Natural Language Understanding

Notes:

Natural-language understanding (NLU) is a subfield of natural language processing (NLP) that focuses on enabling computers to understand and interpret human language in a natural and intuitive way. NLU technology is based on advanced machine learning algorithms and computational linguistics, which allow it to analyze the meaning and intent behind the user’s input. NLU is often used in conjunction with other NLP technologies, such as natural language generation or speech recognition, to create more complete and robust language processing systems. NLU can be used in a variety of applications, such as virtual assistants, chatbots, or other interactive systems. It is a key component of many dialogue systems, and can help improve the system’s ability to understand and respond to user input in a natural and meaningful way.

Wikipedia:

References:

See also:

Language Understanding Engines | Language Understanding Module | Story Understanding Systems | VUE (Visual Understanding Environment)

Natural Language Understanding
M Lapata – 2014 – Citeseer
Run your sampler for 64 iterations, using ?= 1 and ?= 0.01, on the data set provided. Compare the distribution of words in each topic found by the sampler, as output by your lda. print final (), to the original distribution used to create the data set. Does the sampler appear …

Application of deep belief networks for natural language understanding
R Sarikaya, GE Hinton, A Deoras – IEEE/ACM Transactions on …, 2014 – ieeexplore.ieee.org
Applications of Deep Belief Nets (DBN) to various problems have been the subject of a number of recent studies ranging from image classification and speech recognition to audio classification. In this study we apply DBNs to a natural language understanding problem …

Natural Language Understanding
D Fischer – dan.f3c.com
Humans take the ability to understand and use languages as a central feature of their” intelligence”. Linguistic capabilities are perceived as” what makes us different from apes”, as the foundation of our cultures, and as a measure of overall intelligence of an individual. No …

Natural Language Understanding
JF Sowa, AK Majumdar – 2015 – researchgate.net
? Have we been using the right theories, tools, and techniques?? Why haven’t these tools worked as well as we had hoped?? What other methods might be more promising?? What can research in neuroscience and psycholinguistics tell us?? Can it suggest better ways of …

Natural Language Understanding
F Keller – 2016 – inf.ed.ac.uk
… Natural Language Understanding Lecture 10: Introduction to Unsupervised Part-of-Speech Tagging Frank Keller School of Informatics University of Edinburgh keller@inf.ed.ac.uk Based on slides by Sharon Goldwater February …

Natural Language Understanding
BT Time – 2018 – inf.ed.ac.uk
Page 1. Natural Language Understanding Lecture 12: Recurrent Neural Networks and LSTMs Adam Lopez Credits: Mirella Lapata and Frank Keller 26 January 2018 School of Informatics University of Edinburgh alopez@inf.ed.ac.uk 1 Recap: probability, language models, and …

Natural Language Understanding
A Lopez – 2018 – inf.ed.ac.uk
Lecture 2: Revision of neural networks and backpropagation … Adam Lopez Credits: Mirella Lapata and Frank Keller 19 January 2018 … School of Informatics University of Edinburgh alopez@inf.ed.ac.uk … • Neuron receives inputs and combines these in the cell body. • If the …

Do multi-sense embeddings improve natural language understanding?
J Li, D Jurafsky – arXiv preprint arXiv:1506.01070, 2015 – arxiv.org
Abstract: Learning a distinct representation for each sense of an ambiguous word could lead to more powerful and fine-grained models of vector-space representations. Yet whilemulti-sense’methods have been proposed and tested on artificial word-similarity tasks, we don’t …

Enhanced English Universal Dependencies: An Improved Representation for Natural Language Understanding Tasks.
S Schuster, CD Manning – LREC, 2016 – nlp.stanford.edu
Abstract Many shallow natural language understanding tasks use dependency trees to extract relations between content words. However, strict surface-structure dependency trees tend to follow the linguistic structure of sentences too closely and frequently fail to provide …

Spoken language understanding for natural interaction: The siri experience
JR Bellegarda – Natural Interaction with Robots, Knowbots and …, 2014 – Springer
… solutions. This has sparked interest in a more pervasive spoken language interface, in its most inclusive definition encompassing speech recognition, speech synthesis, natural language understanding, and dialog management …

BEETLE II: Deep natural language understanding and automatic feedback generation for intelligent tutoring in basic electricity and electronics
M Dzikovska, N Steinhauser, E Farrow, J Moore… – International Journal of …, 2014 – Springer
Abstract Within STEM domains, physics is considered to be one of the most difficult topics to master, in part because many of the underlying principles are counter-intuitive. Effective teaching methods rely on engaging the student in active experimentation and encouraging …

Towards a model of constructional meaning for natural language understanding
C Periñán-Pascual – … into Functional Linguistics: The role of …, 2013 – books.google.com
Few researchers in natural language processing are nowadays concerned with linguistically-aware applications. On the contrary, the prevailing trend is towards the search of engineering solutions to practical problems, where researchers are motivated by the …

Mivar thechnologies in mathematical modeling of natural language, images and human speech understanding
OO Varlamov, LE Adamova, DV Eliseev… – International Journal of …, 2013 – elibrary.ru
?????. ?????. ??????????? ????? …

Effective and Robust Natural Language Understanding for Human-Robot Interaction.
E Bastianelli, G Castellucci, D Croce, R Basili, D Nardi – ECAI, 2014 – books.google.com
Abstract. Robots are slowly becoming part of everyday life, as they are being marketed for commercial applications (viz. telepresence, cleaning or entertainment). Thus, the ability to interact with non-expert users is becoming a key requirement. Even if user utterances can be …

Learning executable semantic parsers for natural language understanding
P Liang – Communications of the ACM, 2016 – dl.acm.org
Semantic parsers map input utterances into semantic representations called logical forms that support this form of reasoning. For example, the first utterance listed previously would map onto the logical form max (primes?(??, 10)). We can think of the logical form as a …

