Utterance Retrieval Based on Recurrent Surface Text Patterns
This paper investigates the use of recurrent surface text patterns to represent and index open-domain dialogue utterances for a retrieval system that can be embedded in a conversational agent. This approach involves both the building of a database of such patterns by mining a corpus of written dialogic interactions, and the exploitation of this database in a generalised vector space model for utterance retrieval. It is a corpus-based, unsupervised, parameterless and language-independent process. Our study indicates that the proposed model performs objectively well comparatively to other retrieval models on a task of selection of dialogue examples derived from a large corpus of written dialogues.
Code (1)
Tasks
RetrievalSimilar Papers 제목 키워드 기반
Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots
This paper proposes an utterance-to-utterance interactive matching network (U2U-IMN) for multi-turn response selection in retrieval-based chatbots. Different from previous methods following context-to-response matching o…
Conversational Response SelectionRetrievalSentenceBridging CNNs, RNNs, and Weighted Finite-State Machines
Recurrent and convolutional neural networks comprise two distinct families of models that have proven to be useful for encoding natural language utterances. In this paper we present SoPa, a new model that aims to bridge …
General ClassificationRepresentation LearningSmall Data Image Classificationtext-classification+1SoPa: Bridging CNNs, RNNs, and Weighted Finite-State Machines
Recurrent and convolutional neural networks comprise two distinct families of models that have proven to be useful for encoding natural language utterances. In this paper we present SoPa, a new model that aims to bridge …
Explainable artificial intelligenceGeneral ClassificationRepresentation Learningtext-classification+1Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots
We study response selection for multi-turn conversation in retrieval-based chatbots. Existing work either concatenates utterances in context or matches a response with a highly abstract context vector finally, which may …
Conversational Response SelectionRetrievalCFGs-2-NLU: Sequence-to-Sequence Learning for Mapping Utterances to Semantics and Pragmatics
In this paper, we present a novel approach to natural language understanding that utilizes context-free grammars (CFGs) in conjunction with sequence-to-sequence (seq2seq) deep learning. Specifically, we take a CFG author…
Natural Language Understanding