A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Neural Utterance Ranking Model for Conversational Dialogue Systems
2016
Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue
In this study, we present our neural utterance ranking (NUR) model, an utterance selection model for conversational dialogue agents. ...
The NUR model ranks candidate utterances with respect to their suitability in relation to a given context using neural networks; in addition, a dialogue system based on the model converses with humans ...
Acknowledgements This study received a grant of JSPS Grants-in-aid for Scientific Research 16H05880 and a research grant from Kayamori Foundation of Informational Science Advancement. ...
doi:10.18653/v1/w16-3648
dblp:conf/sigdial/InabaT16
fatcat:sosynemjirhdbmi43jna6kf5ra
Weakly-Supervised Neural Response Selection from an Ensemble of Task-Specialised Dialogue Agents
[article]
2020
arXiv
pre-print
We model the problem of selecting the best response from a set of responses generated by a heterogeneous set of dialogue agents by taking into account the conversational history, and propose a Neural Response ...
However, conversations are dynamic in the sense that a selected response will change the conversation on-the-fly, influencing the subsequent utterances in the conversation, which makes the response selection ...
Ensemble Dialogue Systems: Song et al. (2016) proposed an ensemble method for dialogue systems using a combination of a retrieval-based and neural generation based agents. ...
arXiv:2005.03066v1
fatcat:zdi46ht635hhjjuf4ddsdcczn4
FCC: Fusing Conversation History and Candidate Provenance for Contextual Response Ranking in Dialogue Systems
[article]
2023
arXiv
pre-print
Response ranking in dialogues plays a crucial role in retrieval-based conversational systems. ...
We evaluate our model on the MSDialog dataset widely used for evaluating conversational response ranking tasks. ...
Neural response ranking models The upsurge of Word2Vec [14] and the development of neural network models facilitated learning-to-rank performance, and they are quickly adapted to dialogue response ranking ...
arXiv:2304.00180v1
fatcat:wxexu2odmjf5zih57jyjicjrba
GraphWOZ: Dialogue Management with Conversational Knowledge Graphs
[article]
2022
arXiv
pre-print
For conversational entity linking, we show how to connect utterance mentions to their corresponding entity in the knowledge graph with a neural model relying on a combination of both string and graph-based ...
Based on GraphWOZ, we present experimental results for two dialogue management tasks, namely conversational entity linking and response ranking. ...
Such knowledge graphs are frequently used with open domain dialogue systems, but have also been integrated with neural dialogue models for task-oriented dialogue systems [16] Graph representations of ...
arXiv:2211.12852v1
fatcat:o6cea5clpvf6vmmq2digicpzbm
Predicting Relevant Conversation Turns for Improved Retrieval in Multi-Turn Conversational Search
2019
Text Retrieval Conference
We developed a neural model for identifying relevant turn(s) corresponding to the given turn. ...
The goal of the track is to create a reusable benchmark for open-domain information-centric conversational dialogues and to establish a concrete and standard collection of data with information needs to ...
For this, we employed the neural re-ranking model based on BERT, as proposed by Nogueira and Cho [8] . ...
dblp:conf/trec/RissolaCCA19
fatcat:kx676csjjbbtjp6c2asdbn2vbq
EDA: Enriching Emotional Dialogue Acts using an Ensemble of Neural Annotators
[article]
2020
arXiv
pre-print
The recognition of emotion and dialogue acts enriches conversational analysis and help to build natural dialogue systems. ...
These neural models annotate the emotion corpora with dialogue act labels, and an ensemble annotator extracts the final dialogue act label. ...
These relations can be useful to learn about the emotional behaviours with dialogue acts to build a natural dialogue system and for more in-depth conversational analysis. ...
arXiv:1912.00819v3
fatcat:fwnyzsspgzgv5ixjwxnoodrefm
Introducing MANtIS: a novel Multi-Domain Information Seeking Dialogues Dataset
[article]
2019
arXiv
pre-print
We provide baseline results for the conversation response ranking and user intent prediction tasks. ...
Based on the literature, we elicit how existing tasks and test collections from the fields of IR, natural language processing (NLP) and dialogue systems (DS) fit into this model. ...
neural ranking model that creates matching matrices between each utterance in the conversation so far and the candidate response; (3) fine-tuned BERT [10] using the CLS token following [44] ; here, ...
arXiv:1912.04639v1
fatcat:ywrcnweumzhdxh46de64r4vs74
Modeling Situations in Neural Chat Bots
2017
Proceedings of ACL 2017, Student Research Workshop
This paper presents neural conversational models that have general mechanisms for handling a variety of situations that affect our responses. ...
It is, however, still hard to utilize the neural network-based SEQ2SEQ model for dialogue modeling in spite of its acknowledged success in machine translation. ...
