Improving Implicit Discourse Relation Recognition Through Feature Set Optimization
نویسندگان
چکیده
We provide a systematic study of previously proposed features for implicit discourse relation identification, identifying new feature combinations that optimize F1-score. The resulting classifiers achieve the best F1-scores to date for the four top-level discourse relation classes of the Penn Discourse Tree Bank: COMPARISON, CONTINGENCY, EXPANSION, and TEMPORAL. We further identify factors for feature extraction that can have a major impact on performance and determine that some features originally proposed for the task no longer provide performance gains in light of more powerful, recently discovered features. Our results constitute a new set of baselines for future studies of implicit discourse relation identification.
منابع مشابه
Improving Implicit Discourse Relation Recognition with Discourse-specific Word Embeddings
We introduce a simple and effective method to learn discourse-specific word embeddings (DSWE) for implicit discourse relation recognition. Specifically, DSWE is learned by performing connective classification on massive explicit discourse data, and capable of capturing discourse relationships between words. On the PDTB data set, using DSWE as features achieves significant improvements over base...
متن کاملAdversarial Connective-exploiting Networks for Implicit Discourse Relation Classification
Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to learn from another neural network with access to connectives, and thus encouraged to extract sim...
متن کاملDiscourse Relation Recognition by Comparing Various Units of Sentence Expression with Recursive Neural Network
We propose a method for implicit discourse relation recognition using a recursive neural network (RNN). Many previous studies have used the word-pair feature to compare the meaning of two sentences for implicit discourse relation recognition. Our proposed method differs in that we use various-sized sentence expression units and compare the meaning of the expressions between two sentences by con...
متن کاملRecognizing Implicit Discourse Relations through Abductive Reasoning with Large-scale Lexical Knowledge
Discourse relation recognition is the task of identifying the semantic relationships between textual units. Conventional approaches to discourse relation recognition exploit surface information and syntactic information as machine learning features. However, the performance of these models is severely limited for implicit discourse relation recognition. In this paper, we propose an abductive th...
متن کاملShallow Convolutional Neural Network for Implicit Discourse Relation Recognition
Implicit discourse relation recognition remains a serious challenge due to the absence of discourse connectives. In this paper, we propose a Shallow Convolutional Neural Network (SCNN) for implicit discourse relation recognition, which contains only one hidden layer but is effective in relation recognition. The shallow structure alleviates the overfitting problem, while the convolution and nonl...
متن کامل