Notes:
Anaphora resolution, also known as pronoun resolution, is the process of determining the intended referents of pronouns or other anaphoric expressions in a piece of text or speech. These expressions refer back to an earlier word or phrase in the discourse and can be ambiguous, making it difficult to determine their intended meaning.
Anaphora resolution is an important task in natural language processing (NLP) because it allows NLP systems to better understand and interpret the meaning of text. In a dialog system, for example, anaphora resolution can help the system understand the user’s requests and responses and provide appropriate responses.
There are various techniques that can be used to resolve anaphoric expressions, including syntactic and semantic analysis, co-reference resolution, and machine learning. The choice of technique may depend on the specific requirements of the NLP system and the characteristics of the text being processed.
Anaphora resolution is used in dialog systems to help the system understand the intended meaning of pronouns and other anaphoric expressions used by the user. This is important because these expressions can be ambiguous and may refer to concepts or entities that are not explicitly mentioned in the current conversation.
For example, consider the following conversation:
- User: “I’m going to the store. Do you need anything?”
- System: “No, I don’t think so. Do you want me to come with you?”
- User: “Sure, that would be great. Can you bring me my wallet when you come back?”
In this conversation, the user’s request for the system to bring “my wallet” when it comes back refers back to an earlier mention of going to the store. Without anaphora resolution, the system might not understand the intended meaning of “my wallet” and might not be able to fulfill the user’s request.
To resolve the anaphoric expression “my wallet,” the dialog system might use techniques such as syntactic and semantic analysis, co-reference resolution, or machine learning to determine that the intended referent is the user’s wallet. This allows the system to understand the user’s request and respond appropriately.
- Anaphora recognition is the process of identifying anaphoric expressions in a piece of text or speech. An anaphoric expression is a word or phrase that refers back to an earlier word or phrase in the discourse, such as a pronoun or other reference.
- Anaphora resolution is the process of determining the intended referents of anaphoric expressions. This can be done using techniques such as syntactic and semantic analysis, co-reference resolution, and machine learning.
- Anaphoras are anaphoric expressions.
- Anaphoric is an adjective that refers to something that relates to or involves an anaphora. For example, an anaphoric expression is an anaphoric element of a text or speech, and anaphora resolution is the process of resolving anaphoric elements.
Wikipedia:
References:
See also:
Smart enough to talk with us? foundations and challenges for dialogue capable ai systems
BJ Grosz – Computational Linguistics, 2018 – MIT Press
… and language processing methods to improve the conversational abilities of personal assistants, customer service chatbots, and other dialogue systems … deployed immediate focusing as a means of controlling the inferences required for interpreting anaphoric expressions like …
Visual coreference resolution in visual dialog using neural module networks
S Kottur, JMF Moura, D Parikh… – Proceedings of the …, 2018 – openaccess.thecvf.com
… 1). Especially when trying to an- swer a question that contains an anaphora, for instance the pronoun ‘it’, which refers to its full form … We believe such consistency in model outputs is a strongly desirable property as we move towards human-machine interaction in dialog systems …
Anaphora with non-nominal antecedents in computational linguistics: A survey
V Kolhatkar, A Roussel, S Dipper… – Computational …, 2018 – MIT Press
… Anaphoric relations are ubiquitous in all kinds of texts, and non-NA anaphora is especially prevalent in spoken … Here, a dialogue system aware of non-NAs could generate a clarification request: What should be repeated, the act of eating three pieces of cake or the statement …
Building multi-domain conversational systems from single domain resources
D Griol, JM Molina – Neurocomputing, 2018 – Elsevier
… In addition, it resolves ellipsis and anaphora, evaluates the relevance and completeness of user requests, identifies and recovers from … of obtaining sentences in natural language from the non-linguistic, internal representation of information handled by the dialog system [66] …
An Ontology-Based Dialogue Management System for Banking and Finance Dialogue Systems
D Altinok – arXiv preprint arXiv:1804.04838, 2018 – arxiv.org
… used ontologies in our work for two purposes: ? to store the knowledge ? to navigate through the domain The knowledge base component takes part in many dialogue systems … 4.3.4 Implicit Anaphoras It is not always clear when one should do any anaphora resolution at …
Anaphora Resolution in a speech recognition environment
D Woei-A-Jin, L Rothkrantz – fi.muni.cz
… September 2000. [Mur96] M. Murata. Anaphora Resolution in Japanese Sentences Using Surface Expressions and Examples … The thoughtful elephant: Strategies for spoken dialogue systems. IEEE Transactions on Speech and Audio Processing, 8(1):51-62, January 2000 …
Resolving Abstract Anaphora Implicitly in Conversational Assistants using a Hierarchically stacked RNN
P Khurana, P Agarwal, G Shroff, L Vig – Proceedings of the 24th ACM …, 2018 – dl.acm.org
