Learn More
We introduce a model for constructing vector representations of words by composing characters using bidirectional LSTMs. Relative to traditional word representation models that have independent vectors for each word type, our model requires only a single vector per character type and a fixed set of parameters for the compositional model. Despite the(More)
The blood system is maintained by a small pool of haematopoietic stem cells (HSCs), which are required and sufficient for replenishing all human blood cell lineages at millions of cells per second throughout life. Megakaryocytes in the bone marrow are responsible for the continuous production of platelets in the blood, crucial for preventing bleeding--a(More)
The stepwise commitment from hematopoietic stem cells in the bone marrow to T lymphocyte-restricted progenitors in the thymus represents a paradigm for understanding the requirement for distinct extrinsic cues during different stages of lineage restriction from multipotent to lineage-restricted progenitors. However, the commitment stage at which progenitors(More)
Phrase-based systems deeply depend on the quality of their phrase tables and therefore, the process of phrase extraction is always a fundamental step. In this paper we present a general and extensible phrase extraction algorithm, where we have highlighted several control points. The instanti-ation of these control points allows the simulation of previous(More)
Analysing the translation errors is a task that can help us finding and describing translation problems in greater detail, but can also suggest where the automatic engines should be improved. Having these aims in mind we have created a corpus composed of 150 sentences, 50 from the TAP magazine, 50 from a TED talk and the other 50 from the from the TREC(More)
NLP systems that deal with large collections of text require significant computational resources, both in terms of space and processing time. Moreover, these systems typically add new layers of linguistic information with references to another layer. The spreading of these layered annotations across different files makes them more difficult to process and(More)
Thymic T cell development is initiated from bone-marrow-derived multi potent thymus-seeding progenitors. During the early stages of thymocyte differentiation, progenitors become T cell restricted. However, the cellular environments supporting these critical initial stages of T cell development within the thymic cortex are not known. Here we use the(More)
In most statistical machine translation systems , the phrase/rule extraction algorithm uses alignments in the 1-best form, which might contain spurious alignment points. The usage of weighted alignment matrices that encode all possible alignments has been shown to generate better phrase tables for phrase-based systems. We propose two algorithms to generate(More)
A detailed error analysis is a fundamental step in every natural language processing task, as to be able to diagnose what went wrong will provide cues to decide which research directions are to be followed. In this paper we focus on error analysis in Machine Translation (MT). We significantly extend previous error taxonomies so that translation errors(More)