Standard approaches to Chinese word segmentation treat the problem as a tagging task, assigning labels to the characters in the sequence indicating whether the character marks a word boundary. Discriminatively trained models based on local character features are used to make the tagging decisions, with Viterbi decoding finding the highest scoring segmentation. In this paper we propose an alternative, word-based segmentor, which uses features based on complete words and word sequences. The generalized perceptron algorithm is used for discriminative training, and we use a beamsearch decoder. Closed tests on the first and second SIGHAN bakeoffs show that our system is competitive with the best in the literature