• Publications
  • Influence
Wide-Coverage Semantic Analysis with Boxer
  • Johan Bos
  • Computer Science
  • 22 September 2008
Boxer is an open-domain software component for semantic analysis of text, based on Combinatory Categorial Grammar and Discourse Representation Theory, which shows that bridging references and pronouns are not resolved in most cases.
Predicate logic unplugged
Die vorliegende Arbeit wurde im Rahmen des Verbundvorhabens Verbmobil vom Bundes-ministerium f ur Bildung, Wissenschaft, Forschung und Technologie (BMBF) unter dem FF orderkennzeichen 01 IV 101 R
Predicting the 2011 Dutch Senate Election Results with Twitter
By improving the quality of the document collection and by performing sentiment analysis, predictions based on entity counts in tweets can be considerably improved, and become nearly as good as traditionally obtained opinion polls.
Linguistically Motivated Large-Scale NLP with C&C and Boxer
An NLP system which is based on syntactic and semantic formalisms from theoretical linguistics, and which is used to analyse the entire Gigaword corpus in less than 5 days using only 18 processors, represents a break-through in NLP technology.
Recognising Textual Entailment with Logical Inference
This work incorporates model building, a technique borrowed from automated reasoning, and shows that it is a useful robust method to approximate entailment, and uses machine learning to combine these deep semantic analysis techniques with simple shallow word overlap.
Wide-Coverage Semantic Representations from a CCG Parser
It is demonstrated that well-formed semantic representations can be produced for over 97% of the sentences in unseen WSJ text, a major step towards widecoverage semantic interpretation, one of the key objectives of the field of NLP.
Developing a large semantically annotated corpus
It is argued that a bootstrapping approach comprising state-of-the-art NLP tools for parsing and semantic interpretation, in combination with a wiki-like interface for collaborative annotation of experts, and a game with a purpose for crowdsourcing, are the starting ingredients for fulfilling this enterprise.
The Groningen Meaning Bank
The goal of the Groningen Meaning Bank is to obtain a large corpus of English texts annotated with formal meaning representations, and a sophisticated bootstrapping approach employs existing language technology tools to get a reasonable approximation of the target annotations as a starting point.
DIPPER: Description and Formalisation of an Information-State Update Dialogue System Architecture
A formal syntax and semantics for the DIPPER information state update language is defined, independent of particular programming languages, and incorporates procedural attachments for access to external resources using OAA.
The Meaning Factory: Formal Semantics for Recognizing Textual Entailment and Determining Semantic Similarity
This work used an existing system based on formal semantics and logical inference to participate in the first subtask of SemEval-2014, reaching an accuracy of 82%, ranking in the top 5 of more than twenty participating systems.