CONLL

The connection between part-of-speech (POS) categories and morphological properties is well-documented in linguistics but underutilized in text processing systems. This paper proposes a novel model for morphological segmentation that is driven by this ...

We use an automatic pipeline of word tokenization, stemming, POS tagging, and vocalization to perform real-world Arabic dependency parsing. In spite of the high accuracy on the modules, the very few errors in tokenization, which reaches an accuracy of ...

We show how punctuation can be used to improve unsupervised dependency parsing. Our linguistic analysis confirms the strong connection between English punctuation and phrase boundaries in the Penn Treebank. However, approaches that naively include ...

While many computational models have been created to explore how children might learn to segment words, the focus has largely been on achieving higher levels of performance and exploring cues suggested by artificial learning experiments. We propose a ...

During language acquisition, children learn to segment speech into phonemes, syllables, morphemes, and words. We examine word segmentation specifically, and explore the possibility that children might have general-purpose chunking mechanisms to perform ...

One of the goals of computational linguistics is to create automated systems that can learn, generate, and understand language at all levels of structure (semantics, syntax, morphology, phonology, phonetics). This is a very demanding task whose complete ...

We develop an approach to biomedical event extraction using a search-based structured prediction framework, SEARN, which converts the task into cost-sensitive classification tasks whose models are learned jointly. We show that SEARN improves on a simple ...

Automatic extraction of opinion holders and targets (together referred to as opinion entities) is an important subtask of sentiment analysis. In this work, we attempt to accurately extract opinion entities from Urdu newswire. Due to the lack of ...

Crisis-affected populations are often able to maintain digital communications but in a sudden-onset crisis any aid organizations will have the least free resources to process such communications. Information that aid agencies can actually act on, '...

Sociolinguistic theories (e.g., Lakoff (1973)) postulate that women's language styles differ from that of men. In this paper, we explore statistical techniques that can learn to identify the gender of authors in modern English text, such as web blogs ...

Subjectivity word sense disambiguation (SWSD) is automatically determining which word instances in a corpus are being used with subjective senses, and which are being used with objective senses. SWSD has been shown to improve the performance of ...

We present a computational model of language learning via a sequence of interactions between a teacher and a learner. Experiments learning limited sublanguages of 10 natural languages show that the learner achieves a high level of performance after a ...

Feature feedback is an alternative to instance labeling when seeking supervision from human experts. Combination of instance and feature feedback has been shown to reduce the total annotation cost for supervised learning. However, learning problems may ...

In this paper we present ULISSE, an unsupervised linguistically--driven algorithm to select reliable parses from the output of a dependency parser. Different experiments were devised to show that the algorithm is robust enough to deal with the output of ...

Finding the right representation for words is critical for building accurate NLP systems when domain-specific labeled data for the task is scarce. This paper investigates language model representations, in which language models trained on unlabeled ...

Keyphrase extraction aims to select a set of terms from a document as a short summary of the document. Most methods extract keyphrases according to their statistical properties in the given document. Appropriate keyphrases, however, are not always ...

In this paper, we introduce a knowledge-based method to disambiguate biomedical acronyms using second-order co-occurrence vectors. We create these vectors using information about a long-form obtained from the Unified Medical Language System and Medline. ...

The first step in graph-based semi-supervised classification is to construct a graph from input data. While the k-nearest neighbor graphs have been the de facto standard method of graph construction, this paper advocates using the less well-known mutual ...

In this paper we present methods for automatically acquiring training examples for the task of entity extraction. Experimental evidence show that: (1) our methods compete with a current heavily supervised state-of-the-art system, within 0.04 absolute ...

This paper makes two contributions to the area of single-word based word alignment for bilingual sentence pairs. Firstly, it integrates the -- seemingly rather different -- works of (Bodrumlu et al., 2009) and the standard probabilistic ones into a ...

The problem of authorship attribution -- attributing texts to their original authors -- has been an active research area since the end of the 19th century, attracting increased interest in the last decade. Most of the work on authorship attribution ...

We describe the extension and objective evaluation of a network¹ of semantically related noun senses (or concepts) that has been automatically acquired by analyzing lexical cooccurrence in Wikipedia. The acquisition process makes no use of the metadata ...

We investigate the use of Semi-Supervised Learning (SSL) in opinion detection both in sparse data situations and for domain adaptation. We show that co-training reaches the best results in an in-domain setting with small labeled data sets, with a ...

We propose a normalized-cut model for the problem of aligning a known hierarchical browsing structure, e.g., electronic slides of lecture recordings, with the sequential transcripts of the corresponding spoken documents, with the aim to help index and ...

In recent years Bayesian techniques have made good inroads in computational linguistics, due to their protection against overfitting and expressiveness of the Bayesian modeling language. However most Bayesian models proposed so far have used pretty ...

Studying natural language, and especially how people describe the world around them can help us better understand the visual world. In turn, it can also help us in the quest to generate natural language that describes this world in a human manner. We ...

Natural language systems trained on labeled data from one domain do not perform well on other domains. Most adaptation algorithms proposed in the literature train a new model for the new domain using unlabeled data. However, it is time consuming to ...

This paper shows that the performance of history-based models can be significantly improved by performing lookahead in the state space when making each classification decision. Instead of simply using the best action output by the classifier, we ...

Traditional text similarity measures consider each term similar only to itself and do not model semantic relatedness of terms. We propose a novel discriminative training method that projects the raw term vectors into a common, low-dimensional vector ...