Language Understanding Research Articles

Bataille and Wittgenstein: on mysticism, silence, and inner experience

ABSTRACT Despite differences, Georges Bataille, theorist of non-knowledge and atheology, and Ludwig Wittgenstein, the Austrian logician, share specific parallels regarding their understandings of language and mystical experience. For both, mystical experience pushes beyond conventional discourse. Using analogous elements of critical and mystical discourse, each express rather antiphilosophical, spiritual visions. Still, Wittgenstein’s deeply private and agnostic Christianity sharply contrasts Bataille’s own atheological experience of the death of God. Where Bataille’s mysticism challenges rationality, Wittgenstein’s instead expresses the numinous world as such, shedding light on the dark night of Bataille and the specific character of ‘inner experience’. Where Wittgenstein advocates either clarity of expression or silence, however, the transgressive and poetic syntax of Bataille, alongside his evocative and erotic usage of imagery and metaphor, instead presses precisely against the impossibility for words that Wittgenstein’s thinking forecloses. Silence, like evil and poetry for Bataille, is active and imperative to communication, opening itself against the closure of reason. Relative to Wittgenstein and Christianity’s ascent to knowledge and awareness then, Bataille instead dives down deep into the body and night of nonknowledge. In this way, paradoxically, Bataille’s atheological writings approach a new summit of communication only attainable in the absence of God.

Joint Entity and Relation Extraction Using Machine Reading Comprehension for Urdu

Joint Entity and Relation Extraction (JERE) plays an important role in natural language processing (NLP) by identifying names, locations, and the relationships among them from unstructured text. Despite extensive research in languages like English, JERE poses significant challenges in low-resource languages, particularly Urdu, due to limited annotated da-ta and inherent linguistic complexities. In this paper, we propose a novel Machine Reading Comprehension (MRC)-based approach that effectively addresses the JERE task for Urdu, integrating a text encoder and a question-answering module that work synergistically to enhance entity and relationship extraction. We introduce an annotated Urdu JERE dataset and demonstrate how our methodology will significantly contribute to multilingual NLP efforts. We propose an innovative Machine Reading Comprehension (MRC)-based method to tackle JERE in Urdu. This method has two main components: a text encoder and a question answering (QA) module. The text encoder converts Urdu text into a compact vector form, which is then fed into the QA module. The QA module generates answers to queries regarding the desired entities and relationships, producing a sequence of tokens that represent these entities and their interactions. The model is trained to minimize the difference between its predicted answers and the correct ones. Our approach, along with the introduction of an annotated Urdu JERE dataset, significantly advances multilingual NLP and information ex-traction research. The insights gained can be applied to other low-resource languages, aiding in the development of NLP tools and applications for a broader array of languages.

A survey on pragmatic processing techniques

Pragmatics, situated in the domains of linguistics and computational linguistics, explores the influence of context on language interpretation, extending beyond the literal meaning of expressions. It constitutes a fundamental element for natural language understanding in machine intelligence. With the advancement of large language models, the research focus in natural language processing has predominantly shifted toward high-level task processing, inadvertently downplaying the importance of foundational pragmatic processing tasks. Nevertheless, pragmatics serves as a crucial medium for unraveling human language cognition. The exploration of pragmatic processing stands as a pivotal facet in realizing linguistic intelligence. This survey encompasses important pragmatic processing techniques for subjective and emotive tasks, such as personality recognition, sarcasm detection, metaphor understanding, aspect extraction, and sentiment polarity detection. It spans theoretical research, the forefront of pragmatic processing techniques, and downstream applications, aiming to highlight the significance of these low-level tasks in advancing natural language understanding and linguistic intelligence.

ExTraCT - Explainable trajectory corrections for language-based human-robot interaction using textual feature descriptions.