… systems has resulted in an increased demand for more natural dialogue systems, capable of … in the context of conversa- tional systems, referred to as Abstract Anaphoric Intent Identification … Therefore it becomes possible to resolve the abstract anaphora beyond a pair of user …
Applying Coreference Resolution for Usage in Dialog Systems
G Rolih – 2018 – uu.diva-portal.org
… of a rule-based coreference algorithm and its integration into the Teneo dialog system … are very detailed – there are algorithms for different types of anaphoric expressions depending … as- sumption that commonsense knowledge is not needed for pronominal anaphora resolution …
Resolution of Personal Pronoun Anaphora in Chinese Micro-blog
Y Peng, Y Zhang, S Huang, R Chen, J You – Workshop on Chinese Lexical …, 2018 – Springer
… He realized the resolution of pronoun anaphora in his human-machine dialogue system … According to whether the pronoun’s antecedent occurs in micro-blog texts, anaphoric relations can be divided into the internal anaphora and the external anaphora …
Cross-Lingual Approaches to Reference Resolution in Dialogue Systems
A Sharaf, A Gupta, H Ge, C Naik, L Mathias – arXiv preprint arXiv …, 2018 – arxiv.org
… Dialogue Systems … The resulting semantic interpretation is then passed to a reference resolver, in order to resolve referring expressions (including anaphora) to their antecedent slots in the conversation, which is then sent to the dialogue manager whose main responsibility is to …
Advanced Social Interaction with Agents: 8th International Workshop on Spoken Dialog Systems
M Eskenazi, L Devillers, J Mariani – 2018 – Springer
… The DM structure here is designed to address the issues of dialogue state tracking, anaphora and co-reference resolution by using an ontology … They also show that the use of this architecture allows for easier creation of a dialogue system in a new domain, which is one of the …
A Method of Speech Synthesis for Spoken Dialogue Systems and Psychological Assessment of the Synthetic Speech
K HIROSE, N TAKAHASHI, T SENOO, M SAKATA… – sap.ist.i.kyoto-u.ac.jp
… Generate sentences from response contents of deep-level semantic representation, which may include information on focal position, ellipsis and anaphora … As for the rst item, we have developed a method of dialogue processing in a spoken dialogue system with questions and …
Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
C Khatri, B Hedayatnia, A Venkatesh, J Nunn… – arXiv preprint arXiv …, 2018 – arxiv.org
… Anaphora and Co-reference Resolution: Multi-turn dialog systems need to resolve ambiguous phrases with reference to prior entities for downstream tasks such as response generation. Fantom, Tartan and Slugbot did co-reference …
A dialogue based mobile virtual assistant for tourists: The SpaceBook Project
P Bartie, W Mackaness, O Lemon, T Dalmas… – … Environment and Urban …, 2018 – Elsevier
… Location aware spoken dialogue system for pedestrians. • … In contrast, the SpaceBook system deployed a Spoken Dialogue System where multi-turn sequences of interaction are employed in a long-running conversation with the user, lasting many minutes …
I Text
M Sergot – fi.muni.cz
… Simplified Processing of Elliptic and Anaphoric Utterances in a Train Timetable Information Retrieval Dialogue System … An Annotation Scheme for Dialogues Applied to Anaphora Resolution Algorithms410 Patricio Martínez-Barco, Manuel Palomar …
External Memory Enhanced Sequence-to-Sequence Dialogue Systems
J Verdegaal – 2018 – pdfs.semanticscholar.org
… Master Thesis External Memory Enhanced Sequence-to-Sequence Dialogue Systems by … 9 Page 11. In the successful dialogue system mentioned in the introduction, [37] this is done with only the last preceding utterance, ie to generate utterance i, utterance i?1 is context …
Conversational Modelling for ChatBots: Current Approaches and Future Directions
M McTear – 2018 – spokenlanguagetechnology.com
… All three systems were able to handle follow-up questions involving anaphoric reference. In addition to pronouns, Alexa was able to handle anaphora involving the adverb there: User … End-to-end dialogue systems using deep neural networks are the most recent develop- ment …
Dialogue Systems and Conversational Agents for Patients with Dementia: The Human–Robot Interaction
A Russo, G D’Onofrio, A Gangemi, F Giuliani… – Rejuvenation …, 2018 – liebertpub.com
… 8 Rejuvenation R e se arch Dialogue Systems and Conversational A gents fo r Patients w ith Dementia: th … taking into account, on the one side, the inherent complexity of natural language processing (eg, resulting from the presence of ambiguities, anaphora, ellipsis, etc.) and …
Towards Building a Domain Independent Dialog System
P Jwalapuram – 2018 – web2py.iiit.ac.in
Page 1. Towards Building a Domain Independent Dialog System Thesis submitted in partial fulfillment of the requirements for the degree of … Abstract This thesis discusses a mixed-initiative, domain independent dialog system based on a hierarchically structured knowledge base …
Learning Latent Beliefs and Performing Epistemic Reasoning for Efficient and Meaningful Dialog Management
A Chhabra, P Saini, A Sangroya… – arXiv preprint arXiv …, 2018 – arxiv.org
… belief identification and robust reasoning mechanisms, these errors propagate to subsequent stages of processing in a dialog system and exert a … reference to multiple concepts and the need to extract a large amount of facts, commonsense knowledge, anaphora resolution, and …
NIPS Conversational Intelligence Challenge 2017 Winner System: Skill-based Conversational Agent with Supervised Dialog Manager
