Ambiguity Of Natural Language Research Articles

On improving conversational interfaces in educational systems

Conversational Intelligent Tutoring Systems (CITS) have drawn increasing interest in education because of their capacity to tailor learning experiences, improve user engagement, and contribute to the effective transfer of knowledge. Conversational agents employ advanced natural language techniques to engage in a convincing human-like tutorial conversation. In solving math word problems, a significant challenge arises in enabling the system to understand user utterances and accurately map extracted entities to the essential problem quantities required for problem-solving, despite the inherent ambiguity of human natural language. In this study, we propose two possible approaches to enhance the performance of a particular CITS designed to teach learners to solve arithmetic-algebraic word problems. Firstly, we propose an ensemble approach to intent classification and entity extraction, which combines the predictions made by two distinct individual models that use constraints defined by human experts. This approach leverages the intertwined nature of the intents and entities to yield a comprehensive understanding of the user’s utterance, ultimately aiming to enhance semantic accuracy. Secondly, we introduce an adapted Term Frequency-Inverse Document Frequency technique to associate entities with problem quantity descriptions. The evaluation was conducted on the AWPS and MATH-HINTS datasets, containing conversational data and a collection of arithmetical and algebraic math problems, respectively. The results demonstrate that the proposed ensemble approach outperforms individual models, and the proposed method for entity-quantity matching surpasses the performance of typical text semantic embedding models.

A Technological Framework to Support Asthma Patient Adherence Using Pictograms

Background: Low comprehension and adherence to medical treatment among the elderly directly and negatively affect their health. Many elderly patients forget medical instructions immediately after their appointments, misunderstand them, or fail to recall them altogether. Some identified causes include the short time slots allocated for appointments in the public health system in Chile, the complex terminology used by healthcare professionals, and the stress experienced by patients during appointments. One approach to improving patients’ adherence to medical treatment is to combine written and oral instructions with graphical elements such as pictograms. However, several challenges arise due to the ambiguity of natural language and the need for pictograms to accurately represent various medication combinations, doses, and frequencies. Objective: This study introduces SIMAP (System for Integrating Medical Instructions with Pictograms), a technological framework aimed at enhancing adherence among asthma patients through the delivery of pictograms via a computational system. SIMAP utilizes a collaborative and user-centered methodology, involving health professionals and patients in the construction and validation of its components. Methods: The technological framework presented in this study is composed of three parts. The first two are medical indications and pictograms related to the treatment of the disease. Both components were developed through a comprehensive and iterative methodology that incorporates both qualitative and quantitative approaches. This methodology includes the utilization of focus groups, interviews, paper and online surveys, as well as expert validation, ensuring a robust and thorough development. The core of SIMAP is the technological component that leveraged artificial intelligence methods for natural language processing to analyze, tokenize, and associate words and their context to a set of one or more pictograms, addressing issues such as the ambiguity in the text, the cultural factor that involves many ways of expressing the same indication, and typographical errors in the indications. Results: Firstly, we successfully validated 18 clinical indications along with their respective pictograms. Some of the pictograms were redesigned based on the validation results. However, in the final validation, the comprehension percentages of the pictograms exceeded 70%. Furthermore, we developed a software called SIMAP, which translates medical indications into previously validated pictograms. Our proposed software, SIMAP, achieves a correct mapping rate of 96.69%. Conclusions: SIMAP demonstrates great potential as a technological component for supplementing medical instructions with pictograms when tested in a laboratory setting. The use of artificial intelligence for natural language processing can successfully map medical instructions, both structured and unstructured, into pictograms. This integration of textual instructions and pictograms holds promise for enhancing the comprehension and adherence of elderly patients to their medical indications, thereby improving their long-term health.

Fine-Grained Cross-Modal Semantic Consistency in Natural Conservation Image Data from a Multi-Task Perspective.

