Natural language processing systems need large lexicons containing explicit information about lexical-semantlc relationships, selection restrictions, and verb categories. Because the labor involved in constructing such lexicons by hand is overwhelming, we have been trying to construct lexical entries automatically from information available in the machine-readable version of Webst@r's ~@ve~h Co...

this paper I first explain briefly the properties ofone type ofMuIti-Word Expression (MWE), viz., flexible idioms, and how they are dealt with in the Rosetta machine translation system. Taking this as a starting point and generalizing beyond it, I argue that a standardized lexical representation for flexible idioms is not so straightforward. Nevertheless, I make a very concrete proposal for an ...

this paper I first explain briefly the properties ofone type ofMuIti-Word Expression (MWE), viz., flexible idioms, and how they are dealt with in the Rosetta machine translation system. Taking this as a starting point and generalizing beyond it, I argue that a standardized lexical representation for flexible idioms is not so straightforward. Nevertheless, I make a very concrete proposal for an ...

This paper describes successful applications of discriminative lexicon models to the statistical machine translation (SMT) systems into morphologically complex languages. We extend the previous work on discriminatively trained lexicon models to include more contextual information in making lexical selection decisions by building a single global log-linear model of translation selection. In offl...

The swinging lexical network proposal (Abdel Rahman & Melinger, 2009a this issue) incorporates three assumptions that are independently motivated and pre-existing in the literature. We claim that the combination of these three assumptions provides an account for a wide range of facilitation and interference observations. In their comment, Mahon and Caramazza question the success of our proposal...

There are many cases in which the natural translation of one language into another results in a very different form than that of the original. The existence of translation divergences (i.e., crosslinguistic distinctions) makes the straightforward transfer from source structures into target structures impractical. Many existing translation systems have mechanisms for handling divergent structure...

A basic task in opinion mining deals with determining the overall polarity orientation of a document about some topic. This has several applications such as detecting consumer opinions in on-line product reviews or increasing the effectiveness of social media marketing campaigns. However, the informal features of Web 2.0 texts can affect the performance of automated opinion mining tools. These ...

Many researchers have used lexical networks and ontologies to mitigate synonymy and polysemy problems in Question Answering (QA), systems coupled with taggers, query classifiers, and answer extractors in complex and ad-hoc ways. We seek to make QA systems reproducible with shared and modest human effort, carefully separating knowledge from algorithms. To this end, we propose an aesthetically “c...

This work addresses the classification of word pairs as instances of lexical-semantic relations. The classification is approached by leveraging patterns of co-occurrence contexts from corpus data. The significance of using dependency information, of augmenting the set of dependency paths provided to the system, and of generalizing patterns using part-of-speech information for the classification...

this paper examines the semantic contribution of -?r and -andeh suffixes in persian based on lieber’s (2004) lexical semantic representation. this framework using six semantic features ([material], [dynamic], [location], [ieps] , [b] and [ci] and a principle called coordination principle studies the semantic contribution of lexical items including affixes and their functions in compounding, der...