I Yusupov, Y Kuratov – Proceedings of the 27th International Conference …, 2018 – aclweb.org
… 2) shows how user interacts with a dialog system. Figure 2: Dialog system and user interaction flow … However, the bot can’t answer if the user uses anaphora constructions. User: Ask me question Bot: How many years did nbc universal sell in 2006 …
Contextual Slot Carryover for Disparate Schemas
C Naik, A Gupta, H Ge, L Mathias… – arXiv preprint arXiv …, 2018 – arxiv.org
… Index Terms: spoken dialog, state tracking, anaphora resolu- tion, contextual understanding … tasks such as zero pronouns naturally, as we don’t have to explicitly identify the anaphoric mentions … Table 1 shows an example con- versation a user may have with such a dialog system …
JDCFC: A Japanese Dialogue Corpus with Feature Changes
T Nakamura, D Kawahara – … of the Eleventh International Conference on …, 2018 – aclweb.org
… Breakdown Detection Challenge database is a corpus used to detect incorrect replies generated by dialogue systems (Higashinaka et al … with annotations of mor- phology, named entities, dependencies, predicate-argument structures including zero anaphora and coreferences …
Proceedings of the First International Workshop on Spatial Language Understanding
P Kordjamshidi, A Bhatia, J Pustejovsky… – Proceedings of the First …, 2018 – aclweb.org
… like block world and spatial description generation in a dialogue system given a multi-modal setting, generation of large-scale annotated corpora with spatial concepts and primitives, machine learning models for spatial information extraction and resolving anaphora in spatial …
SlugBot: Developing a Computational Model and Framework of a Novel Dialogue Genre
KK Bowden, J Wu, W Cui, J Juraska, V Harrison… – dex-microsites-prod.s3.amazonaws …
… As for the Positive users, we would let them lead the conversation, while for the Negative users, we would suggests some resources in our dialogue system to improve their well-being … We removed utterances that contained any type of anaphora we could identify …
Alana v2: Entertaining and Informative Open-domain Social Dialogue using Ontologies and Entity Linking
AC Curry, I Papaioannou, A Suglia, S Agarwal… – dex-microsites-prod.s3.amazonaws …
… 9. Anaphora Resolution: we exploit both the annotations generated by the NER ensemble and the annotations generated by the entity linker to resolve … This is an important task in dialogue systems that needs to understand mentions to specific entities in the user utterance: it is …
Natural Language Processing for Industry
S Quarteroni – Informatik-Spektrum, 2018 – Springer
… cor- rectly interpret rhetorical phenomena such as ellipsis (missing verbs), anaphora and deictic … one hand, NLU components usually have difficulties resolving ellipsis and anaphoric references (“it … However, many dialogue systems allow such a high flexibility only at the initial, in …
Voice Control in a Real Flight Deck Environment
M Trzos, M Dostl, P Machkov, J Eitlerov – International Workshop on …, 2018 – Springer
… When pilot uses an anaphora in speech utterance the system will try to associate the … accept also partial inputs (cross-modal use-cases) or abstract pronouns (anaphoric interaction) … Gallwitz, F.: Integration of a Kaldi speech recognizer into a speech dialog system for automotive …
Collaborative Human-Machine Interaction in Mobile Phone Support Centers: A Case Study
K Dent, L Plurkowski, J Maxwell – International Conference on Intelligent …, 2018 – Springer
… 4 The Otto Dialog System. In call centers, individual representatives responding to customer queries keeps operating costs high … Otto must also handle typical NLP challenges like anaphora, ellipsis, and ill-formed user input …
Observations of a New Chatbot: Drawing Conclusions from Early Interactions with Users
LN Michaud – IT Professional, 2018 – ieeexplore.ieee.org
… be possible to automate under a framework with sophisticated dialogue-state tracking and anaphora-resolution capabilities … terests include natural language processing and computational linguistics, human–computer interaction, user modeling, dialogue systems, parsing, and …
CAIR’17: First International Workshop on Conversational Approaches to Information Retrieval at SIGIR 2017
H Joho, L Cavedon, J Arguello, M Shokouhi… – ACM SIGIR Forum, 2018 – dl.acm.org
… strong expertise on topics related to Conversational IR, including Interactive IR, Evaluation over Complex Queries, and Spoken Dialogue Systems Evaluation … In terms of key challenges, the authors cited the following: (1) the need for anaphora resolution (eg, being able to …
Research Challenges in Building a Voice-based Artificial Personal Shopper-Position Paper
N Limsopatham, O Rokhlenko, D Carmel – Proceedings of the 2018 …, 2018 – aclweb.org
… In this position paper, we introduce a novel artificial personal shopper task, where a voice- based dialog system is used to enrich on … This would be an interesting area of research that needs to incorporate co-reference resolution and anaphora resolution for grounding personal …
Ask No More: Deciding when to guess in referential visual dialogue
R Shekhar, T Baumgartner, A Venkatesh… – arXiv preprint arXiv …, 2018 – arxiv.org
… in an architecture that can be trained end-to- end directly from raw data, without specific annotations commonly used in dialogue systems, such as … as “Is it the one on the left?” could be asked twice within the same dialogue with different antecedents for the anaphoric phrase “the …
Amusing Tools for Teaching Lesser-Loved Languages
PJ Henrichsen – saiconference.com
