Language Understanding Techniques Research Articles

Natural Language Understanding for Navigation of Service Robots in Low-Resource Domains and Languages: Scenarios in Spanish and Nahuatl

Human–robot interaction is becoming increasingly common to perform useful tasks in everyday life. From the human–machine communication perspective, achieving effective interaction in natural language is one challenge. To address it, natural language processing strategies have recently been used, commonly following a supervised machine learning framework. In this context, most approaches rely on the use of linguistic resources (e.g., taggers or embeddings), including training corpora. Unfortunately, such resources are scarce for some languages in specific domains, increasing the complexity of solution approaches. Motivated by these challenges, this paper explores deep learning methods for understanding natural language commands emitted to service robots that guide their movements in low-resource scenarios, defined by the use of Spanish and Nahuatl languages, for which linguistic resources are scarcely unavailable for this specific task. Particularly, we applied natural language understanding (NLU) techniques using deep neural networks and transformers-based models. As part of the research methodology, we introduced a labeled dataset of movement commands in the mentioned languages. The results show that models based on transformers work well to recognize commands (intent classification task) and their parameters (e.g., quantities and movement units) in Spanish, achieving a performance of 98.70% (accuracy) and 96.96% (F1) for the intent classification and slot-filling tasks, respectively). In Nahuatl, the best performance obtained was 93.5% (accuracy) and 88.57% (F1) in these tasks, respectively. In general, this study shows that robot movements can be guided in natural language through machine learning models using neural models and cross-lingual transfer strategies, even in low-resource scenarios.

Analysis of Digital Information in Storage Devices Using Supervised and Unsupervised Natural Language Processing Techniques

Due to the advancement of technology, cybercrime has increased considerably, making digital forensics essential for any organisation. One of the most critical challenges is to analyse and classify the information on devices, identifying the relevant and valuable data for a specific purpose. This phase of the forensic process is one of the most complex and time-consuming, and requires expert analysts to avoid overlooking data relevant to the investigation. Although tools exist today that can automate this process, they will depend on how tightly their parameters are tuned to the case study, and many lack support for complex scenarios where language barriers play an important role. Recent advances in machine learning allow the creation of new architectures to significantly increase the performance of information analysis and perform the intelligent search process automatically, reducing analysis time and identifying relationships between files based on initial parameters. In this paper, we present a bibliographic review of artificial intelligence algorithms that allow an exhaustive analysis of multimedia information contained in removable devices in a forensic process, using natural language processing and natural language understanding techniques for the automatic classification of documents in seized devices. Finally, some of the open challenges technology developers face when generating tools that use artificial intelligence techniques to analyse the information contained in documents on seized devices are reviewed.

Ad-Hoc Monitoring of COVID-19 Global Research Trends for Well-Informed Policy Making

The COVID-19 pandemic has affected millions of people worldwide with severe health, economic, social, and political implications. Healthcare Policy Makers (HPMs) and medical experts are at the core of responding to this continuously evolving pandemic situation and are working hard to contain the spread and severity of this relatively unknown virus. Biomedical researchers are continually discovering new information about this virus and communicating the findings through scientific articles. As such, it is crucial for HPMs and funding agencies to monitor the COVID-19 research trend globally on a regular basis. However, given the influx of biomedical research articles, monitoring COVID-19 research trends has become more challenging than ever, especially when HPMs want on-demand guided search techniques with a set of topics of interest in mind. Unfortunately, existing topic trend modeling techniques are unable to serve this purpose as (1) traditional topic models are unsupervised, and (2) HPMs in different regions may have different topics of interest that they want to track.    To address this problem, we introduce a novel computational task in this article called Ad-Hoc Topic Tracking , which is essentially a combination of zero-shot topic categorization and the spatio-temporal analysis task. We then propose multiple zero-shot classification methods to solve this task by building on state-of-the-art language understanding techniques. Next, we picked the best-performing method based on its accuracy on a separate validation dataset and then applied it to a corpus of recent biomedical research articles to track COVID-19 research endeavors across the globe using a spatio-temporal analysis. A demo website has also been developed for HPMs to create custom spatio-temporal visualizations of COVID-19 research trends. The research outcomes demonstrate that the proposed zero-shot classification methods can potentially facilitate further research on this important subject matter. At the same time, the spatio-temporal visualization tool will greatly assist HPMs and funding agencies in making well-informed policy decisions for advancing scientific research efforts.

Fusing external knowledge resources for natural language understanding techniques: A survey

Knowledge resources, e.g. knowledge graphs, which formally represent essential semantics and information for logic inference and reasoning, can compensate for the unawareness nature of many natural language processing techniques based on deep neural networks. This paper provides a focused review of the emerging but intriguing topic that fuses quality external knowledge resources in improving the performance of natural language processing tasks. Existing methods and techniques are summarised in three main categories: (1) static word embeddings, (2) sentence-level deep learning models, and (3) contextualised language representation models, depending on when, how and where external knowledge is fused into the underlying learning models. We focus on the solutions to mitigate two issues: knowledge inclusion and inconsistency between language and knowledge. Details on the design of each representative method, as well as their strength and limitation, are discussed. We also point out some potential future directions in view of the latest trends in natural language processing research.

