Semantic Role Labelling

This study will introduce a tool - termed "NLPytaly" - for the automatic treatment of naturally-occurring texts in Italian. The tool distinguishes constructs with an ordinary verb from those with a support verb. Meaning is rendered by using cognate (i.e. etymologically related) semantic roles (CSR), which differ from other roles because they are expressed with the content morpheme of the predicate licensing arguments. CSRs offer a number of advantages: they can be semi-automatically derived and use the who-does-what model. Besides, they facilitate the detection of anaphoric chains and produce a foreground/ background opposition of the named entities. Finally, they permit the construction of a chronology of narrated events.
Keywords: computational linguistics, Natural Language Understanding, semantic roles, non-verbal predication, automatic text summarization

This research focuses on expanding PropBank, a corpus annotated with predicate argument structures, with new predicate types; namely, noun, adjective and complex predicates, such as Light Verb Constructions. This effort is in part inspired by a sister project to PropBank, the Abstract Meaning Representation project, which also attempts to capture “who is doing what to whom ” in a sentence, but does so in a way that abstracts away from syntactic structures. For example, alternate realizations of a destroying event in the form of either the verb destroy or the noun destruction would receive the same Abstract Meaning Representation. In order for PropBank to reach the same level of coverage and continue to serve as the bedrock for Abstract Meaning Representation, predicate types other than verbs, which have previously gone without annotation, must be annotated. This research describes the challenges therein, including the development of new annotation practices that walk the line betwee...

This paper describes the procedure of semantic role labeling and the development of the first manually annotated Persian Proposition Bank (PerPB) which added a layer of predicate-argument information to the syntactic structures of Persian Dependency Treebank (known as PerDT). Through the process of annotating, the annotators could see the syntactic information of all the sentences and so they annotated 29982 sentences with more than 9200 unique verbs. In the annotation procedure, the direct syntactic dependents of the verbs were the first candidates for being annotated. So we did not annotate the other indirect dependents unless their phrasal heads were propositional and had their own arguments or adjuncts. Hence besides the semantic role labeling of verbs, the argument structure of 1300 unique propositional nouns and 300 unique propositional adjectives were annotated in the sentences, too. The accuracy of annotation process was measured by double annotation of the data at two separate stages and finally the data was prepared in the CoNLL dependency format.

This paper outlines and categorizes ways of using syntactic information in a number of algorithms for determining the semantic similarity of short texts. We consider the use of word order information, part-of-speech tagging, parsing and semantic role labeling. We analyze and evaluate the effects of syntax usage on algorithm performance by utilizing the results of a paraphrase detection test on the Microsoft Research Paraphrase Corpus. We also propose a new classification of algorithms based on their applicability to languages with scarce natural language processing tools.

We present a system for automating Semantic Role Labelling of Hindi-English code-mixed tweets. We explore the issues posed by noisy, user generated code-mixed social media data. We also compare the individual effect of various linguistic features used in our system. Our proposed model is a 2-step system for automated labelling which gives an overall accuracy of 84% for Argument Classification, marking a 10% increase over the existing rule-based baseline model. This is the first attempt at building a statistical Semantic Role Labeller for Hindi-English code-mixed data, to the best of our knowledge.

U ovom radu su prikazani i kategorizovani načini korišćenja sintaksnih informacija u više algoritama za određivanje semantičke sličnosti kratkih tekstova. Evaluacija performansi algoritama je sprovedena korišćenjem rezultata testa detekcije parafraza iz Microsoft Research Paraphrase korpusa. Od svih opisanih algoritama i pristupa korišćenju sintaksnih informacija identifikovani su oni najpogodniji za primenu u jezicima sa ograničenim elektronskim jezičkim alatima i, imajući tu svrhu u vidu, predložena je nova klasifikacija algoritama.
/
This paper outlines and categorizes ways of using syntax information in a number of algorithms for determining short text semantic similarity. Algorithm performance was evaluated using the results of a paraphrase detection test on the Microsoft Research Paraphrase Corpus. Among the described algorithms and approaches to using syntax information we identify those best suited for application in languages with limited electronic linguistic tools and, with that goal in mind, we propose a new algorithm classification.

