WSD in the disambiguating sense of ambiguous words in Telugu documents. The dataset is used in the Indo-WordNet.

In this paper we study unsupervised word sense disambiguation (WSD) based on sense definition. We learn low-dimensional latent semantic vectors of concept definitions to construct a more robust sense similarity measure wmfvec. Experiments on four all-words WSD data sets show significant improvement over the baseline WSD systems and LDA based similarity measures, achieving results comparable to state of the art WSD systems.

This paper develops a compositional vector-based semantics of relative pronouns within a categorical framework. Frobenius algebras are used to formalise the operations required to model the semantics of relative pronouns, including passing information between the relative clause and the modified noun phrase, as well as copying, combining, and discarding parts of the relative clause. We develop two instantiations of the abstract semantics, one based on a truth-theoretic approach and one based on corpus statistics.

This paper develops a compositional vector-based semantics of subject and object relative pronouns within a categorical framework. Frobenius algebras are used to formalise the operations required to model the semantics of relative pronouns, including passing information between the relative clause and the modified noun phrase, as well as copying, combining, and discarding parts of the relative clause. We develop two instantiations of the abstract semantics, one based on a truth-theoretic approach and one based on corpus statistics.

Count-based distributional semantic models suffer from sparsity due to unobserved but plausible co-occurrences in any text collection. This problem is amplified for models like Anchored Packed Trees (APTs), that take the grammatical type of a co-occurrence into account. We therefore introduce a novel form of distributional inference that exploits the rich type structure in APTs and infers missing data by the same mechanism that is used for semantic composition.

In this paper, we investigate whether an a priori disambiguation of word senses is strictly necessary or whether the meaning of a word in context can be disambiguated through composition alone. We evaluate the performance of off-the-shelf singlevector and multi-sense vector models on a benchmark phrase similarity task and a novel task for word-sense discrimination. We find that single-sense vector models perform as well or better than multi-sense vector models despite arguably less clean elementary representations. Our findings furthermore show that simple composition functions such as pointwise addition are able to recover sense specific information from a single-sense vector model remarkably well.

Count-based distributional semantic models suffer from sparsity due to unobserved but plausible co-occurrences in any text collection. This problem is amplified for models like Anchored Packed Trees (APTs), that take the grammatical type of a co-occurrence into account. We therefore introduce a novel form of distributional inference that exploits the rich type structure in APTs and infers missing data by the same mechanism that is used for semantic composition.

The process of identifying the meaning of a polysemous word correctly from a given context is known as the Word Sense Disambiguation (WSD) in natural language processing (NLP). Adapted Lesk algorithm based system is proposed which makes use of knowledge based approach. This work utilizes WordNet as the knowledge source (lexical database). The proposed system has three units-Input query, Pre-Processing and WSD classifier. Task of input query is to take the inputs sentence (which is an unstructured query) from the user and render it to the pre-processing unit. Pre-processing unit will convert the received unstructured query into a structured query by adding some features such as Part of Speech (POS) tagging, grammatical identification (Subject, Verb, and Object) and this structured query is transferred to the WSD classifier. WSD classifier uniquely identifies the sense of the polysemous word using the context information of the query and the lexical database.

This paper develops a compositional vector-based semantics of relative pronouns within a categorical framework. Frobenius algebras are used to formalise the operations required to model the semantics of relative pronouns, including passing information between the relative clause and the modified noun phrase, as well as copying, combining, and discarding parts of the relative clause. We develop two instantiations of the abstract semantics, one based on a truth-theoretic approach and one based on corpus statistics.

Despite the incremental nature of Dynamic Syntax (DS), the semantic grounding of it remains that of predicate logic, itself grounded in set theory, so is poorly suited to expressing the rampantly context-relative nature of word meaning, and related phenomena such as incremental judgements of similarity needed for the modelling of disambiguation. Here, we show how DS can be assigned a compositional distributional semantics which enables such judgements and makes it possible to incrementally disambiguate language constructs using vector space semantics. Building on a proposal in our previous work, we implement and evaluate our model on real data, showing that it outperforms a commonly used additive baseline. In conclusion, we argue that these results set the ground for an account of the non-determinism of lexical content, in which the nature of word meaning is its dependence on surrounding context for its construal.

Despite the incremental nature of Dynamic Syntax (DS), the semantic grounding of it remains that of predicate logic, itself grounded in set theory, so is poorly suited to expressing the rampantly context-relative nature of word meaning, and related phenomena such as incremental judgements of similarity needed for the modelling of disambiguation. Here, we show how DS can be assigned a compositional distributional semantics which enables such judgements and makes it possible to incrementally disambiguate language constructs using vector space semantics. Building on a proposal in our previous work, we implement and evaluate our model on real data, showing that it outperforms a commonly used additive baseline. In conclusion, we argue that these results set the ground for an account of the non-determinism of lexical content, in which the nature of word meaning is its dependence on surrounding context for its construal.