Natural language understanding with distributed representation
K Cho – arXiv preprint arXiv:1511.07916, 2015 – arxiv.org
Abstract: This is a lecture note for the course DS-GA 3001< Natural Language Understanding with Distributed Representation> at the Center for Data Science, New York University in Fall, 2015. As the name of the course suggests, this lecture note introduces …

Domain adaptation of recurrent neural networks for natural language understanding
A Jaech, L Heck, M Ostendorf – arXiv preprint arXiv:1604.00117, 2016 – arxiv.org
Abstract: The goal of this paper is to use multi-task learning to efficiently scale slot filling models for natural language understanding to handle multiple target tasks or domains. The key to scalability is reducing the amount of training data needed to learn a model for a new …

Natural language understanding for soft information fusion
SC Shapiro, DR Schlegel – Information Fusion (FUSION), 2013 …, 2013 – ieeexplore.ieee.org
Tractor is a system for understanding English messages within the context of hard and soft information fusion for situation assessment. Tractor processes a message through syntactic processors, and represents the result in a formal knowledge representation language. The …

End-to-end joint learning of natural language understanding and dialogue manager
X Yang, YN Chen, D Hakkani-Tür… – … , Speech and Signal …, 2017 – ieeexplore.ieee.org
Natural language understanding and dialogue policy learning are both essential in conversational systems that predict the next system actions in response to a current user utterance. Conventional approaches aggregate separate models of natural language  …

Targeted feature dropout for robust slot filling in natural language understanding
P Xu, R Sarikaya – Fifteenth Annual Conference of the International …, 2014 – isca-speech.org
Abstract In slot filling with conditional random field (CRF), the strong current word and dictionary features tend to swamp the effect of contextual features, a phenomenon also known as feature undertraining. This is a dangerous tradeoff especially when training data is …

Multi-purpose natural language understanding linked to sensorimotor experience in humanoid robots
E Ovchinnikova, M Wachter… – … ), 2015 IEEE-RAS …, 2015 – ieeexplore.ieee.org
Humans have an amazing ability to bootstrap new knowledge. The concept of structural bootstrapping refers to mechanisms relying on prior knowledge, sensorimotor experience, and inference that can be implemented in robotic systems and employed to speed up …

Situated incremental natural language understanding using markov logic networks
C Kennington, D Schlangen – Computer Speech & Language, 2014 – Elsevier
Abstract We present work on understanding natural language in a situated domain in an incremental, word-by-word fashion. We explore a set of models specified as Markov Logic Networks and show that a model that has access to information about the visual context …

Natural language understanding tools with low language resource in building automatic indonesian mind map generator
A Purwarianti, A Saelan, I Afif, F Ferdian… – International …, 2013 – search.proquest.com
Abstract Here, we describe our work in developing Indonesian Mind Map Generator that employs several Indonesian natural language understanding tools as its main engine. The Indonesian Mind Map Generator1aims to help the user in easily making a Mind Map object …

Situated incremental natural language understanding using a multimodal, linguistically-driven update model
C Kennington, S Kousidis, D Schlangen – Proceedings of COLING 2014 …, 2014 – aclweb.org
Abstract A common site of language use is interactive dialogue between two people situated together in shared time and space. In this paper, we present a statistical model for understanding natural human language that works incrementally (ie, does not wait until the …

Graph-based methods for natural language processing and understanding—a survey and analysis
MT Mills, NG Bourbakis – IEEE Transactions on Systems, Man …, 2014 – ieeexplore.ieee.org
… Abstract—This survey and analysis presents the functional com- ponents, performance, and maturity of graph-based methods for natural language processing and natural language understanding and their potential for mature products …

Application-Independent and Integration-Friendly Natural Language Understanding.
M Eppe, S Trott, V Raghuram, JA Feldman, A Janin – GCAI, 2016 – publications.eppe.eu
Abstract Natural Language Understanding (NLU) has been a long-standing goal of AI and many related fields, but it is often dismissed as very hard to solve. NLU is required complex flexible systems that take action without further human intervention. This inherently involves …

Natural language understanding and communication for multi-agent systems
S Trott, A Appriou, J Feldman, A Janin – AAAI Fall Symposium, 2015 – aaai.org
Abstract Natural Language Understanding (NLU) studies machine language comprehension and action without human intervention. We describe an implemented system that supports deep semantic NLU for controlling systems with multiple simulated …

Towards learning efficient models for natural language understanding of quantifiable spatial relationships
J Arkin, TM Howard – … on Model Learning for Human-Robot …, 2015 – pdfs.semanticscholar.org
Abstract—Natural language interfaces for human-robot interaction offer an avenue for non-experts to efficiently cooperate with robots on a wide spectrum of tasks. While much of the literature has focused on learning qualitative descriptions of behaviors, we seek to learn …

Paraphrase features to improve natural language understanding.
X Liu, R Sarikaya, C Brockett, C Quirk… – …, 2013 – pdfs.semanticscholar.org
Abstract Natural language understanding (NLU) systems for speech applications require large quantities of annotated data. We investigate the use of a domain-independent machine-translationbased paraphrase system to improve performance without incurring the …

Generating grammars for natural language understanding from knowledge about actions and objects
A Perzylo, S Griffiths, R Lafrenz… – … and Biomimetics (ROBIO …, 2015 – ieeexplore.ieee.org
Many applications in the fields of Service Robotics and Industrial Human-Robot Collaboration, require interaction with a human in a potentially unstructured environment. In many cases, a natural language interface can be helpful, but it requires powerful means of …

