Articles

We present an unsupervised approach to recognizing discourse relations of CON- TRAST, EXPLANATION-EVIDENCE, CON- DITION and ELABORATION that hold be- tween arbitrary spans of texts. We show that discourse relation classifiers trained on examples that are automatically ex- tracted from massive amounts of text can be used to distinguish between …...

Human evaluations of machine translation are extensive but expensive. Human eval- uations can take months to finish and in- volve human labor that can not be reused. We propose a method of automatic ma- chine translation evaluation that is quick, inexpensive, and language-independent, that correlates highly with human evalu- ation, …...

This paper describes a decoding algorithm for a syntax-based translation model (Ya- mada and Knight, 2001). The model has been extended to incorporate phrasal translations as presented here. In con- trast to a conventional word-to-word sta- tistical model, a decoder for the syntax- based model builds up an English parse …...

We present a framework for statistical machine translation of natural languages based on direct maximum entropy mod- els, which contains the widely used sour- ce-channel approach as a special case. All knowledge sources are treated as feature functions, which depend on the source language sentence, the target language sentence and …...

Stochastic unification-based grammars (SUBGs) define exponential distributions over the parses generated by a unification- based grammar (UBG). Existing algo- rithms for parsing and estimation require the enumeration of all of the parses of a string in order to determine the most likely one, or in order to calculate the statis- …...

This paper proposes a new method for word translation disambiguation using a machine learning technique called ‘Bilingual Bootstrapping’. Bilingual Bootstrapping makes use of � in learning� a small number of classified data and a large number of unclassified data in the source and the target languages in translation. It constructs …...

We present a stochastic parsing system consisting of a Lexical-Functional Gram- mar (LFG), a constraint-based parser and a stochastic disambiguation model. We re- port on the results of applying this sys- tem to parsing the UPenn Wall Street Journal (WSJ) treebank. The model com- bines full and partial parsing techniques …...

This paper introduces new learning al- gorithms for natural language processing based on the perceptron algorithm. We show how the algorithms can be efficiently applied to exponential sized representa- tions of parse trees, such as the “all sub- trees” (DOP) representation described by (Bod 1998), or a representation tracking all …...

The paper describes the application of k- Means, a standard clustering technique, to the task of inducing semantic classes for German verbs. Using probability distributions over verb subcategorisation frames, we obtained an intuitively plausi- ble clustering of 57 verbs into 14 classes. The automatic clustering was evaluated against independently motivated, …...

Context is used in many NLP systems as an indicator of a term’s syntactic and se- mantic function. The accuracy of the sys- tem is dependent on the quality and quan- tity of contextual information available to describe each term. However, the quan- tity variable is no longer fixed by …...

We present a constancy rate princi- ple governing language generation. We show that this principle implies that lo- cal measures of entropy (ignoring con- text) should increase with the sentence number. We demonstrate that this is indeed the case by measuring entropy in three different ways. We also show that …...

In many types of technical texts, meaning is embedded in noun compounds. A language un- derstanding program needs to be able to inter- pret these in order to ascertain sentence mean- ing. We explore the possibility of using an ex- isting lexical hierarchy for the purpose of plac- ing words …...

We study the impact of richer syntac- tic dependencies on the performance of the structured language model (SLM) along three dimensions: parsing accu- racy (LP/LR), perplexity (PPL) and word- error-rate (WER, N-best re-scoring). We show that our models achieve an im- provement in LP/LR, PPL and/or WER over the reported …...

The n-gram model is a stochastic model, which predicts the next word (predicted word) given the previous words (conditional words) in a word sequence. The cluster n-gram model is a variant of the n-gram model in which similar words are classified in the same cluster. It has been demonstrated that …...

Reducing language model (LM) size is a critical issue when applying a LM to realistic applications which have memory constraints. In this paper, three measures are studied for the purpose of LM pruning. They are probability, rank, and entropy. We evaluated the performance of the three pruning criteria in a …...

Text normalization is an important aspect of successful information retrieval from medical documents such as clinical notes, radiology reports and discharge summaries. In the medical domain, a significant part of the general problem of text normalization is abbreviation and acronym disambiguation. Numerous abbreviations are used routinely throughout such texts and …...

This paper presents a method for incor- porating word pronunciation information in a noisy channel model for spelling cor- rection. The proposed method builds an explicit error model for word pronuncia- tions. By modeling pronunciation simi- larities between words we achieve a sub- stantial performance improvement over the previous best …...

This paper describes a simple pattern- matching algorithm for recovering empty nodes and identifying their co-indexed an- tecedents in phrase structure trees that do not contain this information. The pat- terns are minimal connected tree frag- ments containing an empty node and all other nodes co-indexed with it. This pa- …...

We present a generative distributional model for the unsupervised induction of natural language syntax which explicitly models constituent yields and con- texts. Parameter search with EM produces higher quality analyses than previously exhibited by un- supervised systems, giving the best published un- supervised parsing results on the ATIS corpus. Ex- …...

It is necessary to have a (large) annotated cor- pus to build a statistical parser. Acquisition of such a corpus is costly and time-consuming. This paper presents a method to reduce this demand using active learning, which selects what samples to annotate, instead of annotating blindly the whole training corpus. …...