Detecting Speaker Personas from Conversational Texts
- URL: http://arxiv.org/abs/2109.01330v1
- Date: Fri, 3 Sep 2021 06:14:38 GMT
- Title: Detecting Speaker Personas from Conversational Texts
- Authors: Jia-Chen Gu, Zhen-Hua Ling, Yu Wu, Quan Liu, Zhigang Chen, Xiaodan Zhu
- Abstract summary: We study a new task, named Speaker Persona Detection (SPD), which aims to detect speaker personas based on the plain conversational text.
We build a dataset for SPD, dubbed as Persona Match on Persona-Chat (PMPC)
We evaluate several baseline models and propose utterance-to-profile (U2P) matching networks for this task.
- Score: 52.4557098875992
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- Phrase Retrieval for Open-Domain Conversational Question Answering with
Conversational Dependency Modeling via Contrastive Learning [54.55643652781891]
Open-Domain Conversational Question Answering (ODConvQA) aims at answering questions through a multi-turn conversation.
We propose a method to directly predict answers with a phrase retrieval scheme for a sequence of words.
arXiv Detail & Related papers (2023-06-07T09:46:38Z) - Speaker Profiling in Multiparty Conversations [31.518453682472575]
This research paper explores the task of Speaker Profiling in Conversations (SPC)
The primary objective of SPC is to produce a summary of persona characteristics for each individual speaker present in a dialogue.
To address the task of SPC, we have curated a new dataset named SPICE, which comes with specific labels.
arXiv Detail & Related papers (2023-04-18T08:04:46Z) - When Crowd Meets Persona: Creating a Large-Scale Open-Domain Persona
Dialogue Corpus [13.051107304650627]
Building a natural language dataset requires caution since word semantics is vulnerable to subtle text change or the definition of the annotated concept.
In this study, we tackle these issues when creating a large-scale open-domain persona dialogue corpus.
arXiv Detail & Related papers (2023-04-01T16:10:36Z) - Semantic Parsing for Conversational Question Answering over Knowledge
Graphs [63.939700311269156]
We develop a dataset where user questions are annotated with Sparql parses and system answers correspond to execution results thereof.
We present two different semantic parsing approaches and highlight the challenges of the task.
Our dataset and models are released at https://github.com/Edinburgh/SPICE.
arXiv Detail & Related papers (2023-01-28T14:45:11Z) - A Graph-Based Context-Aware Model to Understand Online Conversations [3.8345539498627437]
In online conversations, comments and replies may be based on external context beyond the immediately relevant information.
We propose GraphNLI, a novel graph-based deep learning architecture that uses graph walks to incorporate the wider context of a conversation.
We evaluate GraphNLI on two such tasks - polarity prediction and misogynistic hate speech detection.
arXiv Detail & Related papers (2022-11-16T20:51:45Z) - Question-Interlocutor Scope Realized Graph Modeling over Key Utterances
for Dialogue Reading Comprehension [61.55950233402972]
We propose a new key utterances extracting method for dialogue reading comprehension.
It performs prediction on the unit formed by several contiguous utterances, which can realize more answer-contained utterances.
As a graph constructed on the text of utterances, we then propose Question-Interlocutor Scope Realized Graph (QuISG) modeling.
arXiv Detail & Related papers (2022-10-26T04:00:42Z) - Findings on Conversation Disentanglement [28.874162427052905]
We build a learning model that learns utterance-to-utterance and utterance-to-thread classification.
Experiments on the Ubuntu IRC dataset show that this approach has the potential to outperform the conventional greedy approach.
arXiv Detail & Related papers (2021-12-10T05:54:48Z) - Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on
Spoken Language Understanding [101.24748444126982]
Decomposable tasks are complex and comprise of a hierarchy of sub-tasks.
Existing benchmarks, however, typically hold out examples for only the surface-level sub-task.
We propose a framework to construct robust test sets using coordinate ascent over sub-task specific utility functions.
arXiv Detail & Related papers (2021-06-29T02:53:59Z) - Dialogue History Matters! Personalized Response Selectionin Multi-turn
Retrieval-based Chatbots [62.295373408415365]
We propose a personalized hybrid matching network (PHMN) for context-response matching.
Our contributions are two-fold: 1) our model extracts personalized wording behaviors from user-specific dialogue history as extra matching information.
We evaluate our model on two large datasets with user identification, i.e., personalized dialogue Corpus Ubuntu (P- Ubuntu) and personalized Weibo dataset (P-Weibo)
arXiv Detail & Related papers (2021-03-17T09:42:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.