Articles

This paper presents an algorithm for learn- ing the probabilities of optional phonolog- ical rules from corpora. The algorithm is based on using a speech recognition sys- tem to discover the surface pronunciations of words in spe.ech corpora; using an auto- matic system obviates expensive phonetic labeling by hand. We …...

• This paper introduces a spelling correction system which integrates seamlessly with morphological analysis using a multi-tape formalism. Handling of various Semitic er- ror problems is illustrated, with reference to Arabic and Syriac examples. The model handles errors vocalisation, diacritics, pho- netic syncopation and morphographemic idiosyncrasies, in addition to Damerau …...

The relevance of context in disambiguat- ing natural language input has been widely acknowledged in the literature. However, most attempts at formalising the intuitive notion of context tend to treat the word and its context symmetrically. We demonstrate here that traditional measures such as mu- tual information score are likely …...

: Based on the long-standing experience with the project Logic-Programm- ing based Machine Translation (LMT), IBM and the publisher von Rheinbaben & Busch have developed Personal Translator®, a machine translation system which is geared toward the needs of home and business users. From the point of view of technology, the …...

A three layer back propagation neural net is set up to study the functional dependency between the semantic class of a bisyllabic Chinese word and that of its two constituent Chinese characters. Simulations were performed using a three-layer back-propagation neural net with various combination of inputs. The inputs are (1) …...

Comprehension is determined by the content of memory. The verbalized concepts reflect the information that is in the focus of attention. Mental models of text must be formed in order to achieve coherence in language understanding. Constructing a mental model requires continual interaction between the text and the reader's linguistic, …...

We analyze number agreement in English in the version of Situa- tion Semantics I put forth in [1]. We propose two theoretical notions, agreement target situations and relevance of situations. We propose that structural constraints shift the former in a way governed by the latter. Our analysis shows that number …...

German is a language with a relatively free word order. During the last few years considerable efforts have been made in all syntactic frameworks to explain so-called scrambling phenomena. In the following paper, I deal with some tough cases of German word order which cannot be described by assuming flat …...

We argue that both Russellian and Heimian definites exist in nat- ural languages. Our account captures both the commonality and difference between the two. Further, we suggest that the Russel- lian/Heimian distinction extends to indefinites too. 1...

In this paper, I argue that the modality contained in declarative sentences is heterogeneous by nature, and its indiscernible treatment evoked pardoxical behaviors of individuals in modal contexts. The difficulty is avoided by classifying the modality in two kinds from a normative point of view: 1) modality in a traditinal …...

In Korean, there are many little words that can best be analyzed as clitics: The copula i- and the adjectival ha-, as well as some nominal and verbal particles. Among others, the clitic analysis of adjectival ha- leads to a unified account of light predicate constructions. I....

This paper reviews the inconsistencies surrounding the English metaphor of the Self and demonstrates that 1) similar metaphorical paradoxes concerning the Self exist in Chinese and Japanese, and 2) these paradoxes occur in English, Japanese, and Chinese because the Inner Self (our internal voice) is being compared either with the …...

We describe, analyze, and experimentally evaluate a new probabilistic model for word- sequence prediction in natural languages, based on prediction suffi~v trees (PSTs). By using efficient data structures, we extend the notion of PST to unbounded vocabularies. We also show how to use a Bayesian approach based on recursive priors …...

Word groupings useful for language processing tasks are increasingly available, as thesauri appear on-line, and as distributional word clustering techniques improve. However, for many tasks, one is interested in relationships among word senses, not words. This paper presents a method for automatic sense disambiguafion of nouns appearing within sets of …...

We describe two new strategies to automatic bracketing of parallel corpora, with particular appli- cation to languages where prior grammar resources are scarce: (1) coarse bilingual grammars, and (2) unsupervised training of such grammars via EM (expectation-maximization). Both methods build upon a formalism we recently introduced called stochastic inversion transduction …...

Recent work has considered corpus-based or statistical approaches to the problem of prepositional phrase attachment ambiguity. Typically, ambiguous verb phrases of the form v rip1 p rip2 are resolved through a model which considers values of the four head words (v, nl, p and 77,2). This paper shows that the …...

Eric Brill introduced transformation-based learning and showed that it can do part-of- speech tagging with fairly high accuracy. The same method can be applied at a higher level of textual interpretation for locating chunks in the tagged text, including non-recursive "baseNP" chunks. For this purpose, it is convenient to view …...

In this paper we describe an unsupervised learning algorithm for automatically training a rule-based part of speech tagger without using a manually tagged corpus. We compare this algorithm to the Baum-Welch algorithm, used for unsupervised training of stochastic taggers. Next, we show a method for combining unsupervised and supervised rule-based …...

Two classes of methods have been shown to be useful for resolving lexical ambiguity. The first relies on tile presence of particular words within some distance of tile ambiguous target word; the second uses the pattern of words and part-of-speech tags around the target word. These methods have complementary coverage: …...

Since polysemy has multiple but related senses, finding any coherent system would seem impossible. But its senses are not random. When we look at inferences among them, it becomes clear that there must be a systematic structure of some kind. Based on the prototype theory, which views lexical items as …...