Articles

We explore a hybrid approach for Chinese definitional question answering by com- bining deep linguistic analysis with sur- face pattern learning. We answer four questions in this study: 1) How helpful are linguistic analysis and pattern learning? 2) What kind of questions can be answered by pattern matching? 3) How …...

Text generation requires a planning mod- ule to select an object of discourse and its properties. This is specially hard in de- scriptive games, where a computer agent tries to describe some aspects of a game world. We propose to formalize this prob- lem as a Markov Decision Process, in …...

Weighted deduction with aggregation is a powerful theoretical formalism that encompasses many NLP algorithms. This pa- per proposes a declarative specification language, Dyna; gives general agenda-based algorithms for computing weights and gradients; briefly discusses Dyna-to-Dyna program transforma- tions; and shows that a first implementation of a Dyna-to-C++ compiler produces code …...

This paper presents comparative experimen- tal results on four techniques of language model adaptation, including a maximum a posteriori (MAP) method and three dis- criminative training methods, the boosting algorithm, the average perceptron and the minimum sample risk method, on the task of Japanese Kana-Kanji conversion. We evalu- ate these …...

In this paper we consider the problem of analysing sentence-level discourse struc- ture. We introduce discourse chunking (i.e., the identification of intra-sentential nucleus and satellite spans) as an al- ternative to full-scale discourse parsing. Our experiments show that the proposed modelling approach yields results com- parable to state-of-the-art while exploit- …...

Machine summaries can be improved by using knowledge about the cognitive sta- tus of news article referents. In this paper, we present an approach to automatically acquiring distinctions in cognitive status using machine learning over the forms of referring expressions appearing in the in- put. We focus on modeling references …...

The paper presents a Bayesian model for text summarization, which explicitly en- codes and exploits information on how hu- man judgments are distributed over the text. Comparison is made against non Bayesian summarizers, using test data from Japanese news texts. It is found that the Bayesian approach generally lever- ages …...

We identify a set of prosodic cues for parsing con- versational speech and show how such features can be effectively incorporated into a statistical parsing model. On the Switchboard corpus of conversa- tional speech, the system achieves improved parse accuracy over a state-of-the-art system which uses only lexical and syntactic …...

We describe the error handling architect- ture underlying the RavenClaw dialog management framework. The architecture provides a robust basis for current and fu- ture research in error detection and recov- ery. Several objectives were pursued in its development: task-independence, ease-of- use, adaptability and scalability. We de- scribe the key aspects …...

To improve the robustness in multimodal input interpretation, this paper presents a new salience driven approach. This approach is based on the observation that, during multimodal conversation, information from deictic gestures (e.g., point or circle) on a graphical display can signal a part of the physical world (i.e., representation of …...

This paper proposes a new discriminative training method, called minimum sample risk (MSR), of estimating parameters of language models for text input. While most existing discriminative training methods use a loss function that can be optimized easily but approaches only approximately to the objec- tive of minimum error rate, MSR …...

During the last years there has been grow- ing interest in using neural networks for language modeling. In contrast to the well known back-off n-gram language models, the neural network approach attempts to overcome the data sparseness problem by performing the estimation in a continuous space. This type of language …...

Most statistical translation systems are based on phrase translation pairs, or “blocks”, which are obtained mainly from word alignment. We use blocks to infer better word alignment and improved word alignment which, in turn, leads to better inference of blocks. We propose two new probabilistic models based on the inner- …...

HMM-based models are developed for the alignment of words and phrases in bitext. The models are formulated so that align- ment and parameter estimation can be per- formed efficiently. We find that Chinese- English word alignment performance is comparable to that of IBM Model-4 even over large training bitexts. Phrase …...

We describe stochastic models of local phrase movement that can be incorpo- rated into a Statistical Machine Transla- tion (SMT) system. These models pro- vide properly formulated, non-deficient, probability distributions over reordered phrase sequences. They are imple- mented by Weighted Finite State Trans- ducers. We describe EM-style parameter re-estimation procedures …...

We approached the problem as learning how to order documents by estimated relevance with respect to a user query. Our support vector machines based classifier learns from the relevance judgments available with the standard test collections and generalizes to new, previously unseen queries. For this, we have designed a representation …...

In order to promote the study of auto- matic summarization and translation, we need an accurate automatic evaluation method that is close to human evalua- tion. In this paper, we present an eval- uation method that is based on convolu- tion kernels that measure the similarities between texts considering their …...

We present a method for speeding up the calculation of tree kernels during train- ing. The calculation of tree kernels is still heavy even with efficient dynamic pro- gramming (DP) procedures. Our method maps trees into a small feature space where the inner product, which can be cal- culated much …...

We propose a generalized bootstrapping algorithm in which categories are de- scribed by relevant seed features. Our method introduces two unsupervised steps that improve the initial categorization step of the bootstrapping scheme: (i) using La- tent Semantic space to obtain a general- ized similarity measure between instances and features, and …...

New Event Detection (NED) involves monitoring chronologically-ordered news streams to automatically detect the stories that report on new events. We compare two stories by finding three cosine simi- larities based on names, topics and the full text. These additional comparisons sug- gest treating the NED problem as a bi- nary …...