Recurrent Convolutional Neural Networks for Discourse Compositionality
The compositionality of meaning extends beyond the single sentence. Just as words combine to form the meaning of sentences, so do sentences combine to form the meaning of paragraphs, dialogues and general discourse. We introduce both a sentence model and a discourse model corresponding to the two levels of compositionality. The sentence model adopts convolution as the central operation for composing semantic vectors and is based on a novel hierarchical convolutional neural network. The discourse model extends the sentence model and is based on a recurrent neural network that is conditioned in a novel way both on the current sentence and on the current speaker. The discourse model is able to capture both the sequentiality of sentences and the interaction between different speakers. Without feature engineering or pretraining and with simple greedy decoding, the discourse model coupled to the sentence model obtains state of the art performance on a dialogue act classification experiment.
Code (0)
등록된 구현이 없습니다.
Tasks
Dialogue Act ClassificationFeature EngineeringSentenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Convolutional Neural Networks with Recurrent Neural Filters
We introduce a class of convolutional neural networks (CNNs) that utilize recurrent neural networks (RNNs) as convolution filters. A convolution filter is typically implemented as a linear affine transformation followed …
SentenceSentiment AnalysisVCWE: Visual Character-Enhanced Word Embeddings
Chinese is a logographic writing system, and the shape of Chinese characters contain rich syntactic and semantic information. In this paper, we propose a model to learn Chinese word embeddings via three-level composition…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)Part-Of-Speech Tagging+3Recognition of Visually Perceived Compositional Human Actions by Multiple Spatio-Temporal Scales Recurrent Neural Networks
The current paper proposes a novel neural network model for recognizing visually perceived human actions. The proposed multiple spatio-temporal scales recurrent neural network (MSTRNN) model is derived by introducing mul…
Sentence Segmentation in Narrative Transcripts from Neuropsychological Tests using Recurrent Convolutional Neural Networks
Automated discourse analysis tools based on Natural Language Processing (NLP) aiming at the diagnosis of language-impairing dementias generally extract several textual metrics of narrative transcripts. However, the absen…
POSSegmentationSentenceSentence segmentation+1Modeling Compositionality with Multiplicative Recurrent Neural Networks
We present the multiplicative recurrent neural network as a general model for compositional meaning in language, and evaluate it on the task of fine-grained sentiment analysis. We establish a connection to the previously…
Sentiment Analysis