Identification Of Multiword Expressions Research Articles

Multilingual Multiword Expression Identification Using Lateral Inhibition and Domain Adaptation

Correctly identifying multiword expressions (MWEs) is an important task for most natural language processing systems since their misidentification can result in ambiguity and misunderstanding of the underlying text. In this work, we evaluate the performance of the mBERT model for MWE identification in a multilingual context by training it on all 14 languages available in version 1.2 of the PARSEME corpus. We also incorporate lateral inhibition and language adversarial training into our methodology to create language-independent embeddings and improve its capabilities in identifying multiword expressions. The evaluation of our models shows that the approach employed in this work achieves better results compared to the best system of the PARSEME 1.2 competition, MTLB-STRUCT, on 11 out of 14 languages for global MWE identification and on 12 out of 14 languages for unseen MWE identification. Additionally, averaged across all languages, our best approach outperforms the MTLB-STRUCT system by 1.23% on global MWE identification and by 4.73% on unseen global MWE identification.

Light Verb Constructions in Lithuanian: Identification and Classification

Light verb constructions (LVCs) are verb-noun constructions in which the noun carries the semantic meaning and the verb is semantically reduced, when compared with its main meaning, for example, atlikti analizę (‘to perform an analysis’). LVCs in Lithuanian have not been addressed much so far. The analysis of Lithuanian LVCs was carried out as a part of the PARSEME project on verbal identification of multiword expressions (MWE). This paper aims at presenting some initial findings on the identification of LVCs in Lithuanian, based on the 1st edition of the PARSEME shared-task results (2017). We describe the identification process according to the semantic and syntactic features of LVCs (PARSEME guidelines 1.0 2017) and discuss the grammatical features of the identified Lithuanian LVCs.
 LVCs seem to be less frequent in Lithuanian than in other languages: they make up about 0.2% (215 instances) of the analysed 200,000 token corpus. Based on the number of different LVCs, there seem to be two groups of verbs functioning as light verbs: a relatively small group of common light verbs used in the most prototypical examples of Lithuanian LVCs (e.g., vykdyti ‘to perform’, atlikti ‘to perform’, daryti ‘to do’, and turėti ‘to have’) and a larger group of less common light verbs. Most of the nouns in analysed LVCs have suffixes -imas and -ymas, which are the most typical Lithuanian suffixes for deriving a noun from a verb. Almost 40% of all LVCs are used with 1–3 words intervening between a verb and a noun.

Design of a Multiword Expressions Database

Abstract The paper proposes design of a generic database for multiword expressions (MWE), based on the requirements for implementation of the lexicon of Czech MWEs. The lexicon is aimed at different goals concerning lexicography, teaching Czech as a foreign language, and theoretical issues of MWEs as entities standing between lexicon and grammar, as well as for NLP tasks such as tagging and parsing, identification and search of MWEs, or word sense and semantic disambiguation. The database is designed to account for flexibility in morphology and word order, syntactic and lexical variants and even creatively used fragments. Current state of implementation is presented together with some emerging issues, problems and solutions.

Enlarging multiword expression dataset by co-training

In multiword expressions (MWEs), multiple words unite to build a new unit in language. When MWE identification is accepted as a binary classification task, one of the most important factors in performance is to train the classifier with enough number of labelled samples. Since manual labelling is a time-consuming task, the performances of MWE recognition studies are limited with the size of the training sets. In this study, we propose the comparison-based and common-decision co-training approaches in order to enlarge the MWE dataset. In the experiments, the performances of the proposed approaches were compared to those of the standard co-training [1] and manual labelling where statistical and linguistic features are employed as two different views of the MWE dataset [2]. A number of tests with different settings were performed on a Turkish MWE dataset. Ten different classifiers were utilized in the experiments and the best performing classifier pair was observed to be the SMO-SMO pair. The experimental results showed that the common-decision co-training approach is an alternative to hand-labeling of large MWE datasets and both newly proposed approaches outperform the standard co-training [2] when the training set is to be enlarged in MWE classification.

L1 Regularization of Word Embeddings for Multi-Word Expression Identification

In this paper we compare the effects of applying various state-of-the-art word representation strategies in the task of multi-word expression (MWE) identification. In particular, we analyze the strengths and weaknesses of the usage of `1-regularized sparse word embeddings for identifying MWEs. Our earlier study demonstrated the effectiveness of regularized word embeddings in other sequence labeling tasks, i.e. part-of-speech tagging and named entity recognition, but it has not yet been rigorously evaluated for the identification of MWEs yet.

