Search results for "Machine translation"
showing 10 items of 64 documents
Learning Molecular Classes from Small Numbers of Positive Examples Using Graph Grammars
2021
We consider the following problem: A researcher identified a small number of molecules with a certain property of interest and now wants to find further molecules sharing this property in a database. This can be described as learning molecular classes from small numbers of positive examples. In this work, we propose a method that is based on learning a graph grammar for the molecular class. We consider the type of graph grammars proposed by Althaus et al. [2], as it can be easily interpreted and allows relatively efficient queries. We identify rules that are frequently encountered in the positive examples and use these to construct a graph grammar. We then classify a molecule as being conta…
LR(k) Parsing
1990
In this chapter we shall generalize the notion of strong LL(k) parsing presented in Chapter 5 and consider a method for deterministic left parsing that applies to a slightly wider class of context-free grammars than does the strong LL(k) parsing method. This method will be called “canonical LL(k) parsing”. As in strong LL(k) parsing, the acronym “LL(k)” means that the input string is parsed (1) in a single Left-to-right scan, (2) producing a Left parse, and (3) using lookahead of length k.
Grammars++ for modelling information in text
1999
Abstract Grammars provide a convenient means to describe the set of valid instances in a text database. Flexibility in choosing a grammar can be exploited to provide information modelling capability by designing productions in the grammar to represent entities and relationships of interest to database applications. Additional constraints can be specified by attaching predicates to selected nonterminals in the grammar. When used for database definition, grammars can provide the functionality that users have come to expect of database schemas. Extended grammars can also be used to specify database manipulation, including query, update, view definition, and index specification.
Testing Grammars for Parsability
1990
In the preceding chapters we have studied in detail the major methods of deterministic context-free parsing: strong LL(k) parsing (Chapter 5), simple precedence parsing (Chapter 5), canonical LR(k) parsing, LALR(k) parsing, and SLR(k) parsing (Chapters 6 and 7), and canonical LL(k) parsing (Chapter 8). Each of these methods induces a class of grammars that are “parsable” using that method, that is, a class of grammars for which a deterministic parser employing that method can be constructed. For example, the LL(k) grammars constitute the class of grammars parsable by the LL(k) parsing method. By definition, a context-free grammar is an LL(k) grammar if and only if its canonical LL(k) parser…
A comparison of compatible, finite, and inductive graph properties
1993
Abstract In the theory of hyperedge-replacement grammars and languages, one encounters three types of graph properties that play an important role in proving decidability and structural results. The three types are called compatible, finite, and inductive graph properties. All three of them cover graph properties that are well-behaved with respect to certain operations on hypergraphs. In this paper, we show that the three notions are essentially equivalent. Consequently, three lines of investigation in the theory of hyperedge replacement - so far separated - merge into one.
Designing the Business Conversation Corpus
2020
While the progress of machine translation of written text has come far in the past several years thanks to the increasing availability of parallel corpora and corpora-based training technologies, automatic translation of spoken text and dialogues remains challenging even for modern systems. In this paper, we aim to boost the machine translation quality of conversational texts by introducing a newly constructed Japanese-English business conversation parallel corpus. A detailed analysis of the corpus is provided along with challenging examples for automatic translation. We also experiment with adding the corpus in a machine translation training scenario and show how the resulting system benef…
Towards the evaluation of automatic simultaneous speech translation from a communicative perspective
2021
In recent years, automatic speech-to-speech and speech-to-text translation has gained momentum thanks to advances in artificial intelligence, especially in the domains of speech recognition and machine translation. The quality of such applications is commonly tested with automatic metrics, such as BLEU, primarily with the goal of assessing improvements of releases or in the context of evaluation campaigns. However, little is known about how the output of such systems is perceived by end users or how they compare to human performances in similar communicative tasks. In this paper, we present the results of an experiment aimed at evaluating the quality of a real-time speech translation engine…
Fast Neural Machine Translation Implementation
2018
This paper describes the submissions to the efficiency track for GPUs at the Workshop for Neural Machine Translation and Generation by members of the University of Edinburgh, Adam Mickiewicz University, Tilde and University of Alicante. We focus on efficient implementation of the recurrent deep-learning model as implemented in Amun, the fast inference engine for neural machine translation. We improve the performance with an efficient mini-batching algorithm, and by fusing the softmax operation with the k-best extraction algorithm. Submissions using Amun were first, second and third fastest in the GPU efficiency track.
Facilitating terminology translation with target lemma annotations
2021
Most of the recent work on terminology integration in machine translation has assumed that terminology translations are given already inflected in forms that are suitable for the target language sentence. In day-to-day work of professional translators, however, it is seldom the case as translators work with bilingual glossaries where terms are given in their dictionary forms; finding the right target language form is part of the translation process. We argue that the requirement for apriori specified target language forms is unrealistic and impedes the practical applicability of previous work. In this work, we propose to train machine translation systems using a source-side data augmentatio…
Ambiguity and complementation in recognizable two-dimensional languages
2008
The theory of one-dimensional (word) languages is well founded and investigated since fifties. From several years, the increasing interest for pattern recognition and image processing motivated the research on two-dimensional or picture languages, and nowadays this is a research field of great interest. A first attempt to formalize the concept of finite state recognizability for two-dimensional languages can be attributed to Blum and Hewitt ([7]) who started in 1967 the study of finite state devices that can define two-dimensional languages, with the aim to finding a counterpart of what regular languages are in one dimension. Since then, many approaches have been presented in the literature…