In human-robot interaction (HRI), understanding human intent is crucial for robots to perform tasks that align with user preferences. Traditional methods that aim to modify robot trajectories based on language corrections often require extensive training to generalize across diverse objects, initial trajectories, and scenarios. This work presents ExTraCT, a modular framework designed to modify robot trajectories (and behaviour) using natural language input. Unlike traditional end-to-end learning approaches, ExTraCT separates language understanding from trajectory modification, allowing robots to adapt language corrections to new tasks-including those with complex motions like scooping-as well as various initial trajectories and object configurations without additional end-to-end training. ExTraCT leverages Large Language Models (LLMs) to semantically match language corrections to predefined trajectory modification functions, allowing the robot to make necessary adjustments to its path. This modular approach overcomes the limitations of pre-trained datasets and offers versatility across various applications. Comprehensive user studies conducted in simulation and with a physical robot arm demonstrated that ExTraCT's trajectory corrections are more accurate and preferred by users in 80% of cases compared to the baseline. ExTraCT offers a more explainable approach to understanding language corrections, which could facilitate learning human preferences. We also demonstrated the adaptability and effectiveness of ExTraCT in a complex scenarios like assistive feeding, presenting it as a versatile solution across various HRI applications.

Idārah Tanfīdz Barnāmaj Ta’līm Al Lughah Al-‘Arabiyah Litarqiyah Kafāah Al Lughah

Management of implementing the Arabic language learning program at the Al-Muhibbin Islamic Boarding School is a planned process. Because considering the current situation where Arabic has become a necessity for today's society in order to be able to keep up with changing times which are increasingly global and not to be left behind by other countries. Therefore, Arabic language learning programs are very important. This research discusses the management of implementing the Arabic language learning program at the Al-Muhibbin Islamic Boarding School. This research uses a qualitative descriptive method, and data collection is carried out by observation, interviews, and documentation. The results of this research indicate that the implementation of the Arabic language learning program at the Al-Muhibbin Islamic Boarding School is going well. There are two Arabic language learning programs at this Islamic boarding school, namely main activities and additional activities. The main activity in this program is classroom learning. This activity goes through three stages, namely introduction, core activities, and closing activities. Activities are held at 14.00-16.00 and 20.00-22.00. Meanwhile, additional activities are divided into daily activities, namely additional mufrodat and muhadasah al-yaumiyah. The weekly activity is muhadhoroh. The annual activities are FASTABIN and rihlah lughoh. Overall, the management of the implementation of the Arabic language learning program at the Al-Muhibbin Islamic Boarding School reflects a strong commitment to providing useful experiences for the students to improve their Arabic language skills and understanding of religion as evidenced by their enthusiasm when participating in this program, their communication practices using Arabic.

Empowering geoportals HCI with task-oriented chatbots through NLP and deep transfer learning

ABSTRACT In the past ten years, chatbot development has matured to become one of the most well-distinguished outcomes of artificial intelligence. Despite some criticism, Bing AI, ChatGPT and other natural language processing (NLP) products of similar nature are becoming more popular. The creation of chatbots can close several gaps in geographic information retrieval as well. This research introduces and successfully implements, for the first time, a model for integrating task-oriented chatbots into geoportals, with the goal of easing user requests, improving access to geospatial services, and fostering human-computer interactions (HCI). Additionally, it presents a novel recommendation solution for matching the most appropriate volunteer to the user’s geospatial needs based on expertise similarity, semantic similarity, and community feedback. The three categories of finding map services, discovering geoprocessing services, and volunteer expert recommendations were shown to be the most significant geoportal bot intents. Depending on the requirement, each intent additionally includes various entities such as time, place, description, skill, etc. The notion of deep transfer learning (DTL) was then put into practice by customizing a pre-trained BERT (Bidirectional Encoder Representations from Transformers) model for our particular aim and creating a task-oriented conversational agent. According to the results, effective intent classification and entity recognition in the geospatial domain could arise from this approach. We performed the training process with 200 sample data, 20% of which were utilized in a stratified manner for testing, and we obtained f1-scores of at least 0.75. Finally, a pilot Geoportal Chabot that combines crowdsourcing and conversational agents’ approaches was put into use and tested with success. In keeping with SDI technical purposes, the system might direct users to common geospatial web services, namely WMS and WPS, in addition to including natural language understanding (NLU) and natural language generation (NLG) capabilities. Result of user-centered evaluation indicated that the integration of a chatbot significantly reduces the average time required to access geospatial data and processing services by more than 50%. Notably, this effect is even more pronounced when locating an expert, with a fivefold decrease in the time required. Finally, overall user satisfaction rose from 86% to 94%.