Multiword Expression Processing: A Survey

Multiword expressions (MWEs) are a class of linguistic forms spanning conventional word boundaries that are both idiosyncratic and pervasive across different languages. The structure of linguistic processing that depends on the clear distinction between words and phrases has to be re-thought to accommodate MWEs. The issue of MWE handling is crucial for NLP applications, where it raises a number of challenges. The emergence of solutions in the absence of guiding principles motivates this survey, whose aim is not only to provide a focused review of MWE processing, but also to clarify the nature of interactions between MWE processing and downstream applications. We propose a conceptual framework within which challenges and research contributions can be positioned. It offers a shared understanding of what is meant by “MWE processing,” distinguishing the subtasks of MWE discovery and identification. It also elucidates the interactions between MWE processing and two use cases: Parsing and machine translation. Many of the approaches in the literature can be differentiated according to how MWE processing is timed with respect to underlying use cases. We discuss how such orchestration choices affect the scope of MWE-aware systems. For each of the two MWE processing subtasks and for each of the two use cases, we conclude on open issues and research perspectives.

A Comprehensive Analysis of Web-based frequency in Multiword Expression Detection

Multiword expressions (MWEs) are syntactic and/or semantic units in language, where the meaning of whole is limitedly connected to the meanings of the constituting units. The most prominent property that distinguishes MWEs from random word combinations is the recurrence. The recurrence is commonly measured by the occurrence frequencies of the MWE and the constituting words. Though occurrence frequency measures are known to be best in distinguishing MWEs from random combinations, the performance of those measures depend mainly on the quality and size of the data source where frequencies are obtained. The main goal of this study is to provide a detailed analysis on the change in performance of frequency based measures when the traditional frequency source, corpus, is swapped with a massive and dynamic data source, the World Wide Web. In order to use the web as a frequency source, the constituting words and word combinations are queried among a popular search engine, and the number of results for each query is accepted to be web-based frequency for the regarding word/word combination. In this study, the web-based frequencies are employed in three different MWE detection-related experiments utilizing a Turkish data set. In first group of experiments, the individual performances of 20 well-known frequency metrics in ranking/sorting MWE candidates based on their tendency to be a MWE is examined. Secondly, the most successful frequency metrics are determined by a feature selection method: filtering. Lastly, MWE detection is accepted to be a classification problem. Eight supervised methods are applied in order to show the combined performance of frequency metrics when the frequency is obtained from web. In all experiments, the performance of web-based frequencies in identification of MWEs is compared to the performance of traditional corpus based frequencies. The experimental results showed that the use of web-based frequency in identification of MWEs reveals promising results.

A classification-based approach to the identification of Multiword Expressions (MWEs) in Magahi Applying SVM

Multiword Expressions are crucial for any Natural Language Processing task as they frequently occur in any natural language. In addition, they “display a continuum of compositionality”. Although they have much frequency in informal spoken corpus, they are used less frequently in formal textual corpus. Multiword expressions in Magahi can provide a unique platform and a gateway to research into other less-resourced Indian languages in general and dialectal varieties of Hindi in particular. This is the very first research project of its kind undertaken in Magahi. In this study, we have applied Support Vector Machines classifier for automatic identification and classification of multiword expressions. For this purpose, we have applied a POS-annotated corpus of approximately 75k word tokens out of which 11k tokens are multiword expressions. The raw data applied in this study have been crawled and sanitized by Indian languages crawler known as IC Crawler and semi-automatically annotated by the ILCI annotation tool. The tagset adhered for annotation comprises of nine annotation labels as adapted from Singh et al. The Magahi multiword extractor achieves a combined overall precision accuracy of 81.57%.

Discriminative Lexical Semantic Segmentation with Gaps: Running the MWE Gamut

We present a novel representation, evaluation measure, and supervised models for the task of identifying the multiword expressions (MWEs) in a sentence, resulting in a lexical semantic segmentation. Our approach generalizes a standard chunking representation to encode MWEs containing gaps, thereby enabling efficient sequence tagging algorithms for feature-rich discriminative models. Experiments on a new dataset of English web text offer the first linguistically-driven evaluation of MWE identification with truly heterogeneous expression types. Our statistical sequence model greatly outperforms a lookup-based segmentation procedure, achieving nearly 60% F1 for MWE identification.

