Rhetorical structure theory

In the current study we aim at exploiting discourse structure of Arabic text to automatically finding answers to non-factoid questions ("Why" and "How to"). Our method is based on Rhetorical Structure Theory (RST) that many studies have shown to be a very effective approach for many computational linguistics applications such as (text generation, text summarization and machine translation). For both types of questions we assign one or more rhetorical relations that help discovering the corresponding answers. This is the first Arabic Question Answering system that attempts to answer the "Why" and "How to" questions.

Rhetorical Structure Theory (RST) is a theory of text structure that is being extended to serve as a theoretical basis for computational text planning. Text structures in RST are hierarchic, built on small patterns called schemas. The schemas which compose the structural hierarchy of a text describe the functions of the parts rather than their form characteristics. Relations between text parts, comparable to conjunctive relations, are a prominent part of RST’s definitional machinery. Recent work has put RST onto a new definitional basis. This paper details the current status of descriptive RST, along with efforts to create a constructive version for use as a basis for programming a text planner.

The existing discourse parsing systems make use of different theories to put at the basis of processes of building discourse trees. Many of them use Recall, Precision and F-measure to compare discourse tree structures. These measures can be used only on topologically identical structures. However, there are known cases when two different tree structures of the same text can express the same discourse interpretation, or something very similar. In these cases Precision, Recall and F-measures are not so conclusive. In this paper, we propose three new scores for comparing discourse trees. These scores take into consideration more and more constraints. As basic elements of building the discourse structure we use those embraced by two discourse theories: Rhetorical Structure Theory (RST) and Veins Theory, both using binary trees augmented with nuclearity notation. We will ignore the second notation used in RST – the name of relations. The first score takes into account the coverage of inner nodes. The second score complements the first score with the nuclearity of the relation. The third score computes Precisions, Recall and F-measures on the vein expressions of the elementary discourse units. We show that these measures reveal comparable scores there where the differences in structure are not doubled by differences in interpretation.Keywordsdiscourse parserRhetorical Structure TheoryVeins Theoryevaluationdiscourse tree structure

Senses are the extensions of language and interrelations between word meanings within language and the basis of flexible language use. Computers are basically made to process symbols. Computational linguistics is to simulate part of, if not all of, the natural language competence. From the perspective of computational linguistics, this paper sheds some light on semantic formalization, and proposes tagging of senses along with tagging weight values when processing word meanings. Also, this paper makes attempts to apply sense weight values to sentence processing in computational linguistics. Keywords-semantics, sense, weight, formalization, computational linguistics I. SEMANTIC KNOWLEDGE IN LANGUAGE PROCESSING According to prototype theory, semantic knowledge is part of human’s cognitive and belief systems. Semantics is also the critical research area since its initiation in 1893 by Michael Breal, and then by Trier and Lakoff who contributes to semantic research from both the descriptive and generative perspective. In linguistic semantics, rules and principles explain how literal meaning is coded in language and how to understand the “senses” of an expression or sense-relations that hold between one word and other expressions within the same language (Ceusters et al, 1999). Language is the carrier of both thoughts and forms. Thoughts are to induce, deduce, infer and judge, while senses are the contents and basis of thoughts. Senses are not the repeated addition of forms, rather a psychological process. Semantics is the mapping of cognitive structure from language expressions. Based on concepts, which are the abstract and general categorization of objects, people can apply semantic principles, situational contexts and encyclopedic knowledge to construct cognitive schema of the outside world. With frequent interactions and cognitive strategies, limited forms can be used to express unlimited connotation of thoughts (Tesser and Leone, 1977). For example, same meanings can be expressed with different semantic forms. a) 他这个人真有意思 (funny); b) 于是人们以为他们有了意思 (wish); c) 你向他意思意思 (express)如何; d) .我根本没有那个意思 (thought); e) 他常说人生真没有意思 (nonsense); f) 你们这么说是什么意思 (intention) These sentences are easy to comprehend. People not only use the grammatical structures but also the sense weights to process the words. The sense weight schema are stored in memory, and activated to represent and distill other sense weights. In this chain activation, sense weights are restructured and created to reflect prototypes. For example, “你好?”, “你好么?”, “好么你?”. Different structures are used in the above examples, but their essential meaning remains the same. So, semantic knowledge is of utmost importance in language comprehension. II. THE STATUS QUO OF COMPUTATIONAL LINGUISTICS Three domains and three corresponding levels of study are involved in building natural language processing systems, i.e. theoretical linguistics and grammar level, computational linguistics and formalization level, computer technology and realization level. Among them, grammar level concerns the innate characteristics of language and paves the way for the latter modules. Realization level focuses on how to control computer operation and provides the efficient development tools and environment. Formalization level is the interface of grammar level and realization level, with the task to readjust the general grammar modules to form grammar modules for convenient computer processing. Computational linguists’ mission is to establish formal grammars (Kaufmann and Pfister, 2012). Computational linguistics is also to establish formalized mathematical modules to analyze and process natural language, and develop computer programs to make it possible that machines can simulate part of, if not all of, human behavior and competence. Computers can only be used to process symbols and all those processed by computers are symbolized with no exception of languages (Yushi, 2003). Meanwhile, there have been breakthroughs in processing Chinese characters and phrases, so sentence level processing has become critical. Basic researches in syntactic, semantic and pragmatic knowledge are the frontier studies in Chinese processing. And how to acquire syntactic and semantic knowledge is the key, while the latter constitutes the major difficulty in processing the word level senses. As aforementioned, semantic formalization can take on many impossible missions in artificial intelligence and computational linguistics, and face challenges at the same time. Thus, the researcher will use semantic field to investigate formalization issues. Semantic fields are the sememe systems, which include the semantemes to represent similarities and differences, and are classified by the subordinates, i.e. degree and number of abstraction of Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013) Published by Atlantis Press, Paris, France.

