Exploiting knowledge graphs in industrial products and services: a survey of key aspects, challenges, and future perspectives
The rapid development of information and communication technologies has enabled a value
co-creation paradigm for developing industrial products and services, where massive …
co-creation paradigm for developing industrial products and services, where massive …
Document-level relation extraction as semantic segmentation
Document-level relation extraction aims to extract relations among multiple entity pairs from
a document. Previously proposed graph-based or transformer-based models utilize the …
a document. Previously proposed graph-based or transformer-based models utilize the …
Taxonomy of abstractive dialogue summarization: scenarios, approaches, and future directions
Abstractive dialogue summarization generates a concise and fluent summary covering the
salient information in a dialogue among two or more interlocutors. It has attracted significant …
salient information in a dialogue among two or more interlocutors. It has attracted significant …
Text generation with text-editing models
Text-editing models have recently become a prominent alternative to seq2seq models for
monolingual text-generation tasks such as grammatical error correction, simplification, and …
monolingual text-generation tasks such as grammatical error correction, simplification, and …
Analyzing and simulating user utterance reformulation in conversational recommender systems
User simulation has been a cost-effective technique for evaluating conversational
recommender systems. However, building a human-like simulator is still an open challenge …
recommender systems. However, building a human-like simulator is still an open challenge …
From spoken dialogue to formal summary: An utterance rewriting for dialogue summarization
Due to the dialogue characteristics of unstructured contexts and multi-parties with first-
person perspective, many successful text summarization works have failed when dealing …
person perspective, many successful text summarization works have failed when dealing …
Hierarchical context tagging for utterance rewriting
L Jin, L Song, L Jin, D Yu, D Gildea - … of the AAAI Conference on Artificial …, 2022 - ojs.aaai.org
Utterance rewriting aims to recover coreferences and omitted information from the latest turn
of a multi-turn dialogue. Recently, methods that tag rather than linearly generate sequences …
of a multi-turn dialogue. Recently, methods that tag rather than linearly generate sequences …
Decoupled dialogue modeling and semantic parsing for multi-turn text-to-SQL
Recently, Text-to-SQL for multi-turn dialogue has attracted great interest. Here, the user
input of the current turn is parsed into the corresponding SQL query of the appropriate …
input of the current turn is parsed into the corresponding SQL query of the appropriate …
RAST: Domain-robust dialogue rewriting as sequence tagging
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying
the missing content from the dialogue context. Until now, the existing models for this task …
the missing content from the dialogue context. Until now, the existing models for this task …
DIR: A Large-Scale Dialogue Rewrite Dataset for Cross-Domain Conversational Text-to-SQL
Semantic co-reference and ellipsis always lead to information deficiency when parsing
natural language utterances with SQL in a multi-turn dialogue (ie, conversational text-to-SQL …
natural language utterances with SQL in a multi-turn dialogue (ie, conversational text-to-SQL …