… Keywords—Computer assisted language learning (CALL); dialogue systems; gaming I. BACKGROUND Developed in 2015-2017, Talerum is the … discourse information is accumulated as long as the dialogue proceeds, enabling the use of anaphoric reference, incremental …
Identifying Participant Mentions and Resolving Their Coreferences in Legal Court Judgements
S Hingmire, GK Palshikar… – Text, Speech, and …, 2018 – books.google.com
… Identifying participant mentions and grouping their coreferents together is a challenging task in Legal text mining and Legal dialogue systems … In: Proceedings of PACLING (2017) 2. Al-Kofahi, K., Grom, B., Jackson, P.: Anaphora resolution in the extraction of treatment history …
Investigating how conversational search agents affect user’s behaviour, performance and search experience
M Dubiel, M Halvey, L Azzopardi… – The Second …, 2018 – strathprints.strath.ac.uk
… KEYWORDS Conversational Search; Dialogue-Systems; Voice Interfaces … These state of the art systems provide limited: (1) state tracking (ie estimating user’s goal in a conversation), (2) anaphora resolution (ie resolving references to earlier items in conversation), and (3) have …
Identifying Participant Mentions and Resolving Their Coreferences in Legal Court Judgements
A Gupta, D Verma, S Pawar, S Patil, S Hingmire… – … Workshop on Temporal …, 2018 – Springer
… Anaphora Resolution is a sub-task of Coreference Resolution where the focus is to find an appropriate antecedent noun phrase for … Identifying participant mentions and grouping their coreferents together is a challenging task in Legal text mining and Legal dialogue systems …
Humor intelligence for virtual agents
AI Niculescu, RE Banchs – colips.org
… 3.2 Multimodal dialogue system … Etc.) Additionally, the logs con- tained questions asked in context, ie questions requesting anaphora resolution, as in the example shown in figure 3. We include in the scripts also questions that were unknown to the system, ie questions for those …
Deep Neural Architecture for Recovering Dropped Pronouns in Korean
S Jung, C Lee – ETRI Journal, 2018 – Wiley Online Library
… a beneficial preprocessing task for machine translation, information extraction, spoken dialog systems, and many … being a pronoun 4. Several studies have addressed dropped anaphora and dropped … entropy models are used to rank and resolve Korean anaphoric zero pronouns …
Statistical Language and Speech Processing: 6th International Conference, SLSP 2018, Mons, Belgium, October 15-16, 2018, Proceedings
T Dutoit, CM Vide, G Pironkov – 2018 – books.google.com
… of statistical models (including machine learning) within language and speech processing, namely: Anaphora and coreference … and language generation Speech recognition Speech synthesis Speech transcription Spelling correction Spoken dialogue systems Term extraction …
Statistical Language and Speech Processing
T Dutoit, C Martín-Vide, G Pironkov – Springer
… of statistical models (including machine learning) within language and speech processing, namely: Anaphora and coreference … and language generation Speech recognition Speech synthesis Speech transcription Spelling correction Spoken dialogue systems Term extraction …
Conversational ai: The science behind the alexa prize
A Ram, R Prasad, C Khatri, A Venkatesh… – arXiv preprint arXiv …, 2018 – arxiv.org
… Anaphora resolution is important for downstream tasks such as question answering and information extraction in multi-turn dialog systems. • Sentence Completion: Some teams expanded user utterances with contextual information …
Challenges and opportunities of applying natural language processing in business process management
H Van der Aa, J Carmona Vargas… – COLING 2018: The …, 2018 – upcommons.upc.edu
… analysis in both process descriptions and computation of similarities while con- sidering the different discourse level, ambiguities, anaphora/coreference in … ultimate goal would be to allow stakeholders of the process to navigate through it by means of querying a dialog system …
Conversational Query Understanding Using Sequence to Sequence Modeling
G Ren, X Ni, M Malik, Q Ke – Proceedings of the 2018 World Wide Web …, 2018 – dl.acm.org
… What is the population?”, there is no anaphora in the second query that explicitly refers to “California”). Example 3 shows that even the perfect coreference resolution sys- tem will not be able to handle the conversational queries that lack anaphoras, such as some of the …
Gunrock: Building A Human-Like Social Bot By Leveraging Large Scale Real User Data
CY Chen, D Yu, W Wen, YM Yang, J Zhang, M Zhou… – dex-microsites-prod.s3.amazonaws …
… Figure 1: Social Bot Framework Figure 1 depicts the social bot dialog system framework … The state-of-the-art models by Stanford CoreNLP and NeuralCoref 14 are trained on non- conversational data and do not work well for dialog conversations in anaphora resolution …
Exploring Conversational Language Generation for Rich Content about Hotels
MA Walker, A Smither, S Oraby, V Harrison… – arXiv preprint arXiv …, 2018 – arxiv.org
… content is given in unordered lists that facilitate visual scanning, as opposed to a conversation in which the dialogue system needs to de … paraphrases the same Turkers produced are shown in Figure 4. The paraphrases contain fewer words per sentence, more use of anaphora …
1. The flipped classroom in the Portuguese as foreign language class
O de Azevedo – leadsummerschool.de
… meaningfully an L2 with an automated agent, through an oral (spoken dialogue systems) or written … Previous studies have shown deficits with anaphora resolution (AR) at the syntax-discourse … Each anaphoric form was tagged using UAM Corpus Tool and was assigned a …