This study investigates the (re)creation of rhetorical structure, a crucial aspect of coherence that plays an important part in establishing functional equivalence in translation. While considerable amount of research is available on certain aspects of coherence, little attention has been devoted to the translation of rhetorical structure, despite its acknowledged significance in discourse processing (Hatim and Mason 1990, Mann et al. 1992, Nord 1997, Tirkkonen-Condit 2002). Based on Rhetorical Structure Theory (Mann and Thompson 1986), this study aims to generate initial hypotheses regarding the (re)creation of rhetorical structure in Hungarian-English news translation and demonstrate the interplay between rhetorical and discourse structure, with a view to highlighting the significance of rhetoric in producing functionally adequate translations. Findings indicate that while no statistically significant shifts occur in the quantity of relational propositions in source texts and translations, considerable shifts may be identified in the quality and position of certain relational propositions . These shifts affect the rhetorical as well as generic structure of the target text and thus exert a very subtle influence on the way it is interpreted by the reader.

Rhetorical relations in university students’ presentations

William C. Mann passed away on August 13, 2004, after a long struggle with leukemia. He is known to readers of Computational Linguistics as a keen supporter and past president (1987) of ACL, a pioneer in the development of text generation as a field of research in computational linguistics, the originator of rhetorical structure theory (RST) and dialogue game theory (DGT), and the developer (together with David Weber) of dialect adaptation as a technique within machine translation. And he’ll be remembered for these and many other contributions, but above all, in this context, he’ll be remembered as a unique visionary in computational linguistics (CL) and as a truly wonderful and extraordinarily generous colleague. Bill Mann made huge contributions to many people’s intellectual development, to their careers, and to their lives in general. What follows are my own recollections of him, selected from a crowded jungle of memories. I will leave it to others to fill out the picture, but I shall attempt to give an indication of the intellectual and historical context in which Bill was working and also of the network of researchers that he created; his ideas have radiated throughout this network of scholars around the world. I met Bill in April 1980 and worked as a research linguist on a succession of projects he directed, or codirected, at the Information Sciences Institute (ISI) at the University of Southern California (USC), until I left the institute to take up a position at the University of Sydney in August 1988. Through that period (which happened to coincide, more or less, with the Reagan years), not only was Bill a very wise and wonderful project leader, but he also became a mentor and guide and a true friend. I followed from afar the further developments in his life: his departure from ISI and move to Kenya with his family to take up a position with the Summer Institute of Linguistics (SIL) as a consultant responsible for work on discourse and computational matters, their return to the United States, and his new phase of research with initiatives in RST and DGT.

This study presents a contrastive analysis of the pronominal uses of bu and su and this and that in written academic discourse within the framework of Rhetorical Structure Theory (Mann and Thompson, 1988; Marcu 2000). The comparative analysis of these pronominals is done with respect to the rhetorical relations in which they are used. Data for this study were retrieved from journal articles on linguistics and education. The results show that bu-su and this-that are sensitive to rhetorical relations. Although bu and this are used in similar rhetorical functions (i.e. interpretation, explanation and reason relations), in some occurrences they are used in different rhetorical relations (i.e textual organisation and hypothetical relations). On the other hand, su is used differently from that and this in the establishment of rhetorical relations. Su is used in the subtypes of elaboration relation (i.e. elaboration-set-member, elaboration part-whole), while that is not used in elaboration relations. That is used in antithesis, list and contrast relations, where occurrences of su are not seen. While this is used in addition, interpretation, hypothetical, summarisation and concession relations, su is not.

These definitions and protocols are intended as an online supplement to work in the course of publication. This work focuses on the tagging of corpora of argumentative writing with logical relations, and presents the frameworks used in the text analysis at the base of the tagging.

Analyzing Chinese text with clause relevance structure

Discourse structures have a central role in several computational tasks, such as question-answering or dialogue generation. In particular, the framework of the Rhetorical Structure Theory (RST) offers a sound formalism for hierarchical text organization. In this article, we present HILDA, an implemented discourse parser based on RST and Support Vector Machine (SVM) classification. SVM classifiers are trained and applied to discourse segmentation and relation labeling. By combining labeling with a greedy bottom-up tree building approach, we are able to create accurate discourse trees in linear time complexity. Importantly, our parser can parse entire texts, whereas the publicly available parser SPADE (Soricut and Marcu 2003) is limited to sentence level analysis. HILDA outperforms other discourse parsers for tree structure construction and discourse relation labeling. For the discourse parsing task, our system reaches 78.3% of the performance level of human annotators. Compared to a state-of-the-art rule-based discourse parser, our system achieves a performance increase of 11.6%.

