Open-domain Commonsense Reasoning Using Discourse Relations from a Corpus of Weblog Stories
نویسندگان
چکیده
We present a method of extracting opendomain commonsense knowledge by applying discourse parsing to a large corpus of personal stories written by Internet authors. We demonstrate the use of a linear-time, joint syntax/discourse dependency parser for this purpose, and we show how the extracted discourse relations can be used to generate opendomain textual inferences. Our evaluations of the discourse parser and inference models show some success, but also identify a number of interesting directions for future work.
منابع مشابه
Mining Commonsense Knowledge From Personal Stories in Internet Weblogs
Recent advances in automated knowledge base construction have created new opportunities to address one of the hardest challenges in Artificial Intelligence: automated commonsense reasoning. In this paper, we describe our recent efforts in mining commonsense knowledge from the personal stories that people write about their lives in their Internet weblogs. We summarize three preliminary investiga...
متن کاملCommonsense Causal Reasoning Using Millions of Personal Stories
The personal stories that people write in their Internet weblogs include a substantial amount of information about the causal relationships between everyday events. In this paper we describe our efforts to use millions of these stories for automated commonsense causal reasoning. Casting the commonsense causal reasoning problem as a Choice of Plausible Alternatives, we describe four experiments ...
متن کاملUnsupervised extraction of semantic relations using discourse information. (Extraction non supervisée de relations sémantiques par l'analyse du discours)
Natural language understanding often relies on common-sense reasoning, for which knowledge about semantic relations, especially between verbal predicates, may be required. This thesis addresses the challenge of using a distibutional method to automatically extract the necessary semantic information for common-sense inference. Typical associations between pairs of predicates and a targeted set o...
متن کاملLearning a Probabilistic Model of Event Sequences from Internet Weblog Stories
One of the central problems in building broad-coverage story understanding systems is generating expectations about event sequences, i.e. predicting what happens next given some arbitrary narrative context. In this paper, we describe how a large corpus of stories extracted from Internet weblogs was used to learn a probabilistic model of event sequences using statistical language modeling techni...
متن کاملA Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories
Representation and learning of commonsense knowledge is one of the foundational problems in the quest to enable deep language understanding. This issue is particularly challenging for understanding casual and correlational relationships between events. While this topic has received a lot of interest in the NLP community, research has been hindered by the lack of a proper evaluation framework. T...
متن کامل