Alexa Prize-State of the Art in Conversational AI
C Khatri, A Venkatesh, B Hedayatnia, A Ram… – AI …, 2018 – search.proquest.com
… Anaphora resolution is important for downstream tasks such as question answering and information extraction in multiturn dialogue systems. Most of the teams used Stanford- CoreNLP’s Coreference Resolution System (Manning et al. 2014) to perform this task …
Discourse and Dialogue
SE Brennan, AK Kuhlen, J Charoy – Stevens’ Handbook of …, 2018 – books.google.com
… answer alone. Finally, computational approaches can implement models of language use (often using findings from these other approaches) to create working text generation programs or spoken dialogue systems. With these …
Iris: A Conversational Agent for Complex Tasks
E Fast, B Chen, J Mendelsohn, J Bassen… – Proceedings of the …, 2018 – dl.acm.org
… For Iris, anaphoric expressions are values produced by a pre- vious command that are necessary to … Finally, Iris supports the sequencing of any of its commands (ie, anaphora resolution) … RELATED WORK Iris is inspired by other dialogue systems that engage with complex tasks …
Safety First: Conversational Agents for Health Care
T Bickmore, H Trinh, R Asadi, S Olafsson – Studies in Conversational UX …, 2018 – Springer
… 1999)—specifies a (very partial) qualitative list of interactional capabilities that dialogue systems should implement to approximate human behavior … assistants are increasingly improving in this regard (eg, remembering recently-mentioned entities for anaphora resolution (Lee et …
Context Aware Conversational Understanding for Intelligent Agents with a Screen
VI Naik, A Metallinou, R Goel – 2018 – m.media-amazon.com
… ‘play the first one’ is a similarly ambiguous anaphoric request that … Utterances 2 and 3 of Table 2 are examples of anaphora, where screen content is used to dis- ambiguate the reference ‘one’ in the former utterance, while the reference in the latter utterance is under-specified …
Importance of Contextual Knowledge in Artificial Moral Agents Development
R Rzepka, K Araki – 2018 – researchgate.net
… When implemented in a dialog system, our method needs to support explaining its judgements which is an important functionality for an … Sev- eral techniques are required for cleaning up the text, rec- ognizing semantic roles, tackling with anaphora resolution, double negations …
Proceedings of the Symposium on Logic and Algorithms in Computational Linguistics 2018 (LACompLing2018)
K Angelov, K Liefke, R Loukanova… – The Symposium on …, 2018 – diva-portal.org
… His main research interests are semantics (both theoretical and computational), dialogue semantics and computational dialogue systems … type theoretical frameworks have been used to model linguistic phenomena of central importance, eg, unbound anaphora (Ranta 1994 …
Applying Pragmatics Principles for Interaction with Visual Analytics
E Hoque, V Setlur, M Tory… – IEEE transactions on …, 2018 – ieeexplore.ieee.org
… We first identify the anaphora in the utterance, such as ‘that’, ‘those’, ‘them’, ‘ones’, ‘previous’, ‘next.’ We then look at the phrasal chunk … Next, we search through the backward-looking centers Cb(Un,DS) to find such entities and replace the anaphoric reference with these entities …
Virtual Assistant for IoT process management, using a middleware
D Chilcañán, P Navas, M Escobar – Proceedings of the 2018 2nd …, 2018 – dl.acm.org
… language for certain tasks, such as automatic translation, interactive dialogue systems, analysis of … something that has already been introduced is called an anaphoric reference.) Referencing … are the algorithm pronoun references [20] and Pronominal Anaphora Resolution [21] …
Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture
G Larionov, Z Kaden, HV Dureddy… – arXiv preprint arXiv …, 2018 – arxiv.org
… Previously, interest in human-machine spoken language interaction had focused on goal-oriented dialog systems … The Natural Language Understanding module contains features such as intent recognition, topic and domain detec- tion, anaphora resolution, and Named Entity …
Low-Resource Contextual Topic Identification on Speech
C Liu, M Wiesner, S Watanabe, C Harman… – arXiv preprint arXiv …, 2018 – arxiv.org
… For in- stance, tasks such as anaphora resolution or entity disambiguation critically depend on contextual clues … in a spoken document, is similar to the domain or intent classification in a multi-turn spoken language understanding (SLU) component of a dialog system [12, 13, 14 …
Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments
D Stojanovski, A Fraser – Proceedings of the Third Conference on …, 2018 – aclweb.org
… language modeling (Ji et al., 2015; Wang and Cho, 2016) and dialogue systems (Serban et … contain a large amount of short, informal and conversational text, where anaphoric pronouns are … a context-aware Transformer model and provided an analysis of anaphora resolution in …
Conversational Homes: A Uniform Natural Language Approach for Collaboration Among Humans and Devices
D Braines, N O’Leary, A Thomas, D Harborne… – orca.cf.ac.uk
… enabled home. With this in mind we have not specifically attempted to build a system which has a rich or complex grammar or dialogue system, nor have we tried to create extensive, rich models or ontologies of the domain. There …
A Bi-Encoder LSTM Model for Learning Unstructured Dialogs
D Shekhar – 2018 – digitalcommons.du.edu