Fine-grained representation is fundamental to species classification based on deep learning, and in this context, cross-modal contrastive learning is an effective method. The diversity of species coupled with the inherent contextual ambiguity of natural language poses a primary challenge in the cross-modal representation alignment of conservation area image data. Integrating cross-modal retrieval tasks with generation tasks contributes to cross-modal representation alignment based on contextual understanding. However, during the contrastive learning process, apart from learning the differences in the data itself, a pair of encoders inevitably learns the differences caused by encoder fluctuations. The latter leads to convergence shortcuts, resulting in poor representation quality and an inaccurate reflection of the similarity relationships between samples in the original dataset within the shared space of features. To achieve fine-grained cross-modal representation alignment, we first propose a residual attention network to enhance consistency during momentum updates in cross-modal encoders. Building upon this, we propose momentum encoding from a multi-task perspective as a bridge for cross-modal information, effectively improving cross-modal mutual information, representation quality, and optimizing the distribution of feature points within the cross-modal shared semantic space. By acquiring momentum encoding queues for cross-modal semantic understanding through multi-tasking, we align ambiguous natural language representations around the invariant image features of factual information, alleviating contextual ambiguity and enhancing model robustness. Experimental validation shows that our proposed multi-task perspective of cross-modal momentum encoders outperforms similar models on standardized image classification tasks and image-text cross-modal retrieval tasks on public datasets by up to 8% on the leaderboard, demonstrating the effectiveness of the proposed method. Qualitative experiments on our self-built conservation area image-text paired dataset show that our proposed method accurately performs cross-modal retrieval and generation tasks among 8142 species, proving its effectiveness on fine-grained cross-modal image-text conservation area image datasets.

Nanjing Yunjin intelligent question-answering system based on knowledge graphs and retrieval augmented generation technology

Nanjing Yunjin, a traditional Chinese silk weaving craft, is celebrated globally for its unique local characteristics and exquisite workmanship, forming an integral part of the world's intangible cultural heritage. However, with the advancement of information technology, the experiential knowledge of the Nanjing Yunjin production process is predominantly stored in text format. As a highly specialized and vertical domain, this information is not readily convert into usable data. Previous studies on a knowledge graph-based Nanjing Yunjin Question-Answering System have partially addressed this issue. However, knowledge graphs need to be constantly updated and rely on predefined entities and relationship types. Faced with ambiguous or complex natural language problems, knowledge graph information retrieval faces some challenges. Therefore, this study proposes a Nanjing Yunjin Question-Answering System that integrates Knowledge Graphs and Retrieval Augmented Generation techniques. In this system, the ROBERTA model is first utilized to vectorize Nanjing Yunjin textual information, delving deep into textual semantics to unveil its profound cultural connotations. Additionally, the FAISS vector database is employed for efficient storage and retrieval of Nanjing Yunjin information, achieving a deep semantic match between questions and answers. Ultimately, related retrieval results are fed into the Large Language Model for enhanced generation, aiming for more accurate text generation outcomes and improving the interpretability and logic of the Question-Answering System. This research merges technologies like text embedding, vectorized retrieval, and natural language generation, aiming to overcome the limitations of knowledge graphs-based Question-Answering System in terms of graph updating, dependency on predefined types, and semantic understanding. System implementation and testing have shown that the Nanjing Yunjin Intelligent Question-Answering System, constructed on the basis of Knowledge Graphs and Retrieval Augmented Generation, possesses a broader knowledge base that considers context, resolving issues of polysemy, vague language, and sentence ambiguity, and efficiently and accurately generates answers to natural language queries. This significantly facilitates the retrieval and utilization of Yunjin knowledge, providing a paradigm for constructing Question-Answering System for other intangible cultural heritages, and holds substantial theoretical and practical significance for the deep exploration and discovery of the knowledge structure of human intangible heritage, promoting cultural inheritance and protection.

