We describe a multi-step process for automatically learning reliable sub-sentential syntactic phrases that are translation equivalents of each other and syntactic translation rules between two languages. The input to the process is a corpus of parallel sentences, word-aligned and annotated with phrase-structure parse trees. We first apply a newly developed algorithm for aligning parse-tree node...

The recent decades have witnessed an unprecedented expansion in the volume of unstructured data in digital textual formats. Companies are now starting to recognize the potential economic value lying untapped in their text data repositories and sources, including external ones, such as social media platforms, and internal ones, such as safety reports and other company-specific document collectio...

PIDE is a general framework for document-oriented prover interaction and integration, based on a bilingual architecture that combines ML and Scala [2]. The overall aim is to connect LCF-style provers like Isabelle [5, §6] (or Coq [5, §4] or HOL [5, §1]) with sophisticated front-end technology on the JVM platform, overcoming command-line interaction at last. The present system description specif...

We present a method that consumes a large corpus of multilingual text and produces a single, unified word embedding in which the word vectors generalize across languages. In contrast to current approaches that require language identification, our method is agnostic about the languages with which the documents in the corpus are expressed, and does not rely on parallel corpora to constrain the sp...

For the improvement of large-scale electronic publications, such as encyclopaedic reference works,we propose an object-oriented document model that in addition to the SGML-structured text corpus represents other access structures, in particular a fine-grained, highly structured, tightly interconnected network of domain-specific objects and facts. The paper presents strategies and tools for effi...

As computing resources become accessible anytime anywhere, rules of interaction and engagement between humans are changing. For example, response-time expectations have dramatically decreased in recent years because of the assumption that recipients are constantly checking e-mail and text messages on their mobile devices. Likewise, expectations of context-awareness have become an important part...

More and more users are getting used to posting images text on social networks share their emotions or opinions. Accordingly, multimodal sentiment analysis has become a research topic of increasing interest in recent years. Typically, there exist affective regions that evoke human an image, which usually manifested by corresponding words peoples comments. Similarly, people also tend portray the...

In recent years, with the development of deep learning, text-generation technology has undergone great changes and provided many kinds services for human beings, such as restaurant reservation daily communication. The automatically generated text is becoming more fluent so researchers begin to consider anthropomorphic technology, that is, conditional generation, including emotional personalized...

Concordancers are tools that display the contexts of a given word in a corpus. Also called key word in context (KWIC), these tools are nowadays indispensable in the work of lexicographers, linguists, and translators. We present an enhanced type of concordancer that integrates syntactic information on sentence structure as well as statistical information on word cooccurrence in order to detect a...