Natural Language Understanding (NLU, not NLP) in Cognitive Systems.
M McShane – AI Magazine, 2017 – search.ebscohost.com
Abstract Developing cognitive agents with human-level natural language understanding (NLU) capabilities requires modeling human cognition because natural, unedited utterances are anything but neat and complete; so understanding them requires the ability to clean up …

An approach to natural language understanding
MS Marlen – 2014 – search.proquest.com
Abstract Natural Language understanding over a set of sentences or a document is a challenging problem. We approach this problem using semantic extraction and an ontology for answering questions based on the data. There is more information in a sentence than …

Natural Language Understanding Performance & Use Considerations in Virtual Medical Encounters.
TB Talbot, N Kalisch, K Christoffersen, GM Lucas… – MMVR, 2016 – books.google.com
Abstract. A virtual standardized patient (VSP) prototype was tested for natural language understanding (NLU) performance. The conversational VSP was evaluated in a controlled 61 subject study over four repetitions of a patient case. The prototype achieved more than …

Improving classification-based natural language understanding with non-expert annotation
F Morbini, E Forbell, K Sagae – Proceedings of the 15th Annual Meeting …, 2014 – aclweb.org
Abstract Although data-driven techniques are commonly used for Natural Language Understanding in dialogue systems, their efficacy is often hampered by the lack of appropriate annotated training data in sufficient amounts. We present an approach for rapid …

Addressing Big Data Problems using Semantics and Natural Language Understanding
E Khan – … on Telecommunications and Informatics (Tele-Info ’13) …, 2013 – wseas.us
Abstract–The need to solve the key problems related to Big Data in a practical and effective way is becoming very important as the data is growing very fast-already exceeding the exabyte range. There are multiple problems with big data including storage, search, transfer …

Computer simulation of mental image processing in natural language understanding by human
R Khummongkol, M Yokota – Awareness Science and …, 2015 – ieeexplore.ieee.org
The terminologynatural language’surely reminds most people of any ordinary human language that they use to communicate with each other, but as well it alludes to the most convenient way by which ordinary non-expert people can intuitively interact with artifacts …

Configuring domain knowledge for natural language understanding
M Selway, W Mayer, M Stumptner – 2013 – search.ror.unisa.edu.au
Abstract: Knowledge-based configuration has been used for numerous applications including natural language processing (NLP). By formalising property grammars as a configuration problem, it has been shown that configuration can provide a flexible …

Natural language understanding and prediction: from formal grammars to large scale machine learning
N Duta – Fundamenta Informaticae, 2014 – content.iospress.com
Abstract Scientists have long dreamed of creating machines humans could interact with by voice. Although one no longer believes Turing’s prophecy that machines will be able to converse like humans in the near future, real progress has been made in the voice and text …

Knowledge representation of entity attribute frame for natural language understanding
H WU, R ZHOU, W Ke – DEStech Transactions on Computer …, 2017 – dpi-proceedings.com
Abstract The key problem in the construction of the semantic knowledge base for natural language understanding lies in the connection between knowledge, language and computation. It’s hardly to get an organized knowledge base without considering the …

IsNL? a discriminative approach to detect natural language like queries for conversational understanding.
A Celikyilmaz, G Tür, D Hakkani-Tür – INTERSPEECH, 2013 – pdfs.semanticscholar.org
… March 1992. [3] R. Kuhn and RD Mori, “The application of seman- tic classification trees to natural language understanding,” IEEE Transactions on Pattern Analysis and Machine In- telligence, vol. 17, pp. 449–460, 1995. [4] Y …

A Synthesis of Stochastic Petri Net (SPN) Graphs for Natural Language Understanding (NLU) Event/Action Association
A Psarologou, A Esposito… – Tools with Artificial …, 2015 – ieeexplore.ieee.org
This paper focuses on the combination of StochasticPetri Net (SPN) graphs for event association in the context ofNatural Languages Understanding (NLU). Our general goal isto develop a new NLU methodology. In this paper we presentsome of its components which …

Understanding Meaning and Knowledge Representation: From Theoretical and Cognitive Linguistics to Natural Language Processing
C Periñán, EM Mestre – 2016 – books.google.com
… Page 25. Introduction xxiv a lexical-conceptual knowledge base particularly designed for natural language understanding systems, and for the development of tools for the automatic processing of language (cf. Periñán-Pascual and Arcas-Túnez 2014b) …

Adaptive Convolutional Filter Generation for Natural Language Understanding
D Shen, MR Min, Y Li, L Carin – arXiv preprint arXiv:1709.08294, 2017 – arxiv.org
Abstract: Convolutional neural networks (CNNs) have recently emerged as a popular building block for natural language processing (NLP). Despite their success, most existing CNN models employed in NLP are not expressive enough, in the sense that all input …

Ask, and Shall You Receive? Understanding Desire Fulfillment in Natural Language Text.
S Chaturvedi, D Goldwasser, H Daumé III – AAAI, 2016 – aaai.org
… Abstract The ability to comprehend wishes or desires and their fulfill- ment is important to Natural Language Understanding. This paper introduces the task of identifying if a desire expressed by a subject in a given short piece of text was fulfilled …

Semantic frame-based natural language understanding for intelligent topic detection agent
YC Chang, YL Hsieh, CC Chen, WL Hsu – International Conference on …, 2014 – Springer
Abstract Detecting the topic of documents can help readers construct the background of the topic and facilitate document comprehension. In this paper, we proposed a semantic frame-based method for topic detection that simulates such process in human perception. We took …

Natural language understanding in a semantic web context
C Barrière – 2016 – Springer
I hope for this book to serve as a good starting point for students and researchers in Semantic Web (SW) interested in discovering what Natural Language Processing (NLP) has to offer. At a time when Open Data is becoming increasingly popular, there is a pressing …