Although language is the primary medium by which we communicate our thoughts and feelings with others, only a fraction of published studies in psychology, communication, and allied fields have addressed the underlying psychology of language. Historically, the complexity of language was simply too overwhelming to tackle. The advent of computational techniques along with digital communication and social media has changed everything. We are now witnessing an exponential growth in the number of studies that link natural language use and real-world behaviors. Over the last thirty years, computer-based text analysis has grown from relatively simple word counting methods to revolutionary Large Language Models (LLMs) that can generate natural language in ways similar to human beings. The psychological study of language has roots in philosophy, with considerable influence and overlap with the fields of anthropology, sociology, linguistics, and communications. Since the 1990s, work in language psychology has been associated with a host of newer disciplines involving natural language processing, such as cognitive science, artificial intelligence, computational linguistics, and even subfields of engineering. The different approaches to the study of language adopted by these various fields are often complementary, with each approach informing the others. Oftentimes, language scholars from different disciplines fail to appreciate each other’s perspectives. Linguists, for example, are primarily interested in the structure and function of language. Computational linguists are usually interested in developing models to best classify two or more groups of language processes. Psychologists who study language are actually interested in the psychological states of the people who are generating the language samples. Accordingly, the readings in this bibliography come from a wide variety of fields but with an emphasis on what might be useful to psychologists in their research on language. The new world of language psychology has largely been built on expanding technologies in computer and data science in parallel with developments in social and cognitive psychology. As a result of cross-disciplinary collaborations, new approaches to data collection, research and statistical methods, and theoretical orientations have evolved. Given the rapid growth of the field, the current bibliography should be viewed as a placeholder as the field will continue to expand over the next few years.

The presented article focuses on new research opportunities in the field of computational linguistics, especially in the context of video games and artificial intelligence and seeks to bridge the three areas. It provides a general introduction to computational linguistics, which emerged in the 1950s in response to the rapid development of science and technology and introduces the reader to concepts such as natural language processing and natural language understanding. It also explores the connections between computational linguistics and not only artificial intelligence, which greatly aids computers in understanding, interpreting, and generating human language, but also video games. The text highlights the role of artificial intelligence in the video game industry, where it is used, for example, to create dialogues and stories, to interact with players, and to translate and localize video game content. The paper also articulates the challenges and benefits of using AI in video games, including the negative ethical and legal aspects. The author mentions that AI can generate personalized stories and guide the behaviour of game characters, contributing to deeper immersion of players. She also discusses the issue of translating video game text, where AI can be helpful, but the translation produced this way still requires human control to ensure quality and accuracy. In conclusion, the author considers the hypothesis that video games are a practical example of the application of computational linguistics and that this linguistic branch can play a key role in the development of video games to be well-founded but encourages further and more detailed research. Computational linguistics and video games are linked through language that exhibits a tension between natural human and machine artificial language.

This article considers the framework of IoT (Internet of Things) and IIoT (Industrial Internet of Things) as a driving factor in the development of new industry functionality for industrial production control systems. And the natural language processing used is related to artificial intelligence (AI) and mathematical linguistics. From a scientific point of view, this factor implies the problems of computer analysis and synthesis of texts in natural languages, where analysis means understanding the language, and synthesis means generating literate text. Processing techniques for converting unstructured data into information understandable to artificial intelligence systems are analyzed so that such systems can take on some individual functions of human intelligence, and on the other hand, provide business users with opportunities for how and when they can have access to such resources. The uniqueness of this development lies in a serious change in the culture of using such solutions, where each authorized business user has access to the source data, based on which such users can conduct their own analysis, with their own tools. And developers can add additional functionality using their authorized ecosystems. Thus, this development implies a new approach to isolated data in the field of business applications in industrial sectors. Such a transition expands business opportunities in its subject area and is a motivating force.

The aim of this paper is to introduce a new method to represent discourse structures. This approach is based on three discourse theories in order to highlight three discourse features: cohesion, coherence and intentionality. The graph representations of discourse structure proposed in this paper address linguistic discourse and chat conversation at the same time. The discourse units are chained to each other in order of their appearance in the text. Using such a representation, chronology of events is kept and highlighted. In graph representations of discourse structure two types of nodes describe the structure: nodes for elementary discourse units and cover nodes. Also, a method for traversing the graph is proposed and two expressions are introduced in order to discover the most important elementary discourse units from text. The paper describes a new graph-based model of discourse structure, building on a number of existing models such as the vein model and rhetorical structure theory. A main goal of the new model is the handling of multi-threaded discourse structures which are common in chat interactions. The operation of the model is demonstrated on one typical discourse and one chat discourse.