Linguistic Properties Matter for Implicit Discourse Relation Recognition: Combining Semantic Interaction, Topic Continuity and Attribution

نویسندگان

  • Wenqiang Lei
  • Yuanxin Xiang
  • Yuwei Wang
  • Qian Zhong
  • Meichun Liu
  • Min-Yen Kan
چکیده

Modern solutions for implicit discourse relation recognition largely build universal models to classify all of the different types of discourse relations. In contrast to such learning models, we build our model from first principles, analyzing the linguistic properties of the individual top-level Penn Discourse Treebank (PDTB) styled implicit discourse relations: Comparison, Contingency and Expansion. We find semantic characteristics of each relation type and two cohesion devices – topic continuity and attribution – work together to contribute such linguistic properties. We encode those properties as complex features and feed them into a Naı̈ve Bayes classifier, bettering baselines (including deep neural network ones) to achieve a new state-of-the-art performance level. Over a strong, feature-based baseline, our system outperforms oneversus-other binary classification by 4.83% for Comparison relation, 3.94% for Contingency and 2.22% for four-way clas-

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Intentionality In A Topical Approach Of Discourse Structure

The alternative to be outlined provides a proposal to solve a central problem in research on discourse structure and discourse coherence, namely, as pointed out by many authors, that of the relationship between linguistic and intentional structure, or, in other words, between subject matter and presentational relations (Mann and Thompson 1988) or informational and intentional relations (Moore a...

متن کامل

Recognizing 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 کامل

SWIM: A Simple Word Interaction Model for Implicit Discourse Relation Recognition

Capturing the semantic interaction of pairs of words across arguments and proper argument representation are both crucial issues in implicit discourse relation recognition. The current state-ofthe-art represents arguments as distributional vectors that are computed via bi-directional Long Short-Term Memory networks (BiLSTMs), known to have significant model complexity. In contrast, we demonstra...

متن کامل

Sense Annotation in the Penn Discourse Treebank

An important aspect of discourse understanding and generation involves the recognition and processing of discourse relations. These are conveyed by discourse connectives, i.e., lexical items like because and as a result or implicit connectives expressing an inferred discourse relation. The Penn Discourse TreeBank (PDTB) provides annotations of the argument structure, attribution and semantics o...

متن کامل

Implicit Causality, Negation, and Models of Discourse

Causality plays an important role in giving discourse its characteristic coherence. This paper examines how causality implicit in an utterance helps to organize dynamically constructed mental models of discourse. Experiments are reported suggesting that the linguistic form of utterances contributes significant semantic information about causality to a discourse representation. This view is cont...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2018