Search results for "natural language processing"

Improved Induction Tree Training for Automatic Lexical Categorization

2009

This paper studies a tuned version of an induction tree which is used for automatic detection of lexical word category. The database used to train the tree has several fields to describe Spanish words morpho-syntactically. All the processing is performed using only the information of the word and its actual sentence. It will be shown here that this kind of induction is good enough to perform the linguistic categorization.

The complexity of graph languages generated by hyperedge replacement

1990

Although in many ways, hyperedge replacement graph grammars (HRGs) are, among all graph generating mechanisms, what context-free Chomsky grammars are in the realm of string rewriting, their parsing problem is known to be, in general, NP-complete. In this paper, the main difficulty in HRG parsing is analysed and some conditions on either grammar or input graphs are developed under which parsing can be done in polynomial time. For some of the cases, the parsing problem is shown to be log-space reducible to context-free string parsing.

Multi-system machine translation using online APIs for English-Latvian

2015

This paper describes a hybrid machine translation (HMT) system that employs several online MT system application program interfaces (APIs) forming a MultiSystem Machine Translation (MSMT) approach. The goal is to improve the automated translation of English – Latvian texts over each of the individual MT APIs. The selection of the best hypothesis translation is done by calculating the perplexity for each hypothesis. Experiment results show a slight improvement of BLEU score and WER (word error rate).

K-Translate - Interactive Multi-system Machine Translation

2016

The tool described in this article has been designed to help machine translation (MT) researchers to combine and evaluate various MT engine outputs through a web-based graphical user interface using syntactic analysis and language modelling. The tool supports user provided translations as well as translations from popular online MT system application program interfaces (APIs). The selection of the best translation hypothesis is done by calculating the perplexity for each hypothesis. The evaluation panel provides sentence tree graphs and chunk statistics. The result is a syntax-based multi-system translation tool that shows an improvement of BLEU scores compared to the best individual baseli…

Truth and Ontology

2010

The grammaticalization and pragmaticalization of cleft constructions in Present-Day English

2012

The present paper examines the development of the variation between a marked and an unmarked infinitival complement clause in three types of cleft constructions in 20th century English. Data from corpora of written and spoken British (BrE) and American English (AmE) evidence a significantly divergent development of these clefts types in speaking when compared to writing. The written corpora show a steady increase in the frequency of clefts, and a decrease of the to-infinitive paired with an increase of the bare infinitive, thus a reversal of preferences in both varieties in all three types of clefts. This erosion of to as an (optional) grammatical marker leads to a higher degree of syntacti…

A framework for sign language sentence recognition by common sense context

2007

This correspondence proposes a complete framework for sign language recognition that integrates a commonsense engine in order to deal with sentence recognition. The proposed system is based on a multilevel architecture that allows modeling and managing of the knowledge of the recognition process in a simple and robust way. The final abstraction level of this architecture introduces the semantic context and the analysis of the correctness of a sentence given in a sequence of recognized signs. Experimentations are presented using a set of signs from the Italian sign language (LIS) for domotic applications. The implemented system maintains a high recognition rate when the set of signs grows, c…

Eye movements when reading sentences with handwritten words.

2016

The examination of how we read handwritten words (i.e., the original form of writing) has typically been disregarded in the literature on reading. Previous research using word recognition tasks has shown that lexical effects (e.g., the word-frequency effect) are magnified when reading difficult handwritten words. To examine this issue in a more ecological scenario, we registered the participants’ eye movements when reading handwritten sentences that varied in the degree of legibility (i.e., sentences composed of words in easy vs. difficult handwritten style). For comparison purposes, we included a condition with printed sentences. Results showed a larger reading cost for sentences with dif…

Overview of the Evalita 2014 SENTIment POLarity Classification Task

2014

International audience; English. The SENTIment POLarity Classification Task (SENTIPOLC), a new shared task in the Evalita evaluation campaign , focused on sentiment classification at the message level on Italian tweets. It included three subtasks: subjectivity classification, polarity classification, and irony detection. SENTIPOLC was the most participated Evalita task with a total of 35 submitted runs from 11 different teams. We present the datasets and the evaluation methodology, and discuss results and participating systems. Italiano. Descriviamo modalit a e risultati della campagna di valutazione di sistemi di sentiment analysis (SENTIment POLarity Classification Task), proposta per la …

Spoken conversational context improves query auto-completion in web search

2021

Web searches often originate from conversations in which people engage before they perform a search. Therefore, conversations can be a valuable source of context with which to support the search process. We investigate whether spoken input from conversations can be used as a context to improve query auto-completion. We model the temporal dynamics of the spoken conversational context preceding queries and use these models to re-rank the query auto-completion suggestions. Data were collected from a controlled experiment and comprised conversations among 12 participant pairs conversing about movies or traveling. Search query logs during the conversations were recorded and temporally associated…