Multi-step natural language understanding
P Milhorat, S Schlögl, G Chollet, J Boudy – Proceedings of the SIGDIAL …, 2013 – aclweb.org
Abstract While natural language as an interaction modality is increasingly being accepted by users, remaining technological challenges still hinder its widespread employment. Tools that better support the design, development and improvement of these types of applications are …

Architectural Mechanisms for Situated Natural Language Understanding in Uncertain and Open Worlds.
T Williams – AAAI, 2016 – aaai.org
As natural language capable robots and other agents become more commonplace, the ability for these agents to understand truly natural human speech is becoming increasingly important. What is more, these agents must be able to understand truly natural human …

Natural language understanding for partial queries
X Liu, A Celikyilmaz, R Sarikaya – … Speech Recognition and …, 2015 – ieeexplore.ieee.org
Typical natural language understanding systems are built based on the assumption that they have access to the fully formed complete queries. Today’s natural user interfaces, however, enable users to interact with various services and agents (eg search engines, personal …

Analysis of natural language understanding technology based on Semantic Web ontology
Y Wang, Z Cao, J Zhang – 2015 International Conference on …, 2015 – atlantis-press.com
Abstract—The key technology of the semantic web are include: ontology, metadata including logic and reasoning and intelligent agents display. Ontology is a formal, explicit specification of conceptualization of the domain knowledge. This paper analyses problems of natural  …

Evaluation of natural language understanding based speech dialog interface’s effectiveness regarding car navigation system usability performance
T Kojima, A Kaminuma, N Isoyama… – The Journal of the …, 2016 – asa.scitation.org
Recently, new cell phone services enable taking input by speaking to a quasi-agent using highly accurate speech recognition technologies. However, there are two problems when equipping a vehicle with these technologies. First, we do not understand yet the effect on …

Personalized Natural Language Understanding.
X Liu, R Sarikaya, L Zhao, Y Ni, YC Pan – INTERSPEECH, 2016 – isca-speech.org
Abstract Natural language understanding (NLU) is one of the critical components of dialog systems. Its aim is to extract semantic meaning from typed text input or the spoken text coming out of the speech recognizer. Traditionally, NLU systems are built in a user …

Use of background knowledge in natural language understanding for information fusion
SC Shapiro, DR Schlegel – Information Fusion (Fusion), 2015 …, 2015 – ieeexplore.ieee.org
Tractor is a system for understanding English messages within the context of hard and soft information fusion for situation assessment. Tractor processes a message through text processors, and stores the result, expressed in a formal knowledge representation …

Semi-supervised learning of statistical models for natural language understanding
D Zhou, Y He – The Scientific World Journal, 2014 – hindawi.com
Natural language understanding is to specify a computational model that maps sentences to their semantic mean representation. In this paper, we propose a novel framework to train the statistical models without using expensive fully annotated data. In particular, the input of our …

Common-sense knowledge for natural language understanding: Experiments in unsupervised and supervised settings
L Di Caro, A Ruggeri, L Cupi, G Boella – Congress of the Italian …, 2015 – Springer
Abstract Research in Computational Linguistics (CL) has been growing rapidly in recent years in terms of novel scientific challenges and commercial application opportunities. This is due to the fact that a very large part of the Web content is textual and written in many …

Reading Twice for Natural Language Understanding
D Weissenborn – arXiv preprint arXiv:1706.02596, 2017 – arxiv.org
Abstract: Despite the recent success of neural networks in tasks involving natural language understanding (NLU) there has only been limited progress in some of the fundamental challenges of NLU, such as the disambiguation of the meaning and function of words in …

Evaluating natural language understanding services for conversational question answering systems
D Braun, A Hernandez-Mendez, F Matthes… – Proceedings of the 18th …, 2017 – aclweb.org
Abstract Conversational interfaces recently gained a lot of attention. One of the reasons for the current hype is the fact that chatbots (one particularly popular form of conversational interfaces) nowadays can be created without any programming knowledge, thanks to …

Large-Scale Paraphrasing for Natural Language Understanding
J Ganitkevitch – Proceedings of the 2013 NAACL HLT Student …, 2013 – aclweb.org
Abstract We examine the application of data-driven paraphrasing to natural language understanding. We leverage bilingual parallel corpora to extract a large collection of syntactic paraphrase pairs, and introduce an adaptation scheme that allows us to tackle a …

Natural language understanding for information fusion
SC Shapiro, DR Schlegel – Fusion Methodologies in Crisis Management, 2016 – Springer
Abstract Tractor is a system for understanding English messages within the context of hard and soft information fusion for situation assessment. Tractor processes a message through text processors using standard natural language processing techniques, and represents the …

An empirical investigation of word class-based features for natural language understanding
A Celikyilmaz, R Sarikaya, M Jeong… – … /ACM Transactions on …, 2016 – ieeexplore.ieee.org
There are many studies that show using class-based features improves the performance of natural language processing (NLP) tasks such as syntactic part-of-speech tagging, dependency parsing, sentiment analysis, and slot filling in natural language understanding  …

Natural language understanding and communication for human-robot collaboration
MI Bloch – ipvs.informatik.uni-stuttgart.de
Abstract Natural language understanding and communication is a key aspect of human-robot collaboration. Concerning natural language understanding, various features need to be covered for creating an overall system. Apart from semantic parsing and mapping, the …

Continuously Improving Natural Language Understanding for Robotic Systems through Semantic Parsing, Dialog, and Multi-modal Perception
J Thomason – 2016 – pdfs.semanticscholar.org
Abstract Robotic systems that interact with untrained human users must be able to understand and respond to natural language commands and questions. If a person requests “take me to Alice’s office”, the system and person must know that Alice is a person who owns …

