Articles

When we write a report or an explanation on a newly-developed technology for readers including laypersons, it is very important to compose a title that can stimulate their in- terest in the technology. However, it is dif- ficult for inexperienced authors to come up with an appealing title. In this …...

Natural Language Interfaces to Databases (NLIs) can benefit from the advances in statis- tical parsing over the last fifteen years or so. However, statistical parsers require training on a massive, labeled corpus, and manually cre- ating such a corpus for each database is pro- hibitively expensive. To address this quandary, …...

We present a set of discourse structure relations that are easy to code, and develop criteria for an appropriate data structure for representing these relations. Discourse structure here refers to informational relations that hold between sentences in a discourse (cf. Hobbs, 1985). We evaluated whether trees are a descriptively adequate …...

In order to boost the translation quality of corpus-based MT systems for speech transla- tion, the technique of splitting an input sen- tence appears promising. In previous re- search, many methods used N-gram clues to split sentences. In this paper, to supplement N-gram based splitting methods, we introduce another clue …...

In this paper we report on the results of an experiment in designing resource-light metrics that predict the potential translation complexity of a text or a corpus of homogenous texts for state-of- the-art MT systems. We show that the best prediction of translation complexity is given by the average number …...

Regular languages are widely used in NLP to- day in spite of their shortcomings. Efficient algorithms that can reliably learn these lan- guages, and which must in realistic applications only use positive samples, are necessary. These languages are not learnable under traditional distribution free criteria. We claim that an ap- …...

We consider the problem of computing the Kullback-Leibler distance, also called the relative entropy, between a probabilistic context-free grammar and a probabilistic fi- nite automaton. We show that there is a closed-form (analytical) solution for one part of the Kullback-Leibler distance, viz. the cross-entropy. We discuss several ap- plications of …...

News articles report on facts, events, and opin- ions with the intent of conveying the truth. However, the facts, events, and opinions appear- ing in the text are often known only second- or third-hand, and as any child who has played “telephone” knows, this relaying of facts often garbles the …...

This paper presents a deterministic dependency parser based on memory-based learning, which parses English text in linear time. When trained and evaluated on the Wall Street Journal sec- tion of the Penn Treebank, the parser achieves a maximum attachment score of 87.1%. Unlike most previous systems, the parser produces la- …...

In this paper I outline Type-inheritance Combi- natory Categorial Grammar (TCCG), an imple- mented feature structure based CCG fragment of English. TCCG combines the fully lexical nature of CCG with the type-inheritance hierar- chies and complex feature structures of Head- driven Phrase Structure Grammars (HPSG). The result is a CCG/HPSG …...

Ngram models are simple in language modeling and have been successfully used in speech recognition and other tasks. However, they can only capture the short distance context dependency within an n-words window where currently the largest practical n for a natural language is three while much of the context dependency …...

This paper presents example-based machine translation (MT) based on syntactic trans- fer, which selects the best translation by us- ing models of statistical machine translation. Example-based MT sometimes generates in- valid translations because it selects similar ex- amples to the input sentence based only on source language similarity. The method …...

In this paper, subclasses of monadic context- free tree grammars (CFTGs) are compared. Since linear, nondeleting, monadic CFTGs gen- erate the same class of string languages as tree adjoining grammars (TAGs), it is examined whether the restrictions of linearity and non- deletion on monadic CFTGs are necessary to generate the …...

We propose a novel method to predict the inter- paragraph discourse structure of text, i.e. to infer which paragraphs are related to each other and form larger segments on a higher level. Our method com- bines a clustering algorithm with a model of seg- ment “relatedness” acquired in a machine …...

The main problems of statistical word alignment lie in the facts that source words can only be aligned to one target word, and that the inappro- priate target word is selected because of data sparseness problem. This paper proposes an ap- proach to improve statistical word alignment with a rule-based …...

This paper proposes a discriminative HMM (DHMM) with long state dependence (LSD- DHMM) to segment and label sequential data. The LSD-DHMM overcomes the strong context independent assumption in traditional generative HMMs (GHMMs) and models the sequential data in a discriminative way, by assuming a novel mutual information independence. As a …...

We present a novel algorithm for Japanese dependency analysis. The algorithm allows us to analyze dependency structures of a sentence in linear-time while keeping a state-of-the-art accuracy. In this paper, we show a formal description of the algorithm and discuss it theoretically with respect to time complexity. In addition, we …...

This paper addresses the documentation of large-scale grammars.1 We argue that grammar implementation differs from ordinary software programs: the concept of modules, as known from software engineering, cannot be trans- ferred directly to grammar implementations, due to grammar-specific properties. These properties also put special constraints on the form of grammar …...

Word-aligned bilingual corpora are an important knowledge source for many tasks in natural language processing. We improve the well-known IBM alignment models, as well as the Hidden-Markov alignment model using a symmetric lex- icon model. This symmetrization takes not only the standard translation direc- tion from source to target into …...

. In this paper, a Mandarin speech based emotion classification method is presented. Five primary human emotions including anger, boredom, happiness, neutral and sadness are investigated. For speech emotion recognition, we select 16 LPC coefficients, 12 LPCC components, 16 LFPC components, 16 PLP coefficients, 20 MFCC components and jitter as …...