… growing rapidly. A Dialog System can communicate with human in text, speech or both and can be classified into – Task-oriented Systems and Chatbot Systems … This is an instance of anaphora, where “she” co-referees to some other discourse entity. 17 Page 26 …
DEMONSTRATIVES IN TURKISH: ON THE PRAGMATIC USE OF DEMONSTRATIVES IN THE CONTEXT OF A COLLABORATIVE PROBLEM SOLVING TASK
F BÜYÜKTEKIN – 2018 – etd.lib.metu.edu.tr
… Unlike traditional dialogue systems, situated dialogue encourages language use as a collab- orative … a noun phrase, substitution anaphora, substitution cataphora, textual anaphora, textual cataphora … Diessel (1999) further divides endophoric use into (i) anaphoric, (ii) discourse …
The First Financial Narrative Processing Workshop (FNP 2018)
M El-Haj, P Rayson, A Moore – 2018 – lrec-conf.org
… Keeping the dialogue state in dialogue systems is a notoriously difficult task. We introduce an ontology-based dialogue manager (OntoDM), a dialogue manager that keeps the state of the conversation, provides a basis for anaphora resolution and drives the conversation via …
Multilayer Corpus Studies
A Zeldes – 2018 – taylorfrancis.com
… a comprehensive annotation scheme for coreference and referentiality which codes, among other things, ambigu- ity in the reference of anaphora was used … Conversely, if we are interested in linking mentions of entities for core- ference, such as the anaphoric relation between a …
The Case for a Visual Discovery Assistant: A Holistic Solution for Accelerating Visual Data Exploration
DJL Lee, A Parameswaran – Data Engineering, 2018 – sites.computer.org
… the system interprets the anaphoric reference as continuing the context of the original utterance related to average price on the y-axis. Semantic ambiguity can often be composed of one or more lexical and syntactical ambiguities. For example, in Iris [9], a dialog system for data …
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
I Gurevych, Y Miyao – Proceedings of the 56th Annual Meeting of the …, 2018 – aclweb.org
Page 1. ACL 2018 The 56th Annual Meeting of the Association for Computational Linguistics Proceedings of the Conference, Vol. 1 (Long Papers) July 15 – 20, 2018 Melbourne, Australia Page 2. Diamond Sponsors: Platinum Sponsors: Gold Sponsors: ii Page 3. Silver Sponsors …
Building a Neural Semantic Parser from a Domain Ontology
J Cheng, S Reddy, M Lapata – arXiv preprint arXiv:1812.10037, 2018 – arxiv.org
… restaurant.kfc). The third construct of meaning representations captures complex human intentions with co-referential variables, which establish anaphoric links between meaning representations (antecedents and consequents). To …
Interactive Question Answering Using Frame-Based Knowledge Representation
EG Boroujerdi – 2018 – yorkspace.library.yorku.ca
… process with an interactive mechanism. The interactive mechanism gives the QA system the ability to remember the context in case of anaphora or coreference in 5 … (NLU) components of the system. IQA is also related to a large portion of research in Dialogue Systems. While it …
Corpus Annotation and Inference with Episodic Logic Type Structure
G Kim – 2018 – cs.rochester.edu
… We do not want a dialogue system or other NLU system to jump to unwarranted conclusions about the reality of ghosts or … relativizers, etc.), which determine how they can coherently combine; scoping of tense, quantifiers, and coordinators; resolution of anaphora; inference of …
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
E Riloff, D Chiang, H Julia, T Jun’ichi – Proceedings of the 2018 …, 2018 – aclweb.org
… She works on spoken language processing and NLP, studying text-to-speech synthesis, spoken dialogue systems, entrainment in conversation, detection of deceptive and emotional speech, hedging behavior, and linguistic code-switching (language mixing). xxii Page 23 …
Automatic Conversation Review for Intelligent Virtual Assistants
IR Beaver – 2018 – digitalrepository.unm.edu
… Page 7. vi Contents List of Figures xiii List of Tables xviii Thesis Statement 1 1 Introduction 2 2 Background 7 2.1 Chatbot or IVA . . . . . 8 2.2 An Evolution of Dialog Systems . . . . . 9 2.3 Architecture of an IVA …
Classical and modern Arabic corpora
E Atwell – Diachronic Corpora, Genre, and Language Change, 2018 – books.google.com
… Classical and modern Arabic corpora?? Carroll 2013); the QurAna anaphoric coreference annotations … to train Machine Learning models for Modern Arabic anaphora resolution (Seddik … and language- benefit: Additional evaluation criteria for natural language dialogue systems …
Recurrence Quantification Models of Human Conversational Grounding Processes: Informing Natural Language Human-Computer Interaction
CD Rothwell – 2018 – rave.ohiolink.edu
… Conversational grounding is also a crucial process for human-computer interaction using language-based methods, such as spoken dialogue systems … 2013, 2004; Clark and Krych, 2004), making it a high priority for increasing capabilities of spoken dialogue systems …
12 ‘You Can Just Give Those Documents to Myself’
SB English – Corpus Approaches to Contemporary British Speech …, 2018 – books.google.com
… Parker et al.(1990, p. 61) argue that reflexives are “fundamentally anaphoric and identify their referents as the discourse referent (ie the topic of the discourse)”, a process which they hold distinct from pronoun/antecedent resolution …
ASHuR: Evaluation of the Relation Summary-Content Without Human Reference Using ROUGE
A Ramírez-Noriega, R Juárez-Ramírez, S Jiménez… – Computing and …, 2018 – cai.sk
Page 1. Computing and Informatics, Vol. 37, 2018, 509–532, doi:10.4149/cai 2018 2 509 ASHUR: EVALUATION OF THE RELATION SUMMARY-CONTENT WITHOUT HUMAN REFERENCE USING ROUGE Alan Ram´?rez-Noriega …
