Published on Fri Sep 03 2021

Detecting Speaker Personas from Conversational Texts

Jia-Chen Gu, Zhen-Hua Ling, Yu Wu, Quan Liu, Zhigang Chen, Xiaodan Zhu

Speaker Persona Detection (SPD) aims to detect speaker personas based on the plain conversational text. In this task, a best-matched persona is searched out from candidates. Both contexts and personas in SPD are composed of multiple sentences.

4
0
0
Abstract

Personas are useful for dialogue response prediction. However, the personas used in current studies are pre-defined and hard to obtain before a conversation. To tackle this issue, we study a new task, named Speaker Persona Detection (SPD), which aims to detect speaker personas based on the plain conversational text. In this task, a best-matched persona is searched out from candidates given the conversational text. This is a many-to-many semantic matching task because both contexts and personas in SPD are composed of multiple sentences. The long-term dependency and the dynamic redundancy among these sentences increase the difficulty of this task. We build a dataset for SPD, dubbed as Persona Match on Persona-Chat (PMPC). Furthermore, we evaluate several baseline models and propose utterance-to-profile (U2P) matching networks for this task. The U2P models operate at a fine granularity which treat both contexts and personas as sets of multiple sequences. Then, each sequence pair is scored and an interpretable overall score is obtained for a context-persona pair through aggregation. Evaluation results show that the U2P models outperform their baseline counterparts significantly.

Wed Apr 29 2020
Artificial Intelligence
Conversations with Search Engines: SERP-based Conversational Response Generation
This paper addresses the problem of answering complex information needs by conversing with search engines. Users can express their queries in natural language, and directly receive the information they need from a short system response in a conversational manner. We pursue two goals in this paper: (1) the creation of a suitable dataset, the Search as a Conversation (SaaC)
1
0
0
Thu Jun 03 2021
NLP
MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding
MPC-BERT is a pre-trained model for multi-party conversation understanding. It considers learning who says what to whom in a unified model with several elaborated self-supervised tasks. We evaluate MPC-BERt on three downstream tasks including addressee recognition, speaker
2
0
1
Tue May 02 2017
NLP
Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systems
Intelligent assistants on smartphones and home electronics can be seen as novel hybrids of domain-specific task-oriented spoken dialogue systems and open-domain non-task-oriented ones. This paper investigates determining whether or not a user is going to have a chat with the system.
0
0
0
Tue Mar 17 2020
NLP
XPersona: Evaluating Multilingual Personalized Chatbot
Personalized dialogue systems are an essential step toward better human-machine interaction. Existing personalized dialogue agents rely on monolingual datasets. We propose a multi-lingual extension of Persona-Chat, called XPersona.
0
0
0
Mon Sep 28 2020
NLP
Pchatbot: A Large-Scale Dataset for Personalized Chatbot
Pchatbot is a large-scale dialogue dataset that contains two subsets collected from Weibo and Judicial forums. Different from existing datasets, Pchatbot provides anonymized user IDs and timestamps for both posts and responses.
2
0
1
Sat Oct 24 2020
NLP
NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions
Existing conversational systems are mostly agent-centric. In real-world scenarios, it is highly desirable that users can speak freely in their own way. There is no clean mapping for a user's free form utterance to an ontology.
2
0
0
Mon Jun 12 2017
NLP
Attention Is All You Need
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms. Experiments on two machine translation tasks show these models to be superior in
51
215
883
Thu Oct 11 2018
NLP
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
BERT is designed to pre-train deep                bidirectional representations from unlabeled text. It can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
13
8
15
Mon Dec 22 2014
Machine Learning
Adam: A Method for Stochastic Optimization
Adam is an algorithm for first-order gradient-based optimization of stochastic objective functions. The method is straightforward to implement and has little memory requirements. It is well suited for problems that are large in terms of data and parameters.
3
0
2
Fri Jun 11 2021
NLP
BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
The proposed model outperforms strong baselines in response quality and persona consistency. The model consists of a BERT-over-BERT encoder and two BERT decoders.
1
1
1
Fri May 27 2016
Artificial Intelligence
TensorFlow: A system for large-scale machine learning
TensorFlow is a machine learning system that operates at large scale and in heterogeneous environments. It maps nodes of a dataflow graph across many machines in a cluster. TensorFlow supports a variety of applications, with particularly strong support for training and inference on deep neural networks.
0
0
0
Tue Jun 30 2015
Neural Networks
The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems
The Ubuntu Dialogue Corpus contains over 7 million utterances and 100 million words. The dataset has both the multi-turn property of conversations in the Dialog State Tracking Challenge datasets and the unstructured nature of interactions from microblog services such as Twitter.
0
0
0