Articles

Automatic word segmentation is a basic re- quirement for unsupervised learning in morpho- logical analysis. In this paper, we formulate a novel recursive method for minimum descrip- tion length (MDL) word segmentation, whose basic operation is resegmenting the corpus on a prefix (equivalently, a suffix). We derive a local expression …...

In the framework of bilingual lexicon acquisition from cross-lingually relevant news articles on the Web, it is relatively harder to reliably estimate bilin- gual term correspondences for low frequency terms. Considering such a situation, this paper proposes to complementarily use much larger monolingual Web documents collected by search engines, as …...

The Papillon project is a collaborative project to establish a multilingual dictio- nary on the Web. This project started 4 years ago with French and Japanese. The partners are now also working on English, Chinese, Lao, Malay, Thai and Vietnamese. It aims to apply the LINUX cooperative construction paradigm to …...

We present a framework for the fast compu- tation of lexical affinity models. The frame- work is composed of a novel algorithm to effi- ciently compute the co-occurrence distribution between pairs of terms, an independence model, and a parametric affinity model. In compari- son with previous models, which either use …...

The evaluative character of a word is called its semantic orientation (SO). A positive SO indicates desirability (e.g. Good, Honest) and a negative SO indicates undesirability (e.g., Bad, Ugly). This paper presents a method, based on Turney (2003), for inferring the SO of a word from its statistical association with …...

We propose a multiple-document summa- rization system with user interaction. Our system extracts keywords from sets of docu- ments to be summarized and shows the key- words to a user on the screen. Among them, the user selects some keywords reflecting his/her needs. Our system controls the pro- duced summary …...

Email summarisation presents a unique set of requirements that are different from general text summarisation. This work describes the implementation of an email summarisation system for use in a voice-based Virtual Per- sonal Assistant developed for the EU FASiL Project. Evaluation results from the first inte- grated version of the …...

We introduce a new, linguistically grounded measure of collocativity based on the property of limited modifiability and test it on German PP-verb combinations. We show that our mea- sure not only significantly outperforms the stan- dard lexical association measures typically em- ployed for collocation extraction, but also yields a valuable …...

We ran both Brill’s rule-based tagger and TNT, a statistical tagger, with a default German newspaper-language model on a medical text corpus. Supplied with limited lexicon re- sources, TNT outperforms the Brill tagger with state-of-the-art performance figures (close to 97% accuracy). We then trained TNT on a large annotated medical …...

In order to control the quality of internet-based language corpora, we developed a method to verify automatically that texts are of (near-) native quality. For the LOCNESS and ICLE corpora, the method is rather successful in separating native and non-native learner texts. The Equal Error Rate is about 10%. However, …...

This work investigates the variation in a word’s dis- tributionally nearest neighbours with respect to the similarity measure used. We identify one type of variation as being the relative frequency of the neigh- bour words with respect to the frequency of the tar- get word. We then demonstrate a three-way …...

We are presenting a working system for automated news analysis that ingests an average total of 7600 news articles per day in five languages. For each language, the system detects the major news stories of the day using a group-average unsupervised ag- glomerative clustering process. It also tracks, for each …...

This paper addresses the mitigation of medi- cal errors due to the confusion of sound-alike and look-alike drug names. Our approach involves application of two new methods— one based on orthographic similarity (“look- alike”) and the other based on phonetic sim- ilarity (“sound-alike”). We present a new recall-based evaluation methodology …...

This paper describes a method to acquire hy- ponyms for given hypernyms from HTML doc- uments on the WWW. We assume that a head- ing (or explanation) of an itemization (or list- ing) in an HTML document is likely to contain a hypernym of the items in the itemization, and …...

This paper presents a statistical model that in- terprets the evaluation of ranking methods as a random experiment. This model predicts the variability of evaluation results, so that appro- priate significance tests for the results can be derived. The paper concludes with an empirical validation of the model on a …...

We present a novel automatic approach to constructing a bilingual semantic network—the BiFrameNet, to enhance statistical and transfer-based machine translation systems. BiFrameNet is a frame semantic representation, and contains semantic structure transfers between English and Chinese. The English FrameNet and the Chinese HowNet provide us with two different views of …...

In this paper, we introduce a model for sense as- signment which relies on assigning senses to the contexts within which words appear, rather than to the words themselves. We argue that word senses as such are not directly encoded in the lexicon of the language. Rather, each word is …...

This paper proposes a method to improve the robustness of a word sense disambigua- tion (WSD) system for Japanese. Two WSD classifiers are trained from a word sense-tagged corpus: one is a classifier ob- tained by supervised learning, the other is a classifier using hypernyms extracted from definition sentences in …...

Classifier combination is a promising way to improve performance of word sense disambiguation. We propose a new combinational method in this paper. We first construct a series of Naïve Bayesian classifiers along a sequence of orderly varying sized windows of context, and perform sense selection for both training samples and …...

In this paper, we explore the use of automatic syntactic simplification for improving content selection in multi-document summarization. In particular, we show how simplifying parenthet- icals by removing relative clauses and apposi- tives results in improved sentence clustering, by forcing clustering based on central rather than background information. We argue …...