VerbKB: A Knowledge Base of Verbs for Natural Language Understanding
DT Wijaya – 2016 – lti.cs.cmu.edu
Abstract A verb is the organizational core of a sentence. Understanding the meaning of the verb is, therefore, a key to understanding the meaning of the sentence. One of the ways we can formulate natural language understanding is by treating it as a task of mapping natural …

… Deep Queries Specified in Natural Language with Respect to a Frame Based Knowledge Base and Developing Related Natural Language Understanding …
NH Vo – 2015 – search.proquest.com
Abstract Question Answering has been under active research for decades, but it has recently taken the spotlight following IBM Watson’s success in Jeopardy! and digital assistants such as Apple’s Siri, Google Now, and Microsoft Cortana through every smart-phone and …

Navigation-orientated natural spoken language understanding for intelligent vehicle dialogue
Y Zheng, Y Liu, JHL Hansen – Intelligent Vehicles Symposium …, 2017 – ieeexplore.ieee.org
… turn-taking speech, dialect, etc. The definition and interpretation of verbal/textual- based requests or commands for navigation-related tasks yields a significant barrier in natural language understanding. In the area of academic …

Understanding Natural Language With Deep Neural Networks Using Torch
S Chintala – 2016 – devblogs.nvidia.com
This post discusses research on using GPU-accelerated Deep Neural Networks with the Torch framework and the cuDNN library for Natural Language Processing.

A Cognitive Architecture for Understanding and Producing Natural Language in Support of Robotic Creativity
A Pipitone, V Cannella, R Pirrone… – Humanoid Robots and …, 2014 – cogsci.eecs.qmul.ac.uk
… Istanbul, Turkey: ELRA, May 2012. [13] L. Steels and J. de Beule, “A (very) brief introduction to fluid con- struction grammar,” in Proceedings of the Third Workshop on Scalable Natural Language Understanding, ser. ScaNaLU ’06 …

Modeling meaning: computational interpreting and understanding of natural language fragments
M Kapustin, P Kapustin – arXiv preprint arXiv:1505.08149, 2015 – arxiv.org
… It stores quantitative information capturing the essence of the concepts, because it is crucial for working with natural language understanding and reasoning. Still, the representation is general enough to allow for new knowledge to be learned, and even generated by the system …

Word Embedding for Understanding Natural Language: A Survey
Y Li, T Yang – Guide to Big Data Applications, 2018 – Springer
… 4.1 Introduction. Natural language understanding from text data is an important field in Artificial Intelligence. As images and acoustic waves can be mathematically modeled by analog or digital signals, we also need a way to represent text data in order to process it automatically …

Knowledge Graph Exploration for Natural Language Understanding in Web Information Retrieval
M Schuhmacher – 2016 – ub-madoc.bib.uni-mannheim.de
Abstract: In this thesis, we study methods to leverage information from fully-structured knowledge bases (KBs), in particular the encyclopedic knowledge graph (KG) DBpedia, for different text-related tasks from the area of information retrieval (IR) and natural language …

Towards Natural Language Understanding using Multimodal Deep Learning
S Bos – pdfs.semanticscholar.org
Abstract This thesis describes how multimodal sensor data from a 3D sensor and microphone array can be processed with deep neural networks such that its fusion, the trained neural network, is a) more robust to noise, b) outperforms unimodal recognition and …

Exploration on Causal Law of Understanding and Fusion Linking of Natural Language
P Huang – International Conference on Intelligence Science, 2017 – Springer
To research the causation law of natural language understanding from its cognitive model is a kind of creative method which has been being developed recently. In this paper, the research situation of …

Will Repeated Reading Benefit Natural Language Understanding?
L Sha, F Qian, Z Sui – National CCF Conference on Natural Language …, 2017 – Springer
Abstract Repeated Reading (re-read), which means to read a sentence twice to get a better understanding, has been applied to machine reading tasks. But there have not been rigorous evaluations showing its exact contribution to natural language processing. In this …

Neural Network Software Library for Natural Language Understanding
P Gogishvili – BOOK OF ABSTRACTS, 2015 – gmu.ge
It is very important to have possibility to do quick testing of new approaches in order to find good solutions for particular tasks. Software library is an effective solution for creating and testing of custom neural networks. We created software library which has ready components …

Natural Language Understanding and Intelligent Applications
CY Lin, N Xue, D Zhao, X Huang, Y Feng – hlt.suda.edu.cn
Abstract. This paper describes our system designed for the NLPCC 2016 shared task on word segmentation on micro-blog texts (ie, Weibo). We treat word segmentation as a character-wise sequence labeling problem, and explore two directions to enhance our CRF …

Natural Language Understanding for Grading Essay Questions in Persian Language
I Mokhtari-Fard – … Linguistics and Natural Language Processing Based …, 2013 – Springer
Abstract Many intelligent systems are intended to communicate with users through natural language. Understanding the natural language by the computer is one of the most essential operations in natural language processing. One of the applications of natural languages is …

Knowledge-Aware Natural Language Understanding
P Dasigi – 2017 – pdfs.semanticscholar.org
Abstract Natural Language Understanding (NLU) systems need to encode human generated text (or speech) and reason over it at a deep semantic level. Any NLU system typically involves two main components: The first is an encoder, which composes words (or …

A non-biological AI approach towards natural language understanding
L Stephen, D Geert, K Andreas… – Future Technologies …, 2016 – ieeexplore.ieee.org
The problem being addressed in this paper is that using brute force in Natural Language Processing and Machine Learning combined with advanced statistics will only approximate meaning and thus will not deliver in terms of real text understanding. Counting words and …

Analysis of knowledge data discovery and mining by construction of natural language understanding system
QF Wang, HL Guo – 2015 – atlantis-press.com
Abstract. Natural language understanding mainly studies the language communicative process simulation of people with electronic computer, and the computer is able to understand and use the natural language of the human society. This paper analyzes the …

