A Persona-based Multi-turn Conversation Model in an Adversarial Learning Framework

Anish Khazane; Erik T. Mueller; Oluwatobi O. Olabiyi

RECORD

A Persona-based Multi-turn Conversation Model in an Adversarial Learning Framework

Oluwatobi O. Olabiyi, Anish Khazane, Erik T. Mueller

Computation and Language · Submitted 29 Apr 2019

abstract compiled · 2026-09-23 · no language-model review

The authors' main claim The resulting persona hredGAN ($phredGAN$) shows better performance than both the existing persona-based Seq2Seq and hredGAN models when those external attributes are available in a multi-turn dialogue corpus.

how it is stated · asserted 1.00 read the record →

Comment (0) Read on arXiv ↗

Cite ▾

arXiv ID1905.01998 (version 1)

Pith IDOW3FQOAC, Pith's permanent record of this paper and its review

CitationAnish Khazane, Erik T. Mueller, Oluwatobi O. Olabiyi. "A Persona-based Multi-turn Conversation Model in an Adversarial Learning Framework." arXiv:1905.01998 (2019). https://pith.science/paper/OW3FQOAC

Claim paper

The compiled record

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.

Open the compiled record

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 3,782 input tokens.

What the abstract itself states, as probabilities: claims first 0.05 · states limitation 0.31 · human participants 0.17 · controlled comparison 0.89 · randomized assignment 0.01 · states quantitative result 0.15 · compares with prior results 0.98 · mentions code or data availability 0.03.

The abstract, sentence by sentence

arXiv listing abstract v1. Results and the main claim are underlined; show every role.

In this paper, we extend the persona-based sequence-to-sequence (Seq2Seq) neural network conversation model to multi-turn dialogue by modifying the state-of-the-art hredGAN architecture. To achieve this, we introduce an additional input modality into the encoder and decoder of hredGAN to capture other attributes such as speaker identity, location, sub-topics, and other external attributes that might be available from the corpus of human-to-human interactions. The resulting persona hredGAN ($phredGAN$) shows better performance than both the existing persona-based Seq2Seq and hredGAN models when those external attributes are available in a multi-turn dialogue corpus. This superiority is demonstrated on TV drama series with character consistency (such as Big Bang Theory and Friends) and customer service interaction datasets such as Ubuntu dialogue corpus in terms of perplexity, BLEU, ROUGE, and Distinct n-gram scores.

background contribution method result interpretation main claim

What the classifier reports for each sentence. The number is the probability it gave the label.
#	sentence	role	the authors' own work	states the main conclusion	strength
s0	In this paper, we extend the persona-based sequence-to-sequence (Seq2Seq) neural network conversation model to multi-turn dialogue by modifying the state-of-the-art hredGAN architecture.	contribution 0.97	0.86	0.07	asserted 0.98
s1	To achieve this, we introduce an additional input modality into the encoder and decoder of hredGAN to capture other attributes such as speaker identity, location, sub-topics, and other external attributes that might be available from the corpus of human-to-human interactions.	method 0.96	0.90	0.03	asserted 0.76
s2	The resulting persona hredGAN ($phredGAN$) shows better performance than both the existing persona-based Seq2Seq and hredGAN models when those external attributes are available in a multi-turn dialogue corpus.	result 1.00	0.93	0.79	asserted 1.00
s3	This superiority is demonstrated on TV drama series with character consistency (such as Big Bang Theory and Friends) and customer service interaction datasets such as Ubuntu dialogue corpus in terms of perplexity, BLEU, ROUGE, and Distinct n-gram scores.	result 0.98	0.92	0.34	asserted 1.00

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.73.

What was examined, and what was not

sources read

arXiv listing abstract v1

not examined

full text
figures and tables
references and citing sentences
relations to other papers

levels run

P abstract

not run

S sections
T body sentences
C citations
R cross-paper relations

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. Every number in the measurements table is the authors', checked by code. Record as JSON

The paper

Original abstract

In this paper, we extend the persona-based sequence-to-sequence (Seq2Seq) neural network conversation model to multi-turn dialogue by modifying the state-of-the-art hredGAN architecture. To achieve this, we introduce an additional input modality into the encoder and decoder of hredGAN to capture other attributes such as speaker identity, location, sub-topics, and other external attributes that might be available from the corpus of human-to-human interactions. The resulting persona hredGAN ($phredGAN$) shows better performance than both the existing persona-based Seq2Seq and hredGAN models when those external attributes are available in a multi-turn dialogue corpus. This superiority is demonstrated on TV drama series with character consistency (such as Big Bang Theory and Friends) and customer service interaction datasets such as Ubuntu dialogue corpus in terms of perplexity, BLEU, ROUGE, and Distinct n-gram scores.

Human review

How Pith checks papers → · Full audit of this paper →

How the literature uses it

What this paper does with the arXiv papers it cites

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

Papers whose main result relates to this one's

Found among the papers closest to this one by title and main claim. Pith's classifier compared each pair's main results and a second model family confirmed the relation; checked against two further families, shown conflicts agreed 118 times in 120 and shown same results 218 times in 239. The quoted sentence is the other paper's main claim.

States the same result 1 paper

To demonstrate the superior performance of phredGAN over the persona Seq2Seq model, we experiment with two conversational datasets, the Ubuntu Dialogue Corpus (UDC) and TV series transcripts from the Big Bang Theory and Friends.

An Adversarial Learning Framework For A Persona-Based Multi-Turn Dialogue Model · 0.87

What it cites · 9 sentences without a confident label

Builds on 1 paper

To overcome these limitations, we propose $phredGAN$, a multi-modal $hredGAN$ dialogue system which additionally conditions the adversarial framework proposed by Olabiyi et al. [ref] on speaker and/or utterance attributes in order to maintain response quality of $hredGAN$ and still capture speaker and other modalities within a conversation.

Multi-turn Dialogue Response Generation in an Adversarial Learning Framework · Introduction · 0.86

Uses the method or tool of 2 papers

We train and sample the proposed phredGAN similar to the procedure for $hredGAN$ [ref] .

Multi-turn Dialogue Response Generation in an Adversarial Learning Framework · Introduction · 0.93
Due to the large word vocabulary size, we use sampled softmax loss [ref] for MLE loss to expedite the training process.

On Using Very Large Target Vocabulary for Neural Machine Translation · Model Training · 0.99

Compares with 1 paper

In this section, we explore $phredGAN$'s results on two conversational datasets and compare its performance to the persona system in Li et al. [ref] and $hredGAN$ [ref] in terms of quantitative and qualitative measures.

Multi-turn Dialogue Response Generation in an Adversarial Learning Framework · Experiments and Results · 1.00

Cites as background 2 papers

For example, Serban et al. [ref] and Xing et al. [ref] introduce a Hierarchical Recurrent Encoder-Decoder (HRED) network architecture that combines a series of recurrent neural networks to capture long-term context state within a dialogue.

Hierarchical Recurrent Attention Network for Response Generation · Introduction · 0.89
Zhang et al. [ref] propose a slightly different approach.

Personalizing Dialogue Agents: I have a dog, do you have pets too? · Introduction · 0.84

Discussion

Know something about this paper? Leave a comment, or highlight any passage above to comment on it.