Assessing the Capability of Advanced AI Models in Cardiovascular Symptom Recognition: A Comparative Study

The field of medical informatics has been significantly transformed in recent years with the emergence of Natural Language Understanding (NLU) and Large Language Models (LLM), providing new opportunities for innovative patient care solutions. This study aims to evaluate the effectiveness of publicly available LLMs as symptom checkers for cardiological diseases by comparing their diagnostic capabilities in real disease cases. We employed a set of 9 models, including ChatGPT-4, OpenSource models, Google PaLM 2, and Meta’s LLaMA, to assess their diagnostic accuracy, reliability, and safety across various clinical scenarios. Our methodology involved presenting these LLMs with symptom descriptions and test results in Spanish, requiring them to provide specialist diagnoses and recommendations in English. This approach allowed us to compare the performance of each model, highlighting their respective strengths and limitations in a healthcare context. The results revealed varying levels of accuracy, precision, and sensitivity among the models, demonstrating the potential of LLMs to enhance medical education and patient care. By analysing the capabilities of each model, our study contributes to a deeper understanding of artificial intelligence’s role in medical diagnosis. We argue for the strategic implementation of LLMs in healthcare, emphasizing the importance of balancing sensitivity and realism to optimize patient outcomes.

Enhancing Task-Oriented Dialogue Systems through Synchronous Multi-Party Interaction and Multi-Group Virtual Simulation

This paper presents two innovative approaches: a synchronous multi-party dialogue system that engages in simultaneous interactions with multiple users, and multi-group simulations involving virtual user groups to evaluate the resilience of this system. Unlike most other chatbots that communicate with each user independently, our system facilitates information gathering from multiple users and executes 17 administrative tasks for group requests adeptly by leveraging a state machine-based framework for complete control over dialogue flow and a large language model (LLM) for robust context understanding. Assessing such a unique dialogue system poses challenges, as it requires many groups of users to interact with the system concurrently for an extended duration. To address this, we simulate various virtual groups using an LLM, each comprising 10–30 users who may belong to multiple groups, in order to evaluate the efficacy of our system; each user is assigned a persona and allowed to interact freely without scripts. As a result, our system shows average success rates of 87% for task completion and 89% for natural language understanding. Comparatively, our virtual simulation, which has an average success rate of 80%, is juxtaposed with a group of 15 human users, depicting similar task diversity and error trends. To our knowledge, it is the first work to show the LLM’s potential in both task execution and the simulation of a synchronous dialogue system to fully automate administrative tasks.

KUHN AND THE MYSTERY OF CONSTITUTING THOUGHT, WORD AND DEED INTO A WORLD

Ever since my first book, Social Epistemology, I have argued that Thomas Kuhn’s philosophy of science presupposes a version of ‘many worlds realism’. This paper continues that line of argument by situating Kuhn’s thinking about language and science in the context of shifting philosophical developments in the 1950s-1970s. Kuhn’s view is related to others exposed to the same developments, especially Willard Quine, Donald Davidson, Wolfgang Stegmüller and Karl Popper. Notably, Quine and Davidson were not tempted to go down the ‘many worlds’ route, largely due to a background commitment to a behaviorist understanding of language that precluded any role for ‘world-making’. However, Alfred Tarski’s ‘semantic’ theory of truth made a notable impression on the logical positivists and Popper, inclining the latter towards his own version of many worlds realism. As Kuhn astutely observed in his later writings, whether one adopted a monist or pluralist approach to the world depended on whether translation or meaning was the key to making sense of language. The paper ends by suggesting that the German historiographical concept of Sonderweg (‘special way’) might provide an interesting, more normatively charged understanding of the sort of many worlds realism promoted by Kuhn.

Languaging-as-practice in science education: an alternative to metaphors of language-as-tool

AbstractThis commentary proposes the metaphor of “languaging-as-practice” in science education as an alternative to “language-as-tool” metaphors. Describing language as a tool implicitly positions language as static and unchanging and assumes that named languages are distinct and bounded entities. In contrast, describing languaging as a practice acknowledges the multiple and advanced ways speakers draw on many aspects of their linguistic repertoires while often crossing purported boundaries between named languages. This approach is grounded in translanguaging theory and offers a dynamic understanding of language in educational settings. It envisions students constructing and expressing scientific knowledge by drawing on their complete linguistic repertoires. By advocating for this approach, we aim to promote practices that acknowledge and leverage the diverse linguistic backgrounds of students, fostering inclusive and effective learning environments. While this approach has gained some traction in language-education circles, we believe it needs more consideration in the science education community. We also critique the limitations of viewing language merely as a tool for reproducing predefined scientific concepts and discourses, proposing that a more expansive approach to language can enhance opportunities for scientific sense-making and knowledge construction. We urge science education researchers and practitioners to shift how we think and talk about language in the science classroom to adopt and act upon a metaphor of “languaging-as-practice.”