In this paper we present a semantic role labeling system submitted to the CoNLL-2005 shared task. The system makes use of partial and full syntactic information and converts the task into a sequential BIO-tagging. As a result, the labeling architecture is very simple. Building on a state-of-the-art set of features, a binary classifier for each label is trained using AdaBoost with fixed depth decision trees. The final system, which combines the outputs of two base systems performed F 1 =76.59 on the official test set. Additionally, we provide results comparing the system when using partial vs. full parsing input information.

Semantic role annotation has become widely used in NLP and lexical resource implementation. Even if attempts of standardization are being developed, discor-dance points are still present. In this paper we consider a problematic semantic role, the Instrument role, which presents differences in definition and causes problems of attribution. Particularly, it is not clear whether to assign this role to inanimate entities occurring as subjects or not. This problem is especially relevant 1-in reason of its treatment in practical annotation and semantic role labeling, 2-because it affects the whole definition of semantic roles. We propose arguments to sustain that inanimate nouns denoting instruments in subject positions are not instantiation of Instrument role, but are Cause, Agent or Theme. Ambiguities in the annotation of these cases are due to confusion between semantic roles and ontological types.

The first semantic roles corpus in Persian language, containing about 30,000 sentences from contemporary Persian language, is manually annotated. This corpus, based on the concept of thematic roles of Fillmore, adds a layer of predicate-argument information to the syntactic structures of Persian Dependency Treebank. In this corpus, the verbs, propositional nouns and adjectives are regarded as the predicates of the sentences and are annotated according to their argument structure. The data was prepared based on Conference on Natural Language Learning (CoNLL) dependency format. Semantic tags used as the semantic annotations include thematic roles and functional tags. Thematic roles labels present the argument structure of the predicates of the sentences, and functional tags modify the verb or the whole sentence. The number of thematic roles tags and functional tags are 27 and 15, respectively. The two tags of NEGATION and MODALS are used as the functional tags.

Semantic Role Labelling (SRL) is the process of automatically finding the semantic roles of terms in a sentence. It is an essential task towards creating a machine-meaningful representation of textual information. One public linguistic resource commonly used for this task is the FrameNet Project. FrameNet is a human and machine-readable lexical database containing a considerable number of annotated sentences, those annotations link sentence fragments to semantic frames. However, while the annotations across all the documents covered in the dataset link to most of the frames, a large group of frames lack annotations in the documents pointing to them. In this paper, we present a data augmentation method for FrameNet documents that increases by over 13% the total number of annotations. Our approach relies on lexical, syntactic, and semantic aspects of the sentences to provide additional annotations. We evaluate the proposed augmentation method by comparing the performance of a state-of-the-art semantic-role-labelling system, trained using a dataset with and without augmentation.

This paper presents the concept, structural design and implementation of components of a multifunctional sensory network, consisting of a Mobile Robotic Platform (MRP) and stationary multifunctional sensors, which are wirelessly communicating with the MRP. Each section provides the review of the principles of operation and the network components' practical implementation. The analysis is focused on the structure of the robotic platform, sensory network and electronics and on the methods of the environment monitoring and data processing algorithms that provide maximal reliability, flexibility and stable operability of the system. The main aim of this project is the development of the Robotic Nurse (RN)—a 24/7 robotic helper for the hospital nurse personnel. To support long-lasting autonomic operation of the platform, all mechanical, electronic and photonic components were designed to provide minimal weight, size and power consumption, while still providing high operational efficiency, accuracy of measurements and adequateness of the sensor response. The stationary sensors serve as the remote " eyes, ears and noses " of the main MRP. After data acquisition, processing and analysing, the robot activates the mobile platform or specific sensors and cameras. The cross-use of data received from sensors of different types provides high reliability of the system. The key RN capabilities are simultaneous monitoring of physical conditions of a large number of patients and alarming in case of an emergency. The robotic platform Nav-2 exploits innovative OPEN ACCESS J. Low Power Electron. Appl. 2013, 3 115 principles of any-direction motion with omni-wheels, navigation and environment analysis. It includes an innovative mini-laser, the absorption spectrum analyser and a portable, extremely high signal-to-noise ratio spectrometer with two-dimensional detector array.