Related papers: Transliteration in Any Language with Surrogate Lan…
One of the challenges in a task oriented natural language application like the Google Assistant, Siri, or Alexa is to localize the output to many languages. This paper explores doing this by applying machine translation to the English…
The article is focused on automatic development and ranking of a large corpus for Russian paraphrase generation which proves to be the first corpus of such type in Russian computational linguistics. Existing manually annotated paraphrase…
Scientific publications have evolved several features for mitigating vocabulary mismatch when indexing, retrieving, and computing similarity between articles. These mitigation strategies range from simply focusing on high-value article…
One approach for multilingual data-to-text generation is to translate grammatical configurations upfront from the source language into each target language. These configurations are then used by a surface realizer and in document planning…
Social tagging has become an interesting approach to improve search and navigation over the actual Web, since it aggregates the tags added by different users to the same resource in a collaborative way. This way, it results in a list of…
We consider language modelling (LM) as a multi-label structured prediction task by re-framing training from solely predicting a single ground-truth word to ranking a set of words which could continue a given context. To avoid annotating…
Among the manifold takes on world literature, it is our goal to contribute to the discussion from a digital point of view by analyzing the representation of world literature in Wikipedia with its millions of articles in hundreds of…
On Wikipedia, articles are categorized to aid readers in navigating content efficiently. The manual creation of new categories can be laborious and time-intensive. To tackle this issue, we built language models to translate Wikipedia…
Machine translation systems for high resource languages perform exceptionally well and produce high quality translations. Unfortunately, the vast majority of languages are not considered high resource and lack the quantity of parallel…
Developing successful sign language recognition, generation, and translation systems requires expertise in a wide range of fields, including computer vision, computer graphics, natural language processing, human-computer interaction,…
Keyphrase is an efficient representation of the main idea of documents. While background knowledge can provide valuable information about documents, they are rarely incorporated in keyphrase extraction methods. In this paper, we propose…
In this paper, we describe a system to rank suspected answers to natural language questions. We process both corpus and query using a new technique, predictive annotation, which augments phrases in texts with labels anticipating their being…
Wikipedia is widely used for finding general information about a wide variety of topics. Its vocation is not to provide local information. For example, it provides plot, cast, and production information about a given movie, but not showing…
Text segmentation, the task of dividing a document into contiguous segments based on its semantic structure, is a longstanding challenge in language understanding. Previous work on text segmentation focused on unsupervised methods such as…
As NLP tools become ubiquitous in today's technological landscape, they are increasingly applied to languages with a variety of typological structures. However, NLP research does not focus primarily on typological differences in its…
News articles, image captions, product reviews and many other texts mention people and organizations whose name recognition could vary for different audiences. In such cases, background information about the named entities could be provided…
Cross-modal language generation tasks such as image captioning are directly hurt in their ability to support non-English languages by the trend of data-hungry models combined with the lack of non-English annotations. We investigate…
Natural language is generated by people, yet traditional language modeling views words or documents as if generated independently. Here, we propose human language modeling (HuLM), a hierarchical extension to the language modeling problem…
Hyperlinks constitute the backbone of the Web; they enable user navigation, information discovery, content ranking, and many other crucial services on the Internet. In particular, hyperlinks found within Wikipedia allow the readers to…
This work introduces a machine translation task where the output is aimed at audiences of different levels of target language proficiency. We collect a high quality dataset of news articles available in English and Spanish, written for…