Ground4Act: Leveraging visual-language model for collaborative pushing and grasping in clutter

The challenge in robotics is to enable robots to transition from visual perception and language understanding to performing tasks such as grasp and assembling objects, bridging the gap between “seeing” and “hearing” to “doing”. In this work, we propose Ground4Act, a two-stage approach for collaborative pushing and grasping in clutter using a visual-language model. In the grounding stage, Ground4Act extracts target features from multi-modal data via visual grounding. In the action stage, it embeds a collaborative pushing and grasping framework to generate the action's position and direction. Specifically, we propose a DQN-based reinforcement learning pushing policy that uses RGBD images as the state space to determine the push action's pixel-level coordinates and direction. Additionally, a least squares-based linear fitting grasping policy takes the target mask from the grounding stage as input to achieve efficient grasp. Simulations and real-world experiments demonstrate Ground4Act's superior performance. The simulation suite, source code, and trained models will be made publicly available.

A Review Study: The Positive Aspects of Using Authentic Materials to Develop Teaching English Language During the Period from 2001 to 2023

This review examines the use of authentic materials by many researchers over twenty years ago. The researchers have suggested that using authentic materials in teaching the English language has many advantages, with the most effective for students. This study is essential for future teaching that could use authentic resources to improve students' understanding of language. Huong (2020) investigated that “teaching materials play a vital role in the teaching and learning process and proved helpful in fulfilling the goal of communicating in foreign languages and meeting the needs of the learners”. Furthermore, these products enhance and strengthen the process of teaching and learning.

The Two Word Test as a semantic benchmark for large language models

Large language models (LLMs) have shown remarkable abilities recently, including passing advanced professional exams and demanding benchmark tests. This performance has led many to suggest that they are close to achieving humanlike or “true” understanding of language, and even artificial general intelligence (AGI). Here, we provide a new open-source benchmark, the Two Word Test (TWT), that can assess semantic abilities of LLMs using two-word phrases in a task that can be performed relatively easily by humans without advanced training. Combining multiple words into a single concept is a fundamental linguistic and conceptual operation routinely performed by people. The test requires meaningfulness judgments of 1768 noun-noun combinations that have been rated as meaningful (e.g., baby boy) or as having low meaningfulness (e.g., goat sky) by human raters. This novel test differs from existing benchmarks that rely on logical reasoning, inference, puzzle-solving, or domain expertise. We provide versions of the task that probe meaningfulness ratings on a 0–4 scale as well as binary judgments. With both versions, we conducted a series of experiments using the TWT on GPT-4, GPT-3.5, Claude-3-Optus, and Gemini-1-Pro-001. Results demonstrated that, compared to humans, all models performed relatively poorly at rating meaningfulness of these phrases. GPT-3.5-turbo, Gemini-1.0-Pro-001 and GPT-4-turbo were also unable to make binary discriminations between sensible and nonsense phrases, with these models consistently judging nonsensical phrases as making sense. Claude-3-Opus made a substantial improvement in binary discrimination of combinatorial phrases but was still significantly worse than human performance. The TWT can be used to understand and assess the limitations of current LLMs, and potentially improve them. The test also reminds us that caution is warranted in attributing “true” or human-level understanding to LLMs based only on tests that are challenging for humans.

