Entity Resolution in Open-domain Conversations

Shang, Mingyue; Wang, Tong; Eric, Mihail; Chen, Jiangning; Wang, Jing; Welch, Matthew D.; Deng, Tiantong; Grewal, Akshay; Wang, Han; Liu, Yue; Liu, Yang; Hakkani‐Tür, Dilek

doi:10.18653/v1/2021.naacl-industry.4

Cited by 4 publications

(2 citation statements)

References 23 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this realm, understanding user utterances plays a crucial role in holding meaningful conversations with users-this process is handled by the natural language understanding (NLU) component in traditional task-oriented dialogue systems [30]. A popular text understanding method, which has proven to be effective in various downstream tasks [19,22,33,34,51,59], is entity linking (EL): the task of recognizing mentions of entities in text and identifying their corresponding entries in a knowledge graph [4]. In this paper, we aim to investigate the role of entity linking in conversational systems.…”

Section: Introductionmentioning

confidence: 99%

Conversational Entity Linking: Problem Definition and Datasets

Joko

Hasibi

Balog

et al. 2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Machine understanding of user utterances in conversational systems is of utmost importance for enabling engaging and meaningful conversations with users. Entity Linking (EL) is one of the means of text understanding, with proven efficacy for various downstream tasks in information retrieval. In this paper, we study entity linking for conversational systems. To develop a better understanding of what EL in a conversational setting entails, we analyze a large number of dialogues from existing conversational datasets and annotate references to concepts, named entities, and personal entities using crowdsourcing. Based on the annotated dialogues, we identify the main characteristics of conversational entity linking. Further, we report on the performance of traditional EL systems on our Conversational Entity Linking dataset, ConEL, and present an extension to these methods to better fit the conversational setting. The resources released with this paper include annotated datasets, detailed descriptions of crowdsourcing setups, as well as the annotations produced by various EL systems. These new resources allow for an investigation of how the role of entities in conversations is different from that in documents or isolated short text utterances like queries and tweets, and complement existing conversational datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

Conversational Entity Linking: Problem Definition and Datasets

Joko

Hasibi

Balog

et al. 2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

show abstract

“…However, answering 𝑞 1 , 𝑞 3 or 𝑞 4 via a KB requires complex reasoning efforts. For 𝑞 1 , even with named entity disambiguation (NED) in conversations [17,43], it is unlikely that the correct KB entity (Tyrion Lannister) can be inferred, which means that the resulting answer search space [7] will not have the answer. For 𝑞 3 , answering via a KB requires a two-step lookup involving the first season, and then the corresponding release date.…”

mentioning

confidence: 99%

Conversational Question Answering on Heterogeneous Sources

Christmann¹,

Roy²,

Weikum³

2022

Preprint

View full text Add to dashboard Cite

Conversational question answering (ConvQA) tackles sequential information needs where contexts in follow-up questions are left implicit. Current ConvQA systems operate over homogeneous sources of information: either a knowledge base (KB), or a text corpus, or a collection of tables. This paper addresses the novel issue of jointly tapping into all of these together, this way boosting answer coverage and confidence. We present Convinse, an end-to-end pipeline for ConvQA over heterogeneous sources, operating in three stages: i) learning an explicit structured representation of an incoming question and its conversational context, ii) harnessing this framelike representation to uniformly capture relevant evidences from KB, text, and tables, and iii) running a fusion-in-decoder model to generate the answer. We construct and release the first benchmark, ConvMix, for ConvQA over heterogeneous sources, comprising 3000 real-user conversations with 16000 questions, along with entity annotations, completed question utterances, and question paraphrases. Experiments demonstrate the viability and advantages of our method, compared to state-of-the-art baselines. CCS CONCEPTS• Information systems → Question answering.

show abstract

Unified Named Entity Recognition as Multi-Label Sequence Generation

2023

2023 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Entity Resolution in Open-domain Conversations

Cited by 4 publications

References 23 publications

Conversational Entity Linking: Problem Definition and Datasets

Conversational Entity Linking: Problem Definition and Datasets

Conversational Question Answering on Heterogeneous Sources

Unified Named Entity Recognition as Multi-Label Sequence Generation

Contact Info

Product

Resources

About