Identification of Multiword Expressions by Combining Multiple Linguistic Information Sources

We propose a framework for using multiple sources of linguistic information in the task of identifying multiword expressions in natural language texts. We define various linguistically motivated classification features and introduce novel ways for computing them. We then manually define interrelationships among the features, and express them in a Bayesian network. The result is a powerful classifier that can identify multiword expressions of various types and multiple syntactic constructions in text corpora. Our methodology is unsupervised and language-independent; it requires relatively few language resources and is thus suitable for a large number of languages. We report results on English, French, and Hebrew, and demonstrate a significant improvement in identification accuracy, compared with less sophisticated baselines.

Modeling the internal variability of multiword expressions through a pattern-based method

The issue of internal variability of multiword expressions (MWEs) is crucial towards their identification and extraction in running text. We present a corpus-supported and computational study on Italian MWEs, aimed at defining an automatic method for modeling internal variation, exploiting frequency and part-of-speech (POS) information. We do so by deriving an XML-encoded lexicon of MWEs based on a manually compiled dictionary, which is then projected onto a a large corpus. Since a search for fixed forms suffers from low recall, while an unconstrained flexible search for lemmas yields a loss in precision, we suggest a procedure aimed at maximizing precision in the identification of MWEs within a flexible search. Our method builds on the idea that internal variability can be modelled via the novel introduction of variation patterns , which work over POS patterns, and can be used as working tools for controlling precision. We also compare the performance of variation patterns to that of association measures, and explore the possibility of using variation patterns in MWE extraction in addition to identification. Finally, we suggest that corpus-derived, pattern-related information can be included in the original MWE lexicon by means of an enriched coding and the creation of an XML-based repository of patterns.

Parsing Models for Identifying Multiword Expressions

Multiword expressions lie at the syntax/semantics interface and have motivated alternative theories of syntax like Construction Grammar. Until now, however, syntactic analysis and multiword expression identification have been modeled separately in natural language processing. We develop two structured prediction models for joint parsing and multiword expression identification. The first is based on context-free grammars and the second uses tree substitution grammars, a formalism that can store larger syntactic fragments. Our experiments show that both models can identify multiword expressions with much higher accuracy than a state-of-the-art system based on word co-occurrence statistics. We experiment with Arabic and French, which both have pervasive multiword expressions. Relative to English, they also have richer morphology, which induces lexical sparsity in finite corpora. To combat this sparsity, we develop a simple factored lexical representation for the context-free parsing model. Morphological analyses are automatically transformed into rich feature tags that are scored jointly with lexical items. This technique, which we call a factored lexicon, improves both standard parsing and multiword expression identification accuracy.

Genetic Algorithm (GA) In Feature Selection For CRF Based Manipuri Multiword Expression (MWE) Identification

This paper deals with the identification of Multiword Expressions (MWEs) in Manipuri, a highly agglutinative Indian Language. Manipuri is listed in the Eight Schedule of Indian Constitution. MWE plays an important role in the applications of Natural Language Processing(NLP) like Machine Translation, Part of Speech tagging, Information Retrieval, Question Answering etc. Feature selection is an important factor in the recognition of Manipuri MWEs using Conditional Random Field (CRF). The disadvantage of manual selection and choosing of the appropriate features for running CRF motivates us to think of Genetic Algorithm (GA). Using GA we are able to find the optimal features to run the CRF. We have tried with fifty generations in feature selection along with three fold cross validation as fitness function. This model demonstrated the Recall (R) of 64.08%, Precision (P) of 86.84% and F-measure (F) of 73.74%, showing an improvement over the CRF based Manipuri MWE identification without GA application.

Alignment-based extraction of multiword expressions

Due to idiosyncrasies in their syntax, semantics or frequency, Multiword Expressions (MWEs) have received special attention from the NLP community, as the methods and techniques developed for the treatment of simplex words are not necessarily suitable for them. This is certainly the case for the automatic acquisition of MWEs from corpora. A lot of effort has been directed to the task of automatically identifying them, with considerable success. In this paper, we propose an approach for the identification of MWEs in a multilingual context, as a by-product of a word alignment process, that not only deals with the identification of possible MWE candidates, but also associates some multiword expressions with semantics. The results obtained indicate the feasibility and low costs in terms of tools and resources demanded by this approach, which could, for example, facilitate and speed up lexicographic work.