Influence of Available Instructional Resources on the Acquisition of Language Skills among Early-Year Learners in Kiambaa Sub-County, Kiambu County, Kenya

Language entails the ability to communicate with other people with significant variations between understanding of speech and language. Although language acquisition largely depends on the learner's ability, the access and availability of instructional resources play a pivotal role in language acquisition among children in Early Childhood Education Centres. The main aim of this study was to assess the influence of available instructional resources on the acquisition of language skills among early-year learners, to determine the impact of teachers' competence on the use of instructional resources on the acquisition of language skills among early-year learners and to determine the influence of challenges in use of instructional resources on the acquisition of language skills among early year learners in Kiambaa sub-county, Kiambu County. The study was based on the constructivists and overlapping spheres of influence theory. The study adopted a descriptive research design. The target population was 98 head teachers and 210 ECD teachers who were considered for the study. Purposive sampling was used to obtain 12 head teachers, and simple random sampling was used to obtain 44 teachers. Statistical Package for Social Sciences was used to analyse the quantitative data, while content analysis was used to analyse the qualitative information gathered using open-ended questions, where findings were reported in a narrative form under each theme. Descriptive analysis was done through frequencies and percentages. A multiple Linear Regression model was used to model the relationship between the independent variable and the response variable (Acquisition of language skills). The study concludes that the availability of Instructional resources has a significant positive effect on the acquisition of language skills as denoted by the p-value (P <0.05). The study recommends that stakeholders, including head teachers, teachers, and parents, should understand the importance of having sufficient instructional resources. Efforts should be made to improve access and availability based on recommendations from ECD teachers, thereby fostering language acquisition among early learners.

Domain-specific research methods in instructed second language acquisition: A next step for research integrity and impact

Abstract Instructed second language acquisition (ISLA) is one of the fastest growing areas of applied linguistics. With this tremendous potential comes great responsibility for robust, ethical, and transparent research methods that are responsive to and tailored for the ISLA domain. This article highlights unique characteristics of ISLA research, provides a current landscape of methodological trends within ISLA, and makes specific recommendations for research methods in future ISLA studies. I begin by briefly operationalizing ISLA and articulating some of the main research questions and overarching goals within ISLA, as well as the nature and ultimate aims of ISLA research. Next, the most unique methodological challenges for ISLA research are reviewed, including the use of intact classes and heterogeneous small participant pools, cross-sectional studies, using one’s own students for research, and individual differences. This is followed by a discussion of several current trends in ISLA research methods, including examining the process of learning/development, conducting practice-based research, expanding our conceptualization of instructional contexts, replication studies, especially with bi/multilingual learners in diverse contexts, refining our methods with an eye for ethics and justice, equity, diversity, and inclusion, and conducting open, transparent research that has potential for real-world impact and which dialogues with multiple stakeholders at all stages. I conclude by highlighting that, as ISLA continues as an independent research domain, the development and implementation of strong research methods tailored for ISLA is critical for research integrity and to make the greatest strides in understanding language acquisition processes and effective pedagogical interventions in diverse instructional contexts.

DCE attribute development investigating public policy for the provision of medicinal cannabis

Background Defining attributes and attribute levels for a discrete choice experiment (DCE) poses a significant challenge for practitioners exploring preferences for new or unfamiliar products due to the dearth of available information and limits in stakeholder knowledge. This study outlines a comprehensive process for identifying attributes and levels in a DCE aimed at gauging public preferences for health policies related to medicinal cannabis (MC). Methods A rigorous four-stage attribute development process was utilized and included i) the formulation of a preliminary attribute list from a scoping review and document analysis, ii) reduction of attributes via focus groups, iii) removal of inappropriate attributes using Delphi studies and research team knowledge, and iv) refinement of attribute language based on the feedback from think-aloud interviews. Results A base attribute list formed from the scoping review and document analysis served as effective discussion stimuli in focus groups, especially for participants with limited subject knowledge. Structured focus group activities proved more effective than open-ended discussions in engaging naive participants. Delphi studies were found to be overcomplex for expert-led attribute prioritization. Think-aloud interviews during a pilot DCE were essential for assessing attribute language and clarity and understanding participants’ decision-making processes. Conclusion The development of DCE attributes measuring preferences for an unfamiliar health product requires a multi-method approach. Evaluating the outcomes from various methods of attribute development yielded a refined list of attributes that were significant to stakeholders, allowed for meaningful trade-offs, and were presented in language accessible to the target population.

