Articles

Lasso is a regularization method for pa- rameter estimation in linear models. It op- timizes the model parameters with respect to a loss function subject to model com- plexities. This paper explores the use of lasso for statistical language modeling for text input. Owing to the very large number of …...

This paper proposes a framework for train- ing Conditional Random Fields (CRFs) to optimize multivariate evaluation mea- sures, including non-linear measures such as F-score. Our proposed framework is derived from an error minimization ap- proach that provides a simple solution for directly optimizing any evaluation mea- sure. Specifically focusing on …...

We present a new semi-supervised training procedure for conditional random fields (CRFs) that can be used to train sequence segmentors and labelers from a combina- tion of labeled and unlabeled training data. Our approach is based on extending the minimum entropy regularization frame- work to the structured prediction case, yielding …...

We explore the use of restricted dialogue contexts in reinforcement learning (RL) of effective dialogue strategies for infor- mation seeking spoken dialogue systems (e.g. COMMUNICATOR (Walker et al., 2001)). The contexts we use are richer than previous research in this area, e.g. (Levin and Pieraccini, 1997; Scheffler and Young, 2001; …...

Data-driven techniques have been used for many computational linguistics tasks. Models derived from data are generally more robust than hand-crafted systems since they better reflect the distribution of the phenomena being modeled. With the availability of large corpora of spo- ken dialog, dialog management is now reaping the benefits of …...

This paper proposes a method for detect- ing errors in article usage and singular plu- ral usage based on the mass count distinc- tion. First, it learns decision lists from training data generated automatically to distinguish mass and count nouns. Then, in order to improve its performance, it is augmented …...

This paper describes a parser which gen- erates parse trees with empty elements in which traces and fillers are co-indexed. The parser is an unlexicalized PCFG parser which is guaranteed to return the most probable parse. The grammar is extracted from a version of the PENN treebank which was automatically …...

Speech recognition problems are a reality in current spoken dialogue systems. In order to better understand these phenom- ena, we study dependencies between speech recognition problems and several higher level dialogue factors that define our notion of student state: frustra- tion/anger, certainty and correctness. We apply Chi Square (χ2) analysis …...

We present a new method for learning to parse a bilingual sentence using Inversion Transduction Grammar trained on a parallel corpus and a monolingual treebank. The method produces a parse tree for a bilingual sentence, showing the shared syntactic structures of individual sentence and the differences of word order within …...

A grammatical method of combining two kinds of speech repair cues is presented. One cue, prosodic disjuncture, is detected by a decision tree-based ensemble clas- sifier that uses acoustic cues to identify where normal prosody seems to be inter- rupted (Lickley, 1996). The other cue, syntactic parallelism, codifies the expec- …...

This paper investigates the use of sublexi- cal units as a solution to handling the com- plex morphology with productive deriva- tional processes, in the development of a lexical functional grammar for Turkish. Such sublexical units make it possible to expose the internal structure of words with multiple derivations to …...

This work provides the essential founda- tions for modular construction of (typed) unification grammars for natural lan- guages. Much of the information in such grammars is encoded in the signature, and hence the key is facilitating a modularized development of type signatures. We intro- duce a definition of signature modules …...

This paper proposes a generic mathemati- cal formalism for the combination of various structures: strings, trees, dags, graphs and products of them. The polari- zation of the objects of the elementary structures controls the saturation of the final structure. This formalism is both elementary and powerful enough to strongly simulate …...

Shortage of manually labeled data is an obstacle to supervised relation extraction methods. In this paper we investigate a graph based semi-supervised learning al- gorithm, a label propagation (LP) algo- rithm, for relation extraction. It represents labeled and unlabeled examples and their distances as the nodes and the weights of …...

This paper proposes a novel hierarchical learn- ing strategy to deal with the data sparseness problem in relation extraction by modeling the commonality among related classes. For each class in the hierarchy either manually prede- fined or automatically clustered, a linear dis- criminative function is determined in a top- down …...

In this paper, we present Espresso, a weakly-supervised, general-purpose, and accurate algorithm for harvesting semantic relations. The main contribu- tions are: i) a method for exploiting ge- neric patterns by filtering incorrect instances using the Web; and ii) a prin- cipled measure of pattern and instance reliability enabling the filtering …...

Fine-grained sense distinctions are one of the major obstacles to successful Word Sense Disambiguation. In this paper, we present a method for reducing the granularity of the WordNet sense inven- tory based on the mapping to a manually crafted dictionary encoding sense hierar- chies, namely the Oxford Dictionary of English. …...

Instances of a word drawn from different domains may have different sense priors (the proportions of the different senses of a word). This in turn affects the accuracy of word sense disambiguation (WSD) sys- tems trained and applied on different do- mains. This paper presents a method to estimate the …...

In this paper we investigate Chinese- English name transliteration using compa- rable corpora, corpora where texts in the two languages deal in some of the same topics — and therefore share references to named entities — but are not transla- tions of each other. We present two dis- tinct methods …...

In this paper we present a novel approach for inducing word alignments from sen- tence aligned data. We use a Condi- tional Random Field (CRF), a discrimina- tive model, which is estimated on a small supervised training set. The CRF is condi- tioned on both the source and target texts, …...