Change and its precondition, variation, are inherent in languages. Over time, new words enter the lexicon, others become obsolete, and existing words acquire new senses. Associating a word’s correct meaning in its historical context is a central challenge in diachronic research. Historical corpora of classical languages, such as Ancient Greek and Latin, typically come with rich metadata, and existing models are limited by their inability to exploit contextual information beyond the document timestamp. While embedding-based methods feature among the current state of the art systems, they are lacking in the interpretative power. In contrast, Bayesian models provide explicit and interpretable representations of semantic change phenomena. In this chapter we build on GASC, a recent computational approach to semantic change based on a dynamic Bayesian mixture model. In this model, the evolution of word senses over time is based not only on distributional information of lexical nature, but...

Researchers working on distributional semantics have recently taken up the challenge of going beyond lexical meaning and tackle the issue of compositionality. Several Compositional Distributional Semantics Models (CDSMs) have been developed and promising results have been obtained in evaluations carried out against data sets of small phrases and as well as data sets of sentences. However, we believe there is the need to further develop good evaluation tasks that show whether CDSM truly capture compositionality. To this end, we present an evaluation task that highlights some differences among the CDSMs currently available by challenging them in detecting semantic differences caused by word order switch and by determiner replacements. We take as starting point simple intransitive and transitive sentences describing similar events, that we consider to be paraphrases of each other but not of the foil paraphrases we generate from them. Only the models sensitive to word order and determiner phrase meaning and their role in the sentence composition will not be captured into the foils' trap.

Much as the social landscape in which languages are spoken shifts, language too evolves to suit the needs of its users. Lexical semantic change analysis is a burgeoning field of semantic analysis which aims to trace changes in the meanings of words over time. This paper presents an approach to lexical semantic change detection based on Bayesian word sense induction suitable for novel word sense identification. This approach is used for a submission to SemEval-2020 Task 1, which shows the approach to be capable of the SemEval task. The same approach is also applied to a corpus gleaned from 15 years of Twitter data, the results of which are then used to identify words which may be instances of slang.

Consider the meanings of the following phrases: “red apple,” “red hair,” and “red state.” The meaning of the word “red” in each of these examples interacts with the meaning of the noun it modifies, applying a different color to the first two and a political affiliation to the third. This is an example of a common phenomenon in natural language in which the meaning of a whole expression is not derived from a simple sum of its parts, but is composed by interactions among their meanings. Semantic interactions have been acknowledged in the philosophical literature, notably by Frege [9], who asserted that a word in isolation is only an abstraction, and its precise meaning only assigned when it is placed in the context of a proposition. Further, semantic interaction is a detectable component of human language processing, as evidenced by the well documented phenomenon of sentential priming [8].

The Practical Lexical Function (PLF) model is a model of computational distributional semantics that attempts to strike a balance between expressivity and learnability in predicting phrase meaning and shows competitive results. We investigate how well the PLF carries over to free word order languages, given that it builds on observations of predicate-argument combinations that are harder to recover in free word order languages. We evaluate variants of the PLF for Croatian, using a new lexical substitution dataset. We find that the PLF works about as well for Croatian as for English, but demonstrate that its strength lies in modeling verbs, and that the free word order affects the less robust PLF variant.

The Practical Lexical Function model (PLF) is a recently proposed compositional distributional semantic model which provides an elegant account of composition, striking a balance between expressiveness and robustness and performing at the state-of-the-art. In this paper, we identify an inconsistency in PLF between the objective function at training and the prediction at testing which leads to an overcounting of the predicate's contribution to the meaning of the phrase. We investigate two possible solutions of which one (the exclusion of simple lexical vector at test time) improves performance significantly on two out of the three composition datasets.

For many decades researchers in the domain of NLP (Natural Language Processing) and its applications like Machine Translation, Text Mining, Question Answering, Information Extraction and Information retrieval etc. have been posed with a challenging area of research i.e. WSD (Word Sense Disambiguation) WSD can be defined as the ability to correctly ascertain the meaning of a word, with reference to the context in which the word was used. Linguistics, has defined context as the passage, sentence or text in which the word appears that is used for ascertaining its meaning. Thus, context is dependent on the POS (Part Of Speech) where the word is used e.g. Adverb, Adjective, Pronoun, Verb and Noun. In the following study we recommend a unique way of WSD based on Context through WordNet, multimodal algorithm that is knowledge based, map-reduce and soft sense WSD.