Sensing complicated meanings from unstructured data: a novel hybrid approach

The majority of data on computers nowadays is in the form of unstructured data and unstructured text. The inherent ambiguity of natural language makes it incredibly difficult but also highly profitable to find hidden information or comprehend complex semantics in unstructured text. In this paper, we present the combination of natural language processing (NLP) and convolution neural network (CNN) hybrid architecture called automated analysis of unstructured text using machine learning (AAUT-ML) for the detection of complex semantics from unstructured data that enables different users to make understand formal semantic knowledge to be extracted from an unstructured text corpus. The AAUT-ML has been evaluated using three datasets data mining (DM), operating system (OS), and data base (DB), and compared with the existing models, i.e., YAKE, term frequency-inverse document frequency (TF-IDF) and text-R. The results show better outcomes in terms of precision, recall, and macro-averaged F1-score. This work presents a novel method for identifying complex semantics using unstructured data.

A Semi-Automated Approach to Process Discovery from Multiple Natural Language Documents

The discovery of process information in natural language documents is hindered by the innate ambiguity of natural language. This issue is even more challenging when process information is spread throughout several documents, each with the possibility of different formats, writers, and original purposes, that must be read and interpreted individually by a business analyst before their information can be uncovered. This work presents a semi-automated approach to process discovery from multiple documents simultaneously, making use of semantic similarity measures and natural language processing techniques to identify, gather, and extract process information from these documents. An experiment is conducted with this approach to demonstrate its use and results.

SJORS: A Semantic Recommender System for Journalists

AbstractRecommender Systems support a broad range of domains, each with peculiarities that recommendation algorithms must consider to produce appropriate suggestions. In the paper, we bring attention to a little-studied scenario related to the news domain: recommendations catering to media journalists. Based on the particular needs inherent to a newsroom, the authors introduce SJORS, a wire news Recommender System that takes into account the activities of each journalist as well as other critical factors that arise in this particular domain, such as wire news recency. Given the nature of the items recommended, SJORS deals with the inherent ambiguity of natural language by exploiting different semantic techniques and technologies. The authors have conducted several experiments in a media company, which validated the performance and applicability of the system. Outcomes emerging from this work could be extended to other domains of interest, such as online stores, streaming platforms, or digital libraries, to name a few.

A Novel Ensemble Learning Approach for Stock Market Prediction Based on Sentiment Analysis and the Sliding Window Method

Financial news disclosures provide valuable information for traders and investors while making stock market investment decisions. Essential but challenging, the stock market prediction problem has attracted significant attention from both researchers and practitioners. Conventional machine learning models often fail to interpret the content of financial news due to the complexity and ambiguity of natural language used in the news. Inspired by the success of recurrent neural networks (RNNs) in sequential data processing, we propose an ensemble RNN approach (long short-term memory, gated recurrent unit, and SimpleRNN) to predict stock market movements. To avoid extracting tens of thousands of features using traditional natural language processing methods, we apply sentiment analysis and the sliding window method to extract only the most representative features. Our experimental results confirm the effectiveness of these two methods for feature extraction and show that the proposed ensemble approach is able to outperform other models under comparison.

Cheating Automatic Short Answer Grading with the Adversarial Usage of Adjectives and Adverbs

Automatic grading models are valued for the time and effort saved during the instruction of large student bodies. Especially with the increasing digitization of education and interest in large-scale standardized testing, the popularity of automatic grading has risen to the point where commercial solutions are widely available and used. However, for short answer formats, automatic grading is challenging due to natural language ambiguity and versatility. While automatic short answer grading models are beginning to compare to human performance on some datasets, their robustness, especially to adversarially manipulated data, is questionable. Exploitable vulnerabilities in grading models can have far-reaching consequences ranging from cheating students receiving undeserved credit to undermining automatic grading altogether—even when most predictions are valid. In this paper, we devise a black-box adversarial attack tailored to the educational short answer grading scenario to investigate the grading models’ robustness. In our attack, we insert adjectives and adverbs into natural places of incorrect student answers, fooling the model into predicting them as correct. We observed a loss of prediction accuracy between 10 and 22 percentage points using the state-of-the-art models BERT and T5. While our attack made answers appear less natural to humans in our experiments, it did not significantly increase the graders’ suspicions of cheating. Based on our experiments, we provide recommendations for utilizing automatic grading systems more safely in practice.