Research Frontiers in Information Retrieval Report from the Third Strategic Workshop on Information Retrieval in Lorne (SWIRL 2018)
JS Culpepper, F Diaz, MD Smucker – culpepper.io
… Building on extensive recent progress in dialog systems, we distinguish CIS from traditional search systems as including capabilities such as long term user state (including tasks that may be continued or repeated with or without variation), taking into account user needs beyond …
Informatika Tanszék-Szakmai konferenciák
AWE Pyramid – 2018 – it.sze.hu
… anaphora and coreference resolution … answering systems semantic role labelling speaker identification and verification speech and language generation speech recognition speech synthesis speech transcription spelling correction spoken dialogue systems term extraction text …
SlugNERDS: A Named Entity Recognition Tool for Open Domain Dialogue Systems
KK Bowden, J Wu, S Oraby, A Misra… – arXiv preprint arXiv …, 2018 – arxiv.org
… of Tools and Corpora To address these challenges we present Slugbot’s Named Entity Recognition for dialogue Systems (SlugNERDS), an NER … SlugNERDS performs anaphoric resolution to perform discourse level entity linking, in this case associating he with Moon Knight …
Attentive Speaking. From Listener Feedback to Interactive Adaptation
H Buschmeier – 2018 – pub.uni-bielefeld.de
… Timo Baumann, David Schlangen, Casey Kennington, and Spyros Kousidis from Bielefeld’s Dialogue Systems group for joint work on incremental and adaptive output gener- ation in dynamic situations. ? Zofia Malisz, Petra Wagner, and Joanna Skubisz for xiii Page 16 …
Nav view search
H Li, HA Patil, N Evans, K Evanini… – 2018 – isca-speech.org
… language processing. q Speech-to-text, text-to-speech and speech-to-speech processing. q Machine translation and dialogue systems. q Application of spoken language technologies for under-resourced languages. Important …
Detecting New, Informative Propositions in Social Media
N Dewdney – 2018 – etheses.whiterose.ac.uk
Page 1. DOCTORAL THESIS Detecting New, Informative Propositions in Social Media Author: Nigel Dewdney Supervisor: Prof. Robert GAIZAUSKAS A thesis submitted in fulfillment of the requirements for the degree of Doctor of Philosophy …
Using natural language processing for question answering in closed and open domains
M Latifi – 2018 – upcommons.upc.edu
Page 1. Universitat Politècnica de Catalunya BarcelonaTECH Department of Computer Science Using Natural Language Processing for Question Answering in Closed and Open Domains A DISSERTATION SUBMITTED TO …
Deep Semantic Learning for Conversational Agents
M Morisio, M Mensio – 2018 – researchgate.net
Page 1. POLITECNICO DI TORINO Master of Science in Computer Engineering Master’s Thesis Deep Semantic Learning for Conversational Agents Supervisor Prof. Maurizio Morisio Candidate Martino Mensio Tutor Istituto Superiore Mario Boella Dr. Giuseppe Rizzo April 2018 …
Literature Survey and Datasets
S Poria, A Hussain, E Cambria – Multimodal Sentiment Analysis, 2018 – Springer
In this chapter we present the literature on unimodal and multimodal approaches to sentiment analysis and emotion recognition. As discussed in the Sect. 2.1, both of these topics can be brought…
Explainable autonomy: A study of explanation styles for building clear mental models
FJC Garcia, DA Robb, X Liu, A Laskov… – Proceedings of the 11th …, 2018 – aclweb.org
… It can han- dle anaphoric references over multiple utterances eg “Where is Vehicle0?” … What is its esti- mated time to completion?”. It also handles el- lipsis eg“What is the battery level of vehicle0?” …What about vehicle1?” …
Non-native Students’ Dismay in the Spoken Context in the United Kingdom
MH Shah – Journal of Second Language Teaching & Research, 2018 – pops.uclan.ac.uk
… It is true that they are informal expressions, but they are formally informal with an anaphoric reference (line 159, Appendix) … A semantic interpreter and a cooperative response generator for a robust spoken dialogue system. International Journal of …
Cross-domain analysis of discourse markers in European Portuguese
V Cabarrão, H Moniz, F Batista… – … -domain analysis of …, 2018 – repositorio.iscte-iul.pt
… shedding light on the prosodic patterns of discourse markers in EP, thus contributing to their identification and modeling in spoken dialogue systems … that the presence of discourse markers can be used to infer the discourse structure, and for resolving anaphoric references, and …
Wikipedia Article Generation for Named Entities
P Yashaswi – 2018 – web2py.iiit.ac.in
Page 1. Wikipedia Article Generation for Named Entities Thesis submitted in partial fulfillment of the requirements for the degree of MS in Computer Science Engineering by Research by P Yashaswi 201102111 p.yashaswi@research.iiit.ac.in …
KOGWIS2018: Computational Approaches to Cognitive Science
C Rothkopf, D Balfanz, R Galuske, F Jäkel… – … Conference of the …, 2018 – tu-darmstadt.de
… 46 Zahra Moradi, Keyvan Yahya, Eckart Altenmüller, Boris Kleber and Nelson Mauro Moldanato Common Ground with Dialogue Systems for Fault Diagnosis: How Should They Ask for Clarification?…. 47 Romy Müller and Dennis Paul …
The Oxford Handbook of Ellipsis
J van Craenenbroeck, T Temmerman – 2018 – books.google.com
… deals with both theoretical and computational linguistics, with a particular interest in ellipsis and other matters involving semantics, anaphora, and discourse … He researches dialogue modelling and dialogue systems, with a focus on incremental processing and disfluency …
Sentiment Analysis in the Bio-Medical Domain
