Inferring Sentence-internal Temporal Relations
نویسندگان
چکیده
In this paper we propose a data intensive approach for inferring sentence-internal temporal relations, which relies on a simple probabilistic model and assumes no manual coding. We explore various combinations of features, and evaluate performance against a goldstandard corpus and human subjects performing the same task. The best model achieves 70.7% accuracy in inferring the temporal relation between two clauses and 97.4% accuracy in ordering them, assuming that the temporal relation is known.
منابع مشابه
Learning Sentence-internal Temporal Relations
In this paper we propose a data intensive approach for inferring sentence-internal temporal relations. Temporal inference is relevant for practical NLP applications which either extract or synthesize temporal information (e.g., summarisation, question answering). Our method bypasses the need for manual coding by exploiting the presence of markers like after, which overtly signal a temporal rela...
متن کاملBefore and after: sentence-internal and -external discourse relations
This study presents a corpora investigation (online available texts of written and spoken English) regarding the usage of the discourse connectives before and after in multi-sentence discourse. We focus on sentences that begin with a connective and analyse these along with the preceding text. Our results show that two discourse relations have to be derived for these sentences: a sentence-extern...
متن کاملThesis Proposal Verb Semantics for Natural Language Understanding
A verb is the organizational core of a sentence. Understanding the meaning of the verb is therefore key to understanding the meaning of the sentence. Natural language understanding is the problem of mapping natural language text to its meaning representation: entities and relations anchored to the world. Since verbs express relations over their arguments in text, a lexical resource about verbs ...
متن کاملInferring Implicit Causal Relationships in Biomedical Literature
Biomedical relations are often expressed between entities occurring within the same sentence through syntactic means. However, a significant portion of such relations (in particular, causal relations) are expressed implicitly across sentence boundaries. Inferring these discourse-level relations can be challenging in the absence of syntactic clues. In this paper, we present a study of textual ch...
متن کاملTemporal order relations in language comprehension.
The role of temporal orientation (chronological or reverse) and chronological distance (close, intermediate, or distant) in general event knowledge on language comprehension was examined. Experiment 1 used a relation-recognition paradigm in which the comprehension of a target event could be facilitated or disrupted by the temporal orientation implied by the prior information. Experiments 2 and ...
متن کامل