Augmented dialectal speech recognition for AI-based neuropsychological scale assessment in Alzheimer’s disease

Alzheimer’s disease (AD) is a prevalent and widespread neurodegenerative disorder among the older adult population worldwide. Among the numerous cognitive screening methods, neuropsychological scale assessments (NSA) are the widely utilized screening tools in clinical practice. The NSA places significant emphasis on speech-related questions, and thus the role of Automatic Speech Recognition (ASR) technology in AI-based NSA evaluations becomes particularly critical. However, the majority of ASR research pays limited attention to the study of speech recognition for various dialects. One of the primary reasons and main challenges for the scarcity of research in dialectal speech recognition is the limited availability of annotated dialectal data. Furthermore, the older adults’ unclear pronunciation leads to erroneous recognition of similar phonetic words by ASR. To overcome the challenges of limited annotated dialect data in various regions and the issues related to confusable pronunciation of older adults, we propose a dialectal collaborative encoder mechanism and a machine reading comprehension augmented model (MRCAM) that automatically corrects the texts in the NSA. The dialectal collaborative encoder mechanism utilizes layer frozenness to transfer recognition ability to the dialectal model. Meanwhile, the MRCAM model fills the gap by combining speech recognition algorithms with natural language processing (NLP) technology to recognize the dialects spoken by older adults. The experimental evaluation results indicate that the proposed augmented model achieves over 90% consistency with the physician’s judgment, providing the premise of the proposed methods for the task of automated screening for AD based on ASR.

Initial exploration into sarcasm and irony through machine translation

In this paper, we investigate sarcasm and irony as seen through a novel perspective of machine translation. We employ various techniques for translation, comparing both manually and automatically translated datasets of irony and sarcasm. We first clarify the definitions of irony and sarcasm and present an exhaustive field review of studies on irony both from purely linguistic as well as computational linguistic perspectives. We also propose a novel evaluation metric for the purpose of evaluating translations of figurative language, with a focus on machine-translated irony and sarcasm. The constructed English and Chinese parallel dataset includes polarized content from tweets as well as forum posts, categorized by irony types. The preferred translation model, mBART-50, is identified through a thorough experimental process. Optimal translation settings and the best-finetuned model for irony are explored, with the most effective model being finetuned on both ironic and non-ironic data. We also experimented which types of irony are best suitable for training in this specific task — short microblogging messages or longer forum posts. Moreover, we compare the capabilities of a well fine-tuned mBART to a prompt-based method using the recently popular ChatGPT model, with the conclusion that the former still outperforms the latter, although ChatGPT without any training can be considered as a “good enough” ad hoc solution in the case of a lack of data for training. Finally, we verify if the translated data – either manually, or with an MT model – can be used as training data in a task of irony detection. We believe that the presented research can be expanded into languages other than the presented here Chinese and English, which together with the ability to detect various categories of irony, could contribute to deepening the understanding of figurative language, especially irony and sarcasm.

Research on the role of LLM in multi-agent systems: A survey

In recent years, the rapid development of large language model (LLM) has demonstrated superior performance in language understanding, text generation, planning, reasoning, and knowledge integration. This has led to the emergence of intelligent agents based on LLM. By leveraging the capabilities of LLM, these agents can effectively make decisions based on given objectives and possess certain learning and adaptation abilities. However, single-agent systems are generally suited to solving relatively simple problems and are limited in handling complex tasks that require coordination. For instance, in fields such as power grid management or traffic control systems, relying solely on a single agent is often insufficient for effective decision-making. In this context, adopting multi-agent systems proves to be more effective: through collaboration among multiple agents, each undertaking specific tasks, complex problems can be efficiently managed through interaction and coordination. This survey will analyze the role of LLM in multi-agent collaboration, discuss and analyze the current research challenges and key issues, and explore potential directions for future development.

Accommodation, translanguaging, and (in)discreteness in the repertoire: A scalar‐chronotopic approach

AbstractA shift from understanding languages as discrete towards understanding them as undifferentiated features in the repertoire has caused disagreements over the reality of linguistic boundaries. In this paper, I show how a middle‐ground approach is achievable by applying the complex workings of a scalar‐chronotopic lens to the discourse of bilingual/multidialectal Bahrainis. I argue that both perspectives on (in)discreteness become relevant in accounting for bi/multilingual subjectivities: at times, Arabic is idealized as a large‐scale code against English, whereas at other times, the intrusiveness of English is backgrounded to show affiliation for one Arabic variety over another. I show accommodation in communication as a spatiotemporally layered process, where the internalized contextual factors within the repertoire may overlap with or take precedence over the immediate context. As such, this paper adds to the question of linguistic discreteness, with implications for our understanding of the repertoire and its utility in bi/multilingual practices and accommodation theory.