R Satapathy, E Cambria, A Hussain – Springer
… Examples of the second domain will include, but not limited to: computational and psychological models of emotions, bodily manifestations of affect (facial expressions, posture, behavior, physiology), and affective interfaces and applications (dialogue systems, games, learning …
Artificial Intelligence for All: An Abiding Destination
V Pathak, P Tiwari – 2018 – books.google.com
Page 1. ARTIFICIAL INTELLIGENCE FOR ALL AN ABIDING DESTINATION º Nº. -º- 2 º nº 2 wº º: DR. PANKAT TIWARI VIKAS PATHAIK Page 2. Artificial Intelligence For All Artificial Intelligence For All i Page 3. Artificial Intelligence …
Sentiment Analysis in the Bio-Medical Domain: Techniques, Tools, and Applications
R Satapathy, E Cambria, A Hussain – 2018 – books.google.com
… Examples of the second domain will include, but not limited to: computational and psychological models of emotions, bodily manifestations of affect (facial expressions, posture, behavior, physiology), and affective interfaces and applications (dialogue systems, games, learning …
The shaping of transitivity and argument structure: theoretical and empirical perspectives
S GILDEA, E GROSSMAN, P MERLO, S LURAGHI… – ling.human.is.tohoku.ac.jp
Page 1. 1 The shaping of transitivity and argument structure: theoretical and empirical perspectives Pavia (Italy), October 25th-27th, 2018 This conference is held in association with the PRIN project ‘Transitivity and Argument Structure in Flux’ (grant no. 20159M7X5P) …
Diving Deep into Event Semantics
Z Liu – 2018 – hunterhector.github.io
Page 1. September 28, 2018 DRAFT Thesis Proposal Diving Deep into Event Semantics Zhengzhong Liu October 2018 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Thesis Committee: Teruko …
CliCR: A Dataset of Clinical Case Reports for Machine Reading Comprehension
S Šuster, W Daelemans – arXiv preprint arXiv:1803.09720, 2018 – arxiv.org
… construct mean vectors for both ground-truth and system answer sequences, and then compare them with the cosine similarity. This and other embed- ding metrics for evaluation were previously studied in dialog-system research (
Keep me in the loop: Increasing operator situation awareness through a conversational multimodal interface
DA Robb, FJ Chiyah Garcia, A Laskov, X Liu… – Proceedings of the …, 2018 – dl.acm.org
… It can handle anaphoric references over multiple utterances eg “Where is Vehicle0 … Dialogue features similar to those traditionally collected when evaluating a spoken dialogue system [23] including number of user and system turns, frequency of dialogue act types, mean number …
R?ku kopa latviešu valodas semantikas anal?zei: publik?ciju kopa
P Paikens – 2018 – dspace.lu.lv
… A deep discourse representation structure for theme-rheme and anaphora resolution … The use-cases are ranging from controlled languages (eg dialogue systems and interfaces to formal languages) to domain-specific machine translation applications (eg speech-to-speech …
KNADIA: Enterprise KNowledge Assisted DIAlogue Systems Using Deep Learning
M Singh, P Agarwal, A Chaudhary… – 2018 IEEE 34th …, 2018 – ieeexplore.ieee.org
… as follows: 1) We define two types of enterprise needs that can be served by knowledge-assisted conversational dialogue systems: ‘Virtual Assistance … current version of the system we anticipate that all user queries are self contained, and does not make anaphoric reference to a …
Questions, pictures, answers
M Theune, B van Schooten, R Op den Akker, W Bosma… – pure.uvt.nl
… Enabling the user to give feedback on her information need is one of the purposes of our dialogue system … In addition, follow-up questions may contain anaphoric references that need to be rewritten to form a self-contained question that can be handled by QA …
Divergently seeking clarification: The emergence of clarification interaction
J Ginzburg, D Kolliakou – Topics in cognitive science, 2018 – Wiley Online Library
Page 1. Topics in Cognitive Science (2018) 1–32 Copyright © 2018 Cognitive Science Society, Inc. All rights reserved. ISSN:1756-8757 print / 1756-8765 online DOI: 10.1111/tops.12333 This article is part of the topic “Miscommunication …
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation
A Gatt, E Krahmer – Journal of Artificial Intelligence Research, 2018 – jair.org
… For example, the generation of spoken utterances in dialogue systems (eg, Walker, Stent, Mairesse, & Prasad, 2007; Rieser & Lemon, 2009; Dethlefs, 2014) is another applica- tion of nlg, but typically it is closely related to dialogue management, so that management and …
Dempster-Shafer theoretic resolution of referential ambiguity
T Williams, F Yazdani, P Suresh, M Scheutz… – Autonomous …, 2018 – Springer
… and so forth. Alternatively, at this stage the robot may elect to generate an anaphoric or deictic expres- sion (involving eye gaze, gesture, or other modalities) rather than a complex noun phrase. 4.5 Surface realization Once a …
Automatic Syntactic Analysis Based on Selectional Preferences
A Gelbukh, H Calvo – 2018 – Springer
… Indeed, what we have then is a new entity called a discourse. A very important problem exists in the analysis of discourse: co-reference. A certain type of co-reference is called anaphoric reference; it points to previous refere
Chapter 5: Discourse and Dialogue
SE BRENNAN, AK KUHLEN… – Stevens’ Handbook of …, 2018 – books.google.com
… answer alone. Finally, computational approaches can implement models of language use (often using findings from these other approaches) to create working text generation programs or spoken dialogue systems. With these …