Formalizing UML State Machines for Automated Verification – A Survey

The Unified Modeling Language (UML) is a standard for modeling dynamic systems. UML behavioral state machines are used for modeling the dynamic behavior of object-oriented designs. The UML specification, maintained by the Object Management Group (OMG), is documented in natural language (in contrast to formal language). The inherent ambiguity of natural languages may introduce inconsistencies in the resulting state machine model. Formalizing UML state machine specification aims at solving the ambiguity problem and at providing a uniform view to software designers and developers. Such a formalization also aims at providing a foundation for automatic verification of UML state machine models, which can help to find software design vulnerabilities at an early stage and reduce the development cost. We provide here a comprehensive survey of existing work from 1997 to 2021 related to formalizing UML state machine semantics for the purpose of conducting model checking at the design stage.

FOLL-E: Teaching First Order Logic to Children

First-order logic (FO) is an important foundation of many domains, including computer science and artificial intelligence. In recent efforts to teach basic CS and AI concepts to children, FO has so far remained absent. In this paper, we examine whether it is possible to design a learning environment that both motivates and enables children to learn the basics of FO. The key components of the learning environment are a syntax-free blocks-based notation for FO, graphics-based puzzles to solve, and a tactile environment which uses computer vision to allow the children to work with wooden blocks. The resulting FOLL-E system is intended to sharpen childrens' reasoning skills, encourage critical thinking and make them aware of the ambiguities of natural language. During preliminary testing with children, they reported that they found the notation intuitive and inviting, and that they enjoyed interacting with the application.

Converting Natural Language To SQL Queries Using LSTM

bstract: In today's world, not everyone is familiar with using Structured Query Language (SQL). This makes it hard for users to understand or create complex SQL queries. What we need is an improved application with a smarter interface that can bridge the gap between novice users and databases. Databases are great at managing data, but to understand their structure, users have to learn SQL. This poses a challenge for non-experts who aren't well-versed in SQL. What they need is a system that allows them to interact with databases in natural language. The system should be capable of understanding and responding to natural language commands. To achieve this objective, we utilize a range of end-to-end deep learning models, as well as probability models like conditional random field. The ambiguity in natural language makes it exceedingly difficult to determine the exact meaning of every word, therefore it is a difficult process to map individual keywords to the description of the schema and the contents of the underlying database. Accurate predictions can help us avoid unnecessary trouble. If we apply machine learning tools, we can skip the complicated process.

Trust, understanding, and machine translation: the task of translation and the responsibility of the translator

AbstractCould translation be fully automated? We must first acknowledge the complexity, ambiguity, and diversity of natural languages. These aspects of natural languages, when combined with a particular dilemma known as the computational dilemma, appear to imply that the machine translator faces certain obstacles that a human translator has already managed to overcome. At the same time, science has not yet solved the problem of how human brains process natural languages and how human beings come to acquire natural language understanding. We will then distinguish between the task of translation and the responsibility of the translator. Thereafter, we will conduct a survey of the methods of machine translation (viz. RBMT, SMT, NMT, foundation models or large language models). These methods will then be critically evaluated both in general and relative to Bar-Hillel’s hypothesis about the impossibility of fully automatic, high-quality machine translation (Fahqmt). Some concluding remarks will be made about the scope, prospects, and limits of machine translation.

Element quality indicator: A quality assessment and defect detection method for software requirement specification

A software requirements specification (SRS) provides a detailed description of the requirements of a software system that is to be developed. The Element Quality Indicator (EQI) is a novel method to detect defects and assess the quality of an SRS. It does not hinge on review guidelines and is based on the SRS element questions extraction method (EQEM). In this study, we optimized the EQI and carried out a systematic and comprehensive experiment to validate and evaluate its effectiveness. The controlled experiment, which included 60 software engineering students, found that 100% of the subjects identified defects in the SRS using EQI. Moreover, the results indicated that the average number of defects detected with EQI was greater than that of the classical review technique - perspective-based reading. Furthermore, the controlled experiment demonstrated that EQI provides a comparatively objective and accurate evaluation of the quality of the SRS and markedly diminishes the bias in understanding software requirements due to the ambiguity of natural language.

