Articles

∗ Traditional word alignment approaches cannot come up with satisfactory results for Named Entities. In this paper, we propose a novel approach using a maximum entropy model for named entity alignment. To ease the training of the maximum entropy model, bootstrapping is used to help supervised learning. Unlike previous work …...

The morphology of Semitic languages is unique in the sense that the major word-formation mechanism is an inherently non-concatenative process of inter- digitation, whereby two morphemes, a root and a pattern, are interwoven. Identifying the root of a given word in a Semitic language is an important task, in some …...

State-of-the-art machine translation techniques are still far from producing high quality translations. This drawback leads us to introduce an alterna- tive approach to the translation problem that brings human expertise into the machine translation sce- nario. In this framework, namely Computer As- sisted Translation (CAT), human translators inter- act with …...

We address the issue of judging the significance of rare events as it typically arises in statistical natural- language processing. We first define a general ap- proach to the problem, and we empirically com- pare results obtained using log-likelihood-ratios and Fisher’s exact test, applied to measuring strength of bilingual word …...

This paper provides evidence for Genzel and Char- niak’s (2002) entropy rate principle, which predicts that the entropy of a sentence increases with its po- sition in the text. We show that this principle holds for individual sentences (not just for averages), but we also find that the entropy rate …...

In this paper, we explore the use of Random Forests (RFs) (Amit and Geman, 1997; Breiman, 2001) in language modeling, the problem of predicting the next word based on words already seen before. The goal in this work is to develop a new language mod- eling approach based on randomly …...

The focus of research in text classification has ex- panded from simple topic identification to more challenging tasks such as opinion/modality identi- fication. Unfortunately, the latter goals exceed the ability of the traditional bag-of-word representation approach, and a richer, more structural representa- tion is required. Accordingly, learning algorithms must be …...

It is often useful to classify email accord- ing to the intent of the sender (e.g., "pro- pose a meeting", "deliver information"). We present experimental results in learn- ing to classify email in this fashion, where each class corresponds to a verb- noun pair taken from a predefined ontol- ogy …...

Logs of user queries to an internet search engine pro- vide a large amount of implicit and explicit informa- tion about language. In this paper, we investigate their use in spelling correction of search queries, a task which poses many additional challenges beyond the traditional spelling correction problem. We pre- …...

A novel technique for maximum “a posteriori” (MAP) adaptation of maximum entropy (MaxEnt) and maximum entropy Markov models (MEMM) is presented. The technique is applied to the problem of recov- ering the correct capitalization of uniformly cased text: a “background” capitalizer trained on 20Mwds of Wall Street Journal (WSJ) text …...

Much natural language processing still depends on the Euclidean (cosine) distance function between two feature vectors, but this has severe problems with regard to feature weightings and feature cor- relations. To answer these problems, we propose an optimal metric distance that can be used as an alter- native to the …...

Chinese part-of-speech (POS) tagging assigns one POS tag to each word in a Chinese sentence. However, since words are not demarcated in a Chinese sentence, Chinese POS tagging requires word segmentation as a prerequisite. We could perform Chinese POS tagging strictly after word segmentation (one-at-a-time approach), or perform both word …...

Starting from first principles, we re-visit the statistical approach and study two forms of the Bayes decision rule: the common rule for minimizing the number of string errors and a novel rule for minimizing the number of symbols errors. The Bayes decision rule for minimizing the number of string errors …...

We perform Noun Phrase Bracketing by using a lo- cal, maximum entropy-based tagging model, which produces bracketing hypotheses. These hypothe- ses are subsequently fed into a reranking frame- work based on support vector machines. We solve the problem of hierarchical structure in our tag- ging model by modeling underspecified tags, …...

Irregular (so-called broken) plural identification in modern standard Arabic is a problematic issue for information retrieval (IR) and language engineering applications, but their effect on the performance of IR has never been examined. Broken plurals (BPs) are formed by altering the singular (as in English: tooth � teeth) through an …...

This work applies boosted wrapper induction (BWI), a machine learning algorithm for informa- tion extraction from semi-structured documents, to the problem of named entity recognition. The de- fault feature set of BWI is augmented with features based on distributional term clusters induced from a large unlabeled text corpus. Using no …...

This paper presents Japanese morphological analy- sis based on conditional random fields (CRFs). Pre- vious work in CRFs assumed that observation se- quence (word) boundaries were fixed. However, word boundaries are not clear in Japanese, and hence a straightforward application of CRFs is not possible. We show how CRFs can …...

Given a parallel parsed corpus, statistical tree- to-tree alignment attempts to match nodes in the syntactic trees for a given sentence in two languages. We train a probabilistic tree transduction model on a large automatically parsed Chinese-English corpus, and evaluate re- sults against human-annotated word level align- ments. We find …...

We propose to score phrase translation pairs for statistical machine translation using term weight based models. These models employ tf.idf to encode the weights of content and non-content words in phrase translation pairs. The transla- tion probability is then modeled by simi- larity functions defined in a vector space. Two …...

This paper presents some of the first data visualiza- tions and analysis of distributions for a lexicalized statistical parsing model, in order to better under- stand their nature. In the course of this analysis, we have paid particular attention to parameters that include bilexical dependencies. The prevailing view has been …...