Bots in software engineering: a systematic mapping study.

Bots have emerged from research prototypes to deployable systems due to the recent developments in machine learning, natural language processing and understanding techniques. In software engineering, bots range from simple automated scripts to decision-making autonomous systems. The spectrum of applications of bots in software engineering is so wide and diverse, that a comprehensive overview and categorization of such bots is needed. Existing works considered selective bots to be analyzed and failed to provide the overall picture. Hence it is significant to categorize bots in software engineering through analyzing why, what and how the bots are applied in software engineering. We approach the problem with a systematic mapping study based on the research articles published in this topic. This study focuses on classification of bots used in software engineering, the various dimensions of the characteristics, the more frequently researched area, potential research spaces to be explored and the perception of bots in the developer community. This study aims to provide an introduction and a broad overview of bots used in software engineering. Discussions of the feedback and results from several studies provide interesting insights and prospective future directions.

How Clinicians Perceive Artificial Intelligence-Assisted Technologies in Diagnostic Decision Making: Mixed Methods Approach.

BackgroundWith the rapid development of artificial intelligence (AI) and related technologies, AI algorithms are being embedded into various health information technologies that assist clinicians in clinical decision making.ObjectiveThis study aimed to explore how clinicians perceive AI assistance in diagnostic decision making and suggest the paths forward for AI-human teaming for clinical decision making in health care.MethodsThis study used a mixed methods approach, utilizing hierarchical linear modeling and sentiment analysis through natural language understanding techniques.ResultsA total of 114 clinicians participated in online simulation surveys in 2020 and 2021. These clinicians studied family medicine and used AI algorithms to aid in patient diagnosis. Their overall sentiment toward AI-assisted diagnosis was positive and comparable with diagnoses made without the assistance of AI. However, AI-guided decision making was not congruent with the way clinicians typically made decisions in diagnosing illnesses. In a quantitative survey, clinicians reported perceiving current AI assistance as not likely to enhance diagnostic capability and negatively influenced their overall performance (β=–0.421, P=.02). Instead, clinicians’ diagnostic capabilities tended to be associated with well-known parameters, such as education, age, and daily habit of technology use on social media platforms.ConclusionsThis study elucidated clinicians’ current perceptions and sentiments toward AI-enabled diagnosis. Although the sentiment was positive, the current form of AI assistance may not be linked with efficient decision making, as AI algorithms are not well aligned with subjective human reasoning in clinical diagnosis. Developers and policy makers in health could gather behavioral data from clinicians in various disciplines to help align AI algorithms with the unique subjective patterns of reasoning that humans employ in clinical diagnosis.

Unsupervised Causal Knowledge Extraction from Text using Natural Language Inference (Student Abstract)

In this paper, we address the problem of extracting causal knowledge from text documents in a weakly supervised manner. We target use cases in decision support and risk management, where causes and effects are general phrases without any constraints. We present a method called CaKNowLI which only takes as input the text corpus and extracts a high-quality collection of cause-effect pairs in an automated way. We approach this problem using state-of-the-art natural language understanding techniques based on pre-trained neural models for Natural Language Inference (NLI). Finally, we evaluate the proposed method on existing and new benchmark data sets.

Human-Centric Relation Segmentation: Dataset and Solution.

Vision and language understanding techniques have achieved remarkable progress, but currently it is still difficult to well handle problems involving very fine-grained details. For example, when the robot is told to "bring me the book in the girl's left hand", most existing methods would fail if the girl holds one book respectively in her left and right hand. In this work, we introduce a new task named human-centric relation segmentation (HRS), as a fine-grained case of HOI-det. HRS aims to predict the relations between the human and surrounding entities and identify the relation-correlated human parts, which are represented as pixel-level masks. For the above exemplar case, our HRS task produces results in the form of relation triplets 〈girl [left hand], hold, book 〉 and exacts segmentation masks of the book, with which the robot can easily accomplish the grabbing task. Correspondingly, we collect a new Person In Context (PIC) dataset for this new task, which contains 17,122 high-resolution images and densely annotated entity segmentation and relations, including 141 object categories, 23 relation categories and 25 semantic human parts. We also propose a Simultaneous Matching and Segmentation (SMS) framework as a solution to the HRS task. It contains three parallel branches for entity segmentation, subject object matching and human parsing respectively. Specifically, the entity segmentation branch obtains entity masks by dynamically-generated conditional convolutions; the subject object matching branch detects the existence of any relations, links the corresponding subjects and objects by displacement estimation and classifies the interacted human parts; and the human parsing branch generates the pixelwise human part labels. Outputs of the three branches are fused to produce the final HRS results. Extensive experiments on PIC and V-COCO datasets show that the proposed SMS method outperforms baselines with the 36 FPS inference speed. Notably, SMS outperforms the best performing baseline m-KERN with only 17.6 percent time cost. The dataset and code will be released at http://picdataset.com/challenge/index/.