DETECTION OF COMPLEX SEMANTICS FROM UNSTRUCTURED DATA USING NLP & CONVOLUTION NEURAL NETWORK TECHNIQUE

The majority of data on computers nowadays still takes the form of unstructured text. The inherent ambiguity of natural language makes it incredibly difficult but also highly profitable to find hidden information or comprehend complex semantics in unstructured text. In this paper, we present combination of Natural Language Processing (NLP) and Convolution Neural Network (CNN) hybrid architecture for detection of complex semantics from unstructured data that enables different users to make understand formal semantic knowledge to be extracted from an unstructured text corpus. Keywords— Convolution Neural Network, Natural Language Processing, Controlled Natural Language, Text Mining, Information Extraction.

The Logical Form and the Ambiguities of Natural Language: The Critics from Postal

The essay discusses which type of ambiguities is better to be eliminated by using the logical perfect language in logical form, discusses the range of the p-complement problem that mind-possessing entity could solve, by analyzing Hasegawa’s examples and Portal’s criticizes, the lexical and syntactic ambiguities, and makes a comparison of the meaning and properties of “entity” between linguistics and metaphysics.

PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation.

Generative text-to-image models have gained great popularity among the public for their powerful capability to generate high-quality images based on natural language prompts. However, developing effective prompts for desired images can be challenging due to the complexity and ambiguity of natural language. This research proposes PromptMagician, a visual analysis system that helps users explore the image results and refine the input prompts. The backbone of our system is a prompt recommendation model that takes user prompts as input, retrieves similar prompt-image pairs from DiffusionDB, and identifies special (important and relevant) prompt keywords. To facilitate interactive prompt refinement, PromptMagician introduces a multi-level visualization for the cross-modal embedding of the retrieved images and recommended keywords, and supports users in specifying multiple criteria for personalized exploration. Two usage scenarios, a user study, and expert interviews demonstrate the effectiveness and usability of our system, suggesting it facilitates prompt engineering and improves the creativity support of the generative text-to-image model.

Intelligent Conversational Agents for Ambient Computing

We are in the midst of an AI revolution. Three primary disruptive changes set off this revolution: 1) increase in compute power, mobile internet, and advances in deep learning. The next decade is expected to be about the proliferation of Internet-of-Things (IoT) devices and sensors, which will generate exponentially larger amounts of data to reason over and pave the way for ambient computing. This will also give rise to new forms of interaction patterns with these systems. Users will have to interact with these systems under increasingly richer context and in real-time. Conversational AI has a critical role to play in this revolution, but only if it delivers on its promise of enabling natural, frictionless, and personalized interactions in any context the user is in, while hiding the complexity of these systems through ambient intelligence. However, current commercial conversational AI systems are trained primarily with a supervised learning paradigm, which is difficult, if not impossible, to scale by manually annotating data for increasingly complex sets of contextual conditions. Inherent ambiguity in natural language further complicates the problem. We need to devise new forms of learning paradigms and frameworks that will scale to this complexity. In this talk, we present some early steps we are taking with Alexa, Amazon's Conversational AI system, to move from supervised learning to self-learning methods, where the AI relies on customer interactions for supervision in our journey to ambient intelligence. Date: 14 July 2022.