Utterance The input utterance (to be responded to by the system) is a primary conversational situation and is already modeled by the encoder in the neural SEQ2SEQ model. ...
doi:10.18653/v1/p17-3020
dblp:conf/acl/SatoYTK17
fatcat:ch6g4lbms5culii5fygo5so3da
A Retrieval-Based Dialogue System Utilizing Utterance and Context Embeddings
2017
2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)
Finding semantically rich and computerunderstandable representations for textual dialogues, utterances and words is crucial for dialogue systems (or conversational agents), as their performance mostly ...
In this paper, the utilization of embeddings for answer retrieval is explored by using Locality-Sensitive Hashing Forest (LSH Forest), an Approximate Nearest Neighbor (ANN) model, to find similar conversations ...
We gratefully acknowledge the support of QNH Consulting with the donation of the Nvidia GTX 1070 GPU used for this research and for providing the Vodafone dataset. ...
doi:10.1109/icmla.2017.00011
dblp:conf/icmla/BartlS17
fatcat:lnxda5dd7vccpj5t3664h2brru
Entrainable Neural Conversation Model Based on Reinforcement Learning
2020
IEEE Access
We optimized a neural conversation model to the entrainment scores using reinforcement learning so that the system can control the degree of entrainment of the system response. ...
Experimental results showed that the proposed entrainable neural conversation model generated comparable or more natural responses than conventional models and satisfactorily controlled the degree of entrainment ...
In this paper, we incorporate entrainment phenomena into a neural conversation model for building a more natural and user-satisfied dialogue system. ...
doi:10.1109/access.2020.3027099
fatcat:p5hymgtl4bga7chi3xz6pcg23m
Multi-Turn Beam Search for Neural Dialogue Modeling
[article]
2019
arXiv
pre-print
In neural dialogue modeling, a neural network is trained to predict the next utterance, and at inference time, an approximate decoding algorithm is used to generate next utterances given previous ones. ...
We propose a novel approach for conversation-level inference by explicitly modeling the dialogue partner and running beam search across multiple conversation turns. ...
Neural Dialogue Modeling Neural dialogue modeling is a framework in which a neural network is used to model a full conversation between two speakers (Vinyals and Le, 2015) . ...
arXiv:1906.00141v2
fatcat:5r7sktsbhbfhhiuakv2grdyfra
Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks
[article]
2021
arXiv
pre-print
With the advancements made by neural approaches in applications such as machine translation (MT), summarization and dialog systems, the need for coherence evaluation of these tasks is now more crucial ...
tasks, and contrast this with their performance on three downstream applications: coherence evaluation for MT and summarization, and next utterance prediction in retrieval-based dialog. ...
(iii) Next Utterance Ranking. Dialogue quality assessment is crucial for evaluating dialogue systems. ...
arXiv:2004.14626v2
fatcat:avtt5p6znvfebpb3vyv7zga3l4
A retrieval-based dialogue system utilizing utterance and context embeddings
[article]
2017
arXiv
pre-print
Finding semantically rich and computer-understandable representations for textual dialogues, utterances and words is crucial for dialogue systems (or conversational agents), as their performance mostly ...
In this paper, the utilization of embeddings for answer retrieval is explored by using Locality-Sensitive Hashing Forest (LSH Forest), an Approximate Nearest Neighbor (ANN) model, to find similar conversations ...
We gratefully acknowledge the support of QNH Consulting with the donation of the Nvidia GTX 1070 GPU used for this research and for providing the Vodafone dataset. ...
arXiv:1710.05780v3
fatcat:o2ci6z5cdrcpzfjdaesxvee4ky
Shaping the Narrative Arc: Information-Theoretic Collaborative DialoguePaper type: Technical Paper
2020
International Conference on Computational Creativity
Empirically, we show how the narrative arc function can model existing dialogues and shape conversation models towards either mode. ...
Collaborative dialogue is distinct from chit-chat in that it is knowledge building, each utterance provides just enough information to add specificity and reduce ambiguity without limiting the conversation ...
While neural response generation systems provide a trainable end-to-end system for language generation, these methods are prone to providing generic, unspecific responses (Li and others 2015) . ...
dblp:conf/icccrea/MathewsonCCFB20
fatcat:snsxvx4v35d3noyu6bb34sj2lm
The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems
[article]
2016
arXiv
pre-print
This provides a unique resource for research into building dialogue managers based on neural language models that can make use of large amounts of unlabeled data. ...
This paper introduces the Ubuntu Dialogue Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words. ...
We would like to thank Laurent Charlin for his input into this paper, as well as Gabriel Forgues and Eric Crawford for interesting discussions. ...
arXiv:1506.08909v3
fatcat:swu6oxfehnhbdarczgixvljefe
« Previous
Showing results 1 — 15 out of 3,640 results