A natural human language framework for digital forensic readiness in the public cloud

ABSTRACT Currently, about half of all global enterprises are adopting and using some form of cloud computing services. In cloud computing, potential digital evidence is distributed across multiple isolated virtual machine instances. Investigating deleted or inactive virtual instances of a cloud is a challenge to digital forensics, and the traditional methods of digital forensics are inadequate to address such digital forensic investigation. Users of the public cloud (whether a potential victim of a cyberattack, a cybercriminal or a digital forensic investigator) inherently communicate using natural human language in the form of sentences and semantics in document messaging such as texts, emails or instant messages. Consequently, natural human language interaction provides a unique identifier for cloud users. This study leverages the natural human language as an identifier to develop a novel digital forensic readiness (DFR) framework for cloud computing to detect cybercrime. The DFR framework comprises the integration of natural language processing techniques in designing a process that mimics a near real-time approach towards cybercrime detection in a cloud environment. Natural language understanding techniques are used to analyse textdata of users in the public cloud and textdata of reported cybercrimes to develop a DFR framework. In the preliminary formation of the DFR framework, the output shows that cybercrime attacks that are in progress in the form of textdata such as online documents, instant messages or emails within an organizational cloud domain can be identified, and potentially investigated swiftly, using the unique signature of users as identifiers. When adopted, the proposed DFR framework can minimize the time lapses in incident identification and reduce the subsequent investigation time of cybercrimes in the public cloud domain.

A Compression-based BiLSTM for Treating Teenagers’ Depression Chatbot

Anxiety is a psychological condition that often occurs during adolescence. Due to lack of relief and counseling, teenager’s psychological anxiety may gradually develop into anxiety. Chabot can be used as a new tool to relieve anxiety among teenagers. However, the natural language understanding techniques currently applied to Chabot still have problems, such as lack of effective data, high training complexity, and lack of interpretability of the network. This paper proposes a compression-based bidirectional Long Short-Term Memory depth neural network structure. The main objective is to reduce the complexity of the parameters further, and to make the network of each layer have certain interpretability by means of the reduction of sparsity. Under our own collection of teen depression text data, this structure shows a better performance than traditional networks.

Apparatus and methods for speaker verification/identification/classification employing non-acoustic and/or acoustic models and databases

A method and apparatus for securing access to a service or facility employing automatic speech recognition, text-independent speaker identification, natural language understanding techniques and additional dynamic and static features. The method includes the steps of receiving and decoding speech containing indicia of the speaker such as a name, address or customer number; accessing a database containing information on candidate speakers; questioning the speaker based on the information; receiving, decoding and verifying an answer to the question; obtaining a voice sample of the speaker and verifying the voice sample against a model; generating a score based on the answer and the voice sample; and granting access if the score is equal to or greater than a threshold. Alternatively, the method includes the steps of receiving and decoding speech containing indicia of the speaker; generating a sub-list of speaker candidates having indicia substantially matching the speaker; activating databases containing information about the speaker candidates in the sub-list; performing voice classification analysis; eliminating speaker candidates based on the voice classification analysis; questioning the speaker regarding the information; eliminating speaker candidates based on the answer; and iteratively repeating prior steps until one speaker candidate (in which case the speaker is granted access), or no speaker candidate remains (in which case the speaker is not granted access).

The DARPA TIPSTER project

This note is the first of four papers in this issue describing the ongoing work connected with the DARPA TIPSTER Project. The note provides an overview of the project, and the next papers by three of the contractors involved in the project provide some details on the systems involved, and some of the initial results.The TIPSTER project is sponsored by the Software and Intelligent Systems Technology Office of the Defense Advanced Research Projects Agency (DARPA/SISTO) in an effort to significantly advance the state of the art in effective document detection (information retrieval) and data extraction from large, real-world data collections. The first two-year phase of the program is concerned with the development of algorithms for document retrieval, document routing, and data extraction that are both domain and language independent. A call for proposals was made in June of 1990, and contracts for the six participating groups were let in the fall of 1991. Three meetings have been held so far, with the first results presented in September of 1992.There are two separate, but connected parts of TIPSTER. The first part of the project, document detection, is concerned with retrieving relevant documents" from very large (3 gigabyte) collections of documents, both in a routing environment, and in an adhoc retrieval environment. The routing environment is similar to the document filtering or profile searches currently done in libraries, where a query topic is constant, and the documents are viewed as the incoming stream of publications. The adhoc part of the project is similar to the standard search done against static collections.The second part of the TIPSTER project is concerned with data extraction. Here it is assumed that there is a much smaller set of documents, presumed to be mostly relevant to a topic, and the goal is to extract information to fill a database. This database could then be used for many applications, such as question-answering systems, report writing, or data analysis. The data extraction part of TIPSTER is being done by groups using natural language understanding techniques, and this part will not be described in this issue.