Articles

We present a multi-dialect neural machine translation (NMT) model tailored to Japanese. While the surface forms of Japanese dialects differ from those of standard Japanese, most of the dialects share fundamental proper- ties such as word order, and some also use many of the same phonetic correspondence rules. To take …...

The Part-Of-Speech tag of a word can pro- vide crucial information for a large num- ber of tasks, and so, it is of utmost im- portance that the POS tagged data is ac- curate. However, manually checking the data is a tedious and time consuming task. Thus, there is a …...

For the purpose of POS tagging noisy user-generated text, should normalization be handled as a preliminary task or is it possible to handle misspelled words directly in the POS tagging model? We propose in this paper a combined approach where some errors are normalized before tagging, while a Gated Recurrent …...

This paper describes a project for constructing FrameNet annotations in Korean over the KAIST treebank corpus to scale up the Korean FrameNet resource. Annotating FrameNet over raw sentences is an expensive and complex task, because of which we have designed this project using a semi-automatic annotation approach. This paper describes …...

It is now a common practice to compare models of human language processing by comparing how well they predict behavioral and neural measures of processing difficulty, such as reading times, on corpora of rich naturalistic linguistic materials. However, many of these corpora, which are based on naturally-occurring text, do not …...

The paper introduces a multi-level annotation of the R. GVEDA, a fundamental Sanskrit text composed in the 2. millenium BCE that is important for South-Asian and Indo-European linguistics, as well as Cultural Studies. We describe the individual annotation levels, including phonetics, morphology, lexicon, and syntax, and show how these different …...

The task of selecting suitable fonts for a given text is non-trivial, as tens of thousands of fonts are available, and the choice of font has been shown to affect the perception of the text as well as of the author or of the brand being advertized. Aiming to support …...

This paper focuses on specific changes to the semantic representations associated with classes of verbs in the English lexical resource VerbNet (Schuler, 2005). The new form has been restricted to first-order representations to simplify use by and integration with planners. More significantly, the modifications incorporate the Generative Lexicon’s event structure, …...

Neural word embedding models trained on sizable corpora have proved to be a very efficient means of representing meaning. However, the abstract vectors representing words and phrases in these models are not interpretable for humans by themselves. In this paper we present the Thing Recognizer, a method that assigns explicit …...

Distinguishing lexical relations has been a long term pursuit in natural language processing (NLP) domain. Recently, in order to detect lexical relations like hypernymy, meronymy, co-hyponymy etc., distributional semantic models are being used extensively in some form or the other. Even though a lot of efforts have been made for …...

Idiom translation is a challenging problem in machine translation because the meaning of idioms is non-compositional, and a literal (word-by-word) translation is likely to be wrong. In this paper, we focus on evaluating the quality of idiom translation of MT systems. We introduce a new evaluation method based on an …...

Training models for the automatic correction of machine-translated text usually relies on data consisting of (source, MT, human post- edit) triplets providing, for each source sentence, examples of translation errors with the corresponding corrections made by a human post-editor. Ideally, a large amount of data of this kind should allow …...

There are many machine translation (MT) papers that propose novel approaches and show improvements over their self-defined baselines. The experimental setting in each paper often differs from one another. As such, it is hard to determine if a proposed approach is really useful and advances the state of the art. …...

We present an evaluation of the benefits of domain adaptation for machine translation, on three separate domains and language pairs, with varying degrees of domain specificity and amounts of available training data. Domain-adapted statistical and neural machine translation systems are compared to each other and to generic online systems, thus …...

Recent works in spoken language translation (SLT) have attempted to build end-to-end speech-to-text translation without using source language transcription during learning or decoding. However, while large quantities of parallel texts (such as Europarl, OpenSubtitles) are available for training machine translation systems, there are no large (>100h) and open source parallel …...

Many Natural Language Processing applications nowadays rely on pre-trained word representations estimated from large text corpora such as news collections, Wikipedia and Web Crawl. In this paper, we show how to train high-quality word vector representations by using a combination of known tricks that are however rarely used together. The …...

AbstractContext-free grammars (CFG) were one of the first formal tools used to model natural languages, and they remain relevant today as the basis of several frameworks. A key ingredient of CFG is the presence of nested recursion. In this paper, we investigate experimentally the capability of several recurrent neural networks …...

This study sets out to examine the linguis- tic difference between truthful and decep- tive texts. In order to take more linguistic features into consideration, this research applied multidimensional analysis, which can reduce many linguistic features into several factors. This study used a self-built corpus containing 100 truthful texts and …...

We propose a model based on context en- coder to solve formal analogies on strings like aaabbbccc : aaaabbbbcccc :: abc : x ⇒ x = aabbcc or ubid : tubid :: ofjid : x ⇒ x = tofjid. As a context encoder model, it consists of a generator and …...

One methodological issue in tonal acoustic analyses is revisited and resolved in this study. Previous tone normalization methods mainly served for categorizing tones but did not aim to preserve sociolinguistic variation. This study, from the perspective of variationist studies, re- evaluates the effectiveness of sixteen tone normalization methods and finds …...