Exploiting a Verb Lexicon in Automatic Semantic Role Labelling

نویسندگان

  • Robert S. Swier
  • Suzanne Stevenson
چکیده

We develop an unsupervised semantic role labelling system that relies on the direct application of information in a predicate lexicon combined with a simple probability model. We demonstrate the usefulness of predicate lexicons for role labelling, as well as the feasibility of modifying an existing role-labelled corpus for evaluating a different set of semantic roles. We achieve a substantial improvement over an informed baseline.

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

Construction of a Chinese-english Verb Lexicon for Embedded Machine Translation in Cross-language Information Retrieval

This paper addresses the problem of automatic acquisition of lexical knowledge for rapid construction of MT engines multilingual applications. We describe new techniques for large-scale construction of a Chinese-English verb lexicon and we evaluate the coverage and eeectiveness of the resulting lexicon for a structured MT approach that is embedded in a cross-language information retrieval syste...

متن کامل

Construction of a Chinese-english Verb Lexicon for Machine Translation

This paper addresses the problem of automatic acquisition of lexical knowledge for rapid construction of MT engines in multilingual applications. We describe new techniques for large-scale construction of a Chinese-English verb lexicon and we evaluate the coverage and eeectiveness of the resulting lexicon. Leveraging oo an existing Chinese conceptual database called HowNet and a large, semantic...

متن کامل

Semantic Roles for Nominal Predicates: Building a Lexical Resource

The linguistic annotation of noun-verb complex predicates (also termed as light verb constructions) is challenging as these predicates are highly productive in Hindi. For semantic role labelling, each argument of the noun-verb complex predicate must be given a role label. For complex predicates, frame files need to be created specifying the role labels for each noun-verb complex predicate. The ...

متن کامل

Combining Contexts in Lexicon Learning for Semantic Parsing

We introduce a method for the automatic construction of noun entries in a semantic lexicon. Using the entries already present in the lexicon, semantic features are inherited from known to yet unknown words along similar contexts. As contexts, we use three specific syntactic-semantic relations: modifying adjective, verb-deep-subject and verbdeep-object. The combination of evidences from differen...

متن کامل

Building a Large Lexicon of Complex Valency Frames

This paper describes the process of building and using a new comprehensive lexicon of Czech verb valency frames based on complex valency frames. The main features of the lexicon entries are designed to bring important semantic information to computer processing of predicate constructions in running texts. The most notable features include two-level semantic labels with linkage to the Princeton ...

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 2005