This paper presents a primarily data-driven Chinese word segmentation system and its performances on the closed track using two corpora at the first international Chinese word segmentation bakeoff. The system consists of a new words recognizer, a base segmentation algorithm, and procedures for combining single characters, suffixes, and checking segmentation consistencies.

We examine the task of temporal relation classification. Unlike existing approaches to this task, we (1) classify an event-event or eventtime pair as one of the 14 temporal relations defined in the TimeBank corpus, rather than as one of the six relations collapsed from the original 14; (2) employ sophisticated linguistic knowledge derived from a variety of semantic and discourse relations, rath...

Many research efforts have been devoted to develop robust statistical modeling techniques for many NLP tasks. Our field is now moving towards more complex tasks (e.g. RTE, QA), which require to complement these methods with a semantically rich representation based on world and linguistic knowledge (i.e. annotated linguistic data). In this tutorial we show several approaches to extract this know...

State-of-the-art statistical approaches to the Coreference Resolution task rely on sophisticated modeling, but very few (10-20) simple features. In this paper we propose to extend the standard feature set substantially, incorporating more linguistic knowledge. To investigate the usability of linguistically motivated features, we evaluate our system for a variety of machine learners on the stand...

This paper addresses the issue of "algorithm vs. representation" for case-based learning of linguistic knowledge. We first present empirical evidence that the success of case-based learning methods for natural language processing tasks depends to a large degree on the feature set used to describe the training instances. Next, we present a technique for automating feature set selection for case-...

This paper refers to the forthcoming ISCA (International Speech Communication Association) Workshop “Experimental Linguistics” in Athens, Greece, in 2006. The major objectives of the Workshop are (1) the development of experimental methodologies in linguistic research with new perspectives for the study of language, (2) the unification of linguistic knowledge in relation to linguistic theory ba...

Is it possible to discover semantic term relations useful for thesauri without any semantic information? Yes, it is. A recent approach for automatic thesaurus construction is based on explicit linguistic knowledge , i.e. a domain independent parser without any semantic component, and implicit linguistic knowledge contained in large amounts of real world texts. Such texts include implicitly the ...

this article aims at defining ricest stemmer in persian language set up in the regional information center for science and technology (ricest). we applied linguistic knowledge and standard algorithms to extract machine-readable rules. in addition, plural suffixes and exceptions of which compound nouns are a part were applied. different parts of singular-stemmer and their functions are described.

Natural language understanding systems have to exploit various kinds of knowledge in order to represent the meaning behind texts. Getting this knowledge in place is often such a huge enterprise that it is tempting to look for systems that can discover such knowledge automatically. We describe how the distinction between conceptual and linguistic semantics may assist in reaching this objective, ...

Natural language understanding systems have to exploit various kinds of knowledge to be able to represent the meaning behind texts. Getting this knowledge in place is often such a huge enterprise that it is tempting to look for systems that can discover such knowledge automatically. In this paper, we describe how the distinction between conceptual and linguistic semantics probably can assist in...