Can Humans Detect Malicious Always-Listening Assistants? A Framework for Crowdsourcing Test Drives

As intelligent voice assistants become more widespread and the scope of their listening increases, they become attractive targets for attackers. In the future, a malicious actor could train voice assistants to listen to audio outside their purview, creating a threat to users' privacy and security. How can this misbehavior be detected? Due to the ambiguities of natural language, people may need to work in conjunction with algorithms to determine whether a given conversation should be heard. To investigate how accurately humans can perform this task, we developed a framework for people to conduct "Test Drives" of always-listening services: after submitting sample conversations, users receive instant feedback about whether these would have been captured. Leveraging a Wizard of Oz interface, we conducted a study with 200 participants to determine whether they could detect one of four types of attacks on three different services. We studied the behavior of individuals, as well as groups working collaboratively, and investigated the effects of task framing on performance. We found that individuals were able to successfully detect malicious apps at varying rates (7.5% to 75%), depending on the type of malicious attack, and that groups were highly successful when considered collectively. Our results suggest that the Test Drive framework can be an effective tool for studying user behaviors and concerns, as well as a potentially welcome addition to voice assistant app stores, where it could decrease privacy concerns surrounding always-listening services.

Traduction d’unités polylexicales du portugais en français par MT@EC et eTranslation

Translation of Multi-Word Units from Portuguese into French by MT@EC and eTranslation
 This paper aims to determine the extent to which the shift from statistical machine translation (SMT) to neural machine translation (NMT) improved the performance of European Union machine translation systems between 2015 and 2021 in terms of multi-word unit translation and domain coverage. To do so, we chose to test these systems on machine translation into French of multi-word units expressing quantitative and qualitative progression in Portuguese from Portugal. These units consist of the 2-gram ‘cada vez’ and a comparative adjective or adverb (cada vez COMP), and their word-for-word translation into French is not idiomatic (*chaque fois COMP). The most frequent translation into French is ‘de COMP en COMP’. This implies that these multi-word units must be translated ‘en bloc’, but their identification is not straightforward. On the one hand, COMP is not fixed and may include one (mais / plus, menos / moins, maior / plus grand, menor / plus petit, melhor / meilleur – mieux, pior / pire – plus mal) or several words (mais or menos N, ADJ, ADV). On the other hand, the 2-gram ‘cada vez’ can be part of other multi-word units expressing iteration (de cada vez (que)/(à) chaque fois (que)), or ‘dropper’ ([a certain quantity] de cada vez/ à la fois), This raises the challenge of ambiguity, well known to biotranslators and still often problematic for NMT. Moreover, units expressing quantitative or qualitative progression may raise other translation challenges when they are coordinate (with or without repetition of the 2-gram ‘cada vez’), when they are split (cada vez (…) COMP), or when they combine with verbs or nouns to form extended translation units whose translation into French can result in a more concise solution we refer to as ‘lexicalisation’. We established a biotranslation model based on a manually aligned French-Portuguese parallel literary corpus and online searchable French-Portuguese aligned corpora (translation memories). We selected a sample of occurrences of these multi-word units including several translation challenges. These occurrences were selected from a Portuguese journalistic corpus. They belong therefore to general language, whereas the EU's translation memories cover the domains dealt with by its institutions, which represents an additional challenge, considering the critical importance of domain coverage in the data to NMT performance quality. The selected occurrences were translated into French by the EU SMT system in 2015 (MT@EC) and 2019 (eTranslation Legacy) and by eTranslation (the EU NMT system) in 2019 and 2021. Firstly, MT output was analysed according to two general criteria: ‘non- literality’, that is translation into French without ‘chaque’, and acceptability from a semantic point of view, that is MT output without any false meaning, opposite meaning or nonsense. Then we looked at specific challenges, some of which could lead to original solutions, worthy of a professional human translator, such as lexicalisation, change of grammatical category or ‘recategorisation’ and ‘naturalisation’, that is phraseological or syntactic rearrangement that makes the target text more idiomatic. The results show that MT is improving, especially according to the criterion of non-literality. Original solutions are still rare, but they are diversifying in NMT output. Nevertheless, NMT remains imperfect, not least because of the inherent ambiguity of natural languages and the inevitable gaps in the data on which these systems are based. The results also demonstrate the importance of human intervention in the maintenance of the systems learning automatically, since the quality of SMT system’s output decreases between 2015 and 2019, when all efforts were focused on improving EU NMT system. Finally, results reveal the dangers of using English as a pivot language when translating from one Romance language into another, and the need to train future translators in NMT and post-editing.