Assessment and analysis of the applicability of recurrent neural networks to natural language understanding with a focus on the problem of coreference resolution
FD Kaumanns – 2016 – edoc.ub.uni-muenchen.de
Abstract Recurrent Neural Networks erweitern das konnektionistische Prinzip der Informationsverarbeitung um eine grundlegende Fähigkeit biologischer Kognition: temporale Modellierung sequentieller Eingaben. Diese Erweiterung erlaubt einem …

A Perspective on Natural Language Understanding Capability: An Interview with Sam Bowman
V Dhar, S Bowman – Big data, 2017 – online.liebertpub.com
Prof. Bowman: I can only give a very high-level overview of the earlier part of this history, but there are three broad families of approaches to language understanding in natural language processing (NLP). From the 1960s through right around 1990, the predominant mode of …

Contextual awareness: Understanding monologic natural language instructions for autonomous robots
J Arkin, MR Walter, A Boteanu… – Robot and Human …, 2017 – ieeexplore.ieee.org
… Natural language understanding for robot instructions can be formulated as a problem of associating a free-form utter- ance with a set of semantic symbols, an instance of the “sym- bol grounding” [7] problem. Early approaches to symbol …

Natural Language Understanding in a Continuous Space
KM Hermann, N Kalchbrenner, E Grefenstette… – lxmls.it.pt
Page 1. Natural Language Understanding in a Continuous Space Karl-Moritz Hermann, Nal Kalchbrenner, Edward Grefenstette, and Phil Blunsom phil.blunsom@cs.ox.ac.uk Page 2. Features and NLP Twenty years ago log-linear models freed us from the shackles of simple …

Audio quotation marks for natural language understanding
S Boutin, R Tremblay, P Cardinal, D Peters… – … Annual Conference of …, 2015 – isca-speech.org
Abstract Detecting the presence of quotations in speech is a difficult task for automatic natural language understanding. This paper presents a study on the correlation between three prosodic features present in a voice command and the presence or absence of …

Combining Stochastic Petri Nets (SPNs) for Natural Language Understanding (NLU)
A Psarologou, N Bourbakis, A Esposito – researchgate.net
Petri Net (SPN) graphs for event association in the context of Natural Languages Understanding (NLU). We present the use of Anaphora Resolution (AR) and the extraction of kernel (s) using parsed trees that later are represented with SPN graphs. We also define …

Natural Language Understanding: Deep Learning for Abstract Meaning Representation
WR Foland Jr – 2017 – scholar.colorado.edu
Abstract In the last few years there have been major improvements in the performance of hard nat-ural language processing tasks due to the application of artificial neural network models. These models replace complex hand-engineered systems for extracting and …

Natural Language Understanding Systems: Processing Strategies and Processor Structure
VS Rubashkin – Russian Digital Libraries Journal, 2014 – elbib.ru
Abstract The paper discusses the general architecture of NLU-systems. We focus on three main subjects: target information technology and target knowledge representation language; processing levels interaction and integration; role and proportion of rule-based and corpus …

Learning Semantic Parsers for Natural Language Understanding
P Liang – pdfs.semanticscholar.org
ABSTRACT For building question answering systems and natural language interfaces, semantic parsing has emerged as an important and powerful paradigm. Semantic parsers map natural language into logical forms, the classic representation for many important …

Topic Modeling for Natural Language Understanding
X Song – 2016 – search.proquest.com
Abstract This thesis presents new topic modeling methods to reveal underlying language structures. Topic models have seen many successes in natural language understanding field. Despite these successes, the further and deeper exploration of topic modeling in …

Understanding Natural Language Processing and its Primary Aspects
A Roy, AG Majumder, A Nath – International Journal, 2017 – ijarcsms.com
… as natural language. Natural language summarization is a task which resembles this. C. Natural language understanding: This is perhaps the most important task of natural language semantics. It is a subfield of natural language …

Extending the Semantics in Natural Language Understanding
M Marlen, D Gustafson – Proceedings of the Joint Symposium on …, 2013 – aclweb.org
Abstract Natural Language understanding over a set of sentences or a document is a challenging problem. We approach this problem using semantic extraction and building an ontology for answering questions based on the data. There is more information in a …

Applying domain-specific natural language understanding techniques to film
A Calderwood – Student Research Celebration, 2017 – scholarworks.montana.edu
We report on our work involving adapting Natural Language Processing (NLP) tools, including subject-predicate-object triplet generation, to build a system capable of automatically testing if a given film or play passes the Bechdel-Wallace test, a test from …

Verb Semantics for Natural Language Understanding
DT Wijaya – pdfs.semanticscholar.org
Abstract A verb is the organizational core of a sentence. Understanding the meaning of the verb is therefore key to understanding the meaning of the sentence. Natural language understanding is the problem of mapping natural language text to its meaning …

Role of KR in Natural Language Understanding and Synergic KR
Y Lierler – cs.utexas.edu
Research in natural language understanding (NLU) focuses on the design of systems that process information expressed in natural language and use it in reasoning. Key components of such systems are responsible for (a) transforming input in natural language (NL) into logic …

Underspecification in Natural Language Understanding for Dialog Automation
J Chen, S Bangalore – … of the International Conference Recent Advances …, 2017 – acl-bg.org
Abstract With the increasing number of communication platforms that offer variety of ways of connecting two interlocutors, there is a resurgence of chat-based dialog systems. These systems, typically known as chatbots have been successfully applied in a range of consumer …

Coarse-grained parallelism in natural language understanding: parsing as message passing
S SCHACHT, UDO HAHN – New Methods In Language …, 2013 – books.google.com
This paperl surveys ParseTalk, a grammar model for natural language analysis that combines lexical organization of grammatical knowledge with lexicalized control of the corresponding parser in an object-oriented speci?cation framework. Our research takes into …

Dealing with quantifier scope ambiguity in natural language understanding
MH Manshadi – 2014 – search.proquest.com
Abstract Quantifier scope disambiguation (QSD) is one of the most challenging problems in deep natural language understanding (NLU) systems. The most popular approach for dealing with QSD is to simply leave the semantic representation (scope-) underspecified …

Situated Learning and Understanding of Natural Language
Y Artzi – 2015 – digital.lib.washington.edu
Page 1. ©Copyright 2015 Yoav Artzi Page 2. Situated Understanding and Learning of Natural Language Yoav Artzi A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy University of Washington 2015 Reading Committee …

Natural Language Understanding and Intelligent Applications: 5th CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2016 …
CY Lin, N Xue, D Zhao, X Huang, Y Feng – 2016 – books.google.com
This book constitutes the joint refereed proceedings of the 5th CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2016, and the 24th International Conference on Computer Processing of Oriental Languages, ICCPOL 2016, held in …

A Study on Image Semantic Analysis Algorithm for Natural Language Understanding
J LUO, HUAJUN WANG, YANMEI LI… – Journal of Residuals …, 2016 – dpi-journals.com
Abstract At this stage, the optimization of natural language in the process of information technology has become the most important research direction in this field. Especially the understanding and application of Chinese natural language has played an important role in …

Syllabus: CSCI 8450 Advanced Topics in Natural Language Understanding
Y Lierler – 2016 – works.bepress.com
Available at: https://works.bepress.com/yuliya_lierler/78 … M 2:20-3:00pm Th 3:00-3:40pm or by appointment … Text Core: Speech and Language Processing (Second Edition) by Daniel Jurafsky and James H. Martin … Supplementary: Natural Language Processing with Python …

Dialog Natural Language Understanding using a Generic Textual Inference System
E Segal-haLevi, I Dagan, I Ramat-Gan – events.eventact.com
Abstract One of the components of a dialog system is the Natural Language Understanding (NLU) component. This component accepts natural language text, and returns the meaning of that text, in some formal application-specific meaning representation. One of the …

Neural Conditional Random Fields for Natural Language Understanding
MAR Beauchamp – 2016 – digitool.library.mcgill.ca
Abstract This thesis presents work on Neural Conditional Random Fields (NeuroCRFs), a combination of neural network and conditional random field, applied to chunking and named entities recognition (NER), two information extraction tasks. Information extraction is a …

ASP for Abduction in Natural Language Understanding made more efficient using External Propagators
P Schüller, C Dodaro, F Ricca – 8th International Workshop, CSLP 2016 – peterschueller.com
Abstract. Answer Set Programming (ASP) is a powerful paradigm for knowledge representation and reasoning. Several tasks in Natural Language Understanding (NLU) have been or have the potential to be modeled in ASP. Among these, abduction under …

Integrating multi-purpose natural language understanding, robot’s memory, and symbolic planning for task execution in humanoid robots
M Wächter, E Ovchinnikova, V Wittenbeck… – Robotics and …, 2018 – Elsevier
Abstract We propose an approach for instructing a robot using natural language to solve complex tasks in a dynamic environment. In this study, we elaborate on a framework that allows a humanoid robot to understand natural language, derive symbolic representations of …

A Comparison and Critique of Natural Language Understanding Tools
M Canonico, L De Russis – porto.polito.it
Abstract—In the last 10 years, various cloud platforms enabled developers to easily create applications able to understand, with some limitations, natural languages. Nowadays, such cloud platforms for natural language understanding (NLU) are widely used, thanks to the …

Evaluating Globally Normalized Transition Based Neural Networks for Multilingual Natural Language Understanding
A Azzarone – 2017 – diva-portal.org
Abstract We analyze globally normalized transition-based neural network models for dependency parsing on English, German, Spanish, and Catalan. We compare the results with FreeLing, an open source language analysis tool developed at the UPC natural …

Big Data, Natural Language Understanding and Intelligent Agent based Web
E KHAN – wseas.us
Abstract:-We have seen the progression of the Internet from portal (Yahoo) to search (Google), to e-Commerce (e-Bay, Amazon) to social networks (Facebook, Twitter). What is NEXT? Well, we see a clear trend that the future Internet will be something that can provide …

Logical analysis of natural language semantics to solve the problem of computer understanding
Y Ostapov – arXiv preprint arXiv:1308.1507, 2013 – arxiv.org
… E-mail: yugo.ost@gmail.com Abstract An object–oriented approach to create a natural language understanding system is considered … 1. Introduction The given paper is devoted to logical aspects of object–oriented approach to create a natural language understanding system …

Research of Natural Language Understanding in Human-Service Robot Interaction
W Wen, Z Qunfei, Z Tehao – Microcomputer Applications, 2015 – en.cnki.com.cn
Aiming at unconstrained natural language instructions for interacting with a service robot, a classification and understanding method based on maximum entropy is proposed. Firstly, a series of effective robot control commands are designed by collecting corpus on home …

An Empirical Investigation of Word Clustering Techniques for Natural Language Understanding
DA Shunmugam, P Archana – International Journal of Engineering …, 2016 – ijesc.org
Abstract: Natural language processing (NLP) tasks such as syntactic part-of-speech tagging, dependency parsing, sentiment analysis, and slot Riling in natural language understanding (NLU), but not much has been reported on the underlying reasons for the performance …

An approach to mental image based understanding of natural language: Focused on static and dynamic spatial relations
R Khummongkol, M Yokota – Awareness Science and …, 2017 – ieeexplore.ieee.org
… them. This work proposes a methodology for natural language understanding through an AI system named Conversation Management System (CMS) based on Mental Image Directed Semantic Theory proposed by M. Yokota …

Human-level natural language understanding: False progress and real challenges
PG Bignoli – 2013 – search.proquest.com
Abstract The field of Natural Language Processing (NLP) focuses on the study of how utterances composed of human-level languages can be understood and generated. Typically, there are considered to be three intertwined levels of structure that interact to …

Guidelines for improving task-based natural language understanding in human-robot rescue teams
M Beetz, M Scheutz, F Yazdani – … (CogInfoCom), 2017 8th IEEE …, 2017 – ieeexplore.ieee.org
Mixed human-robot teams are increasingly considered for accomplishing complex mission due to their complementary capabilities. A major barrier for deploying such heterogeneous teams in real-world settings, is the current lack of natural skills in robotic team members …

Natural language understanding as first-order abduction via stable models
P Homola – Proceedings of the 2015 International Conference on …, 2015 – ceur-ws.org
Abstract We present a method for finding abductive proofs in first-order Horn theories by using an answer-set solver. We illustrate our solution with examples from the domain of natural language understanding. Furthermore we describe a novel way of ranking abductive …

Zero-shot Learning for Natural Language Understanding using Domain-Independent Sequential Structure and Question Types
K Sadamitsu, Y Homma… – Proc. Interspeech …, 2017 – pdfs.semanticscholar.org
Abstract Natural language understanding (NLU) is an important module of spoken dialogue systems. One of the difficulties when it comes to adapting NLU to new domains is the high cost of constructing new training data for each domain. To reduce this cost, we propose a …

From Characters to Understanding Natural Language (C2NLU): Robust End-to-End Deep Learning for NLP (Dagstuhl Seminar 17042)
P Blunsom, K Cho, C Dyer, H Schütze – Dagstuhl Reports, 2017 – drops.dagstuhl.de
… de/17042 1998 ACM Subject Classification I. 2 Artificial Intelligence, I. 2.7 Natural Language Processing Keywords and phrases Natural Language Understanding, Artificial Intelligence, Deep Learning, Natural Language Processing, Representation Learning Digital Object …

A Comparative Study to Understanding about Poetics Based on Natural Language Processing
L Zhang, J Gao – Open Journal of Modern Linguistics, 2017 – scirp.org
This paper tries to find out five poets’ (Thomas Hardy, Wilde, Browning, Yeats, and Tagore) differences and similarities through analyzing their works on nineteenth Century by using natural language understanding technology and word vector model …

Using Natural Language Understanding
N Pathak – Artificial Intelligence for. NET: Speech, Language, and …, 2017 – Springer
Abstract Natural language understanding or NLU: you have been hearing this term since Chapter 1. You have seen with examples what it’s about and what it can do. By now you know that this is the thing that lends an application a human-like ability to understand a …

Natural Language Understanding and Prediction Technologies
N Duta – ijcai-15.org
Scientists have long dreamed of creating machines humans could interact with by voice. In his most cited paper published in 1950, Computing machinery and intelligence Turing predicted that “at the end of the century the use of words and general educated opinion will …

An operation-oriented document natural language understanding method based on event model
B Xie, K Liu – Progress in Informatics and Computing (PIC) …, 2014 – ieeexplore.ieee.org
Operation-oriented Document Natural Language Understanding (take ODNLU for short) is an important approach to automatic plotting research. However, current researches have not given a feasible method to ODNLU, but with some designed processes. The purpose of this …

Natural language understanding with commonsense reasoning: application to the winograd schema challenge
A López Torres – 2016 – oa.upm.es
En 1950, Alan Turing propuso un test para evaluar el grado de inteligencia humana que podría presentar una máquina. La idea principal era realmente sencilla: llevar a cabo una charla abierta entre un evaluador y la máquina. Si dicho evaluador era incapaz de discernir …

A Natural Language Processing Based Approach Using Stochastic Petri Nets For Understanding Software Requirement Specifications
RS Ashtankar, WM Choudhari – International Journal of Computer …, 2016 – academia.edu
… Proposed framework aims to model complex software requirements expressed in natural language and represent them with a new methodology that captures the natural language understanding (NLU) of events and models them using Stochastic Petri Nets (SPN) instead of …

AUTOMATIC UNDERSTANDING AND FORMALIZATION OF NATURAL LANGUAGE GEOMETRY PROBLEMS USING SYNTAX-SEMANTICS MODELS
W Gan, X Yu – ijicic.org
… How to extract the relations in the problems is critical to success- fully implement the proposed approach. General natural language understanding targets to understand the semantic meaning of text. However, a geometry relation can have a slew of semantic expressions …

Whodunnit? Crime Drama as a Case for Natural Language Understanding
L Frermann, SB Cohen, M Lapata – arXiv preprint arXiv:1710.11601, 2017 – arxiv.org
Abstract: In this paper we argue that crime drama exemplified in television programs such as CSI: Crime Scene Investigation is an ideal testbed for approximating real-world natural language understanding and the complex inferences associated with it. We propose to treat …

Exploring natural language understanding in robotic interfaces
I Giachos, EC Papakitsos… – International Journal of …, 2017 – media.neliti.com
Abstract Natural Language Understanding is a major aspect of the intelligence of robotic systems. A main goal of improving their artificial intelligence is to allow a robot to ask questions, whenever the given instructions are not complete, and also by using implicit …

Never-Ending Learning for Deep Understanding of Natural Language
T Mitchell – 2017 – dtic.mil
… 2.0 INTRODUCTION For many years, researchers in natural language understanding have pointed to a key bottleneck to progress: the need for substantial background knowledge to resolve the many ambiguities inherent in natural language text and speech …