Docalog: Multi-document Dialogue System using Transformer-based Span Retrieval
Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative answers based on users’ needs. This paper discusses our proposed approach, Docalog, for the DialDoc-22 (MultiDoc2Dial) shared task. Docalog identifies the most relevant knowledge in the associated document, in a multi-document setting. Docalog, is a three-stage pipeline consisting of (1) a document retriever model (DR. TEIT), (2) an answer span prediction model, and (3) an ultimate span picker deciding on the most likely answer span, out of all predicted spans. In the test phase of MultiDoc2Dial 2022, Docalog achieved f1-scores of 36.07% and 28.44% and SacreBLEU scores of 23.70% and 20.52%, respectively on the MDD-SEEN and MDD-UNSEEN folds.
Code (1)
Tasks
Response GenerationRetrievalSimilar Papers 제목 키워드 기반
A Compare Aggregate Transformer for Understanding Document-grounded Dialogue
Unstructured documents serving as external knowledge of the dialogues help to generate more informative responses. Previous research focused on knowledge selection (KS) in the document with dialogue. However, dialogue hi…
Response GenerationIncremental Transformer with Deliberation Decoder for Document Grounded Conversations
Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document. Obviously, document knowledge plays a critical role in Document Grounded Conversations, while …
DecoderExploiting Pairwise Mutual Information for Knowledge-Grounded Dialogue
External document knowledge is helpful for dialogue systems to generate high-quality responses. Although several knowledge-grounded dialogue models have been designed, external knowledge cannot be comprehensively exploit…
Dialogue GenerationMarCQAp: Effective Context Modeling for Conversational Question Answering
State-of-the-art models for Document-grounded Conversational Question Answering (DCQA) are based on the Transformer architecture. This raises two open issues: (a) Is it sufficient to concatenate the dialog history and th…
Conversational Question AnsweringQuestion AnsweringBuilding Knowledge-Grounded Dialogue Systems with Graph-Based Semantic Modeling
The knowledge-grounded dialogue task aims to generate responses that convey information from given knowledge documents. However, it is a challenge for the current sequence-based model to acquire knowledge from complex do…
Dialogue GenerationResponse GenerationText Generation