Related papers: Treating `Free Word Order' in Machine Translation
This paper have two parts. In the first part we discuss word embeddings. We discuss the need for them, some of the methods to create them, and some of their interesting properties. We also compare them to image embeddings and see how word…
In relatively free word order languages, grammatical functions are intricately related to case marking. Assuming an ordered representation of the predicate-argument structure, this work proposes a Combinatory Categorial Grammar formulation…
Reordering is a challenge to machine translation (MT) systems. In MT, the widely used approach is to apply word based language model (LM) which considers the constituent units of a sentence as words. In speech recognition (SR), some phrase…
We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic…
Classic grammars and regular expressions can be used for a variety of purposes, including parsing, intent detection, and matching. However, the comparisons are performed at a structural level, with constituent elements (words or characters)…
Sentiment-aware intelligent systems are essential to a wide array of applications. These systems are driven by language models which broadly fall into two paradigms: Lexicon-based and contextual. Although recent contextual models are…
Disambiguation of word senses in context is easy for humans, but is a major challenge for automatic approaches. Sophisticated supervised and knowledge-based models were developed to solve this task. However, (i) the inherent Zipfian…
This work presents a new and simple approach for fine-tuning pretrained word embeddings for text classification tasks. In this approach, the class in which a term appears, acts as an additional contextual variable during the fine tuning…
Most natural languages have a predominant or fixed word order. For example in English the word order is usually Subject-Verb-Object. This work attempts to explain this phenomenon as well as other typological findings regarding word order…
This paper presents a joint model for performing unsupervised morphological analysis on words, and learning a character-level composition function from morphemes to word embeddings. Our model splits individual words into segments, and…
Turkish has considerably freer word order than English. The interpretations of different word orders in Turkish rely on information that describes how a sentence relates to its discourse context. To capture the syntactic features of a free…
In this paper we introduce a word embedding composition method based on the intuitive idea that a fair embedding representation for a given set of words should satisfy that the new vector will be at the same distance of the vector…
In this paper, we describe an approach to sentence categorization which has the originality to be based on natural properties of languages with no training set dependency. The implementation is fast, small, robust and textual errors…
As a step toward better document-level understanding, we explore classification of a sequence of sentences into their corresponding categories, a task that requires understanding sentences in context of the document. Recent successful…
In natural language the intended meaning of a word or phrase is often implicit and depends on the context. In this work, we propose a simple yet effective method for sentiment analysis using contextual embeddings and a self-attention…
Cue phrases may be used in a discourse sense to explicitly signal discourse structure, but also in a sentential sense to convey semantic rather than structural information. Correctly classifying cue phrases as discourse or sentential is…
Cue phrases may be used in a discourse sense to explicitly signal discourse structure, but also in a sentential sense to convey semantic rather than structural information. Correctly classifying cue phrases as discourse or sentential is…
Learning word embeddings using distributional information is a task that has been studied by many researchers, and a lot of studies are reported in the literature. On the contrary, less studies were done for the case of multiple languages.…
Learning sentence vectors that generalise well is a challenging task. In this paper we compare three methods of learning phrase embeddings: 1) Using LSTMs, 2) using recursive nets, 3) A variant of the method 2 using the POS information of…
A machine translation system is said to be *complete* if all expressions that are correct according to the source-language grammar can be translated into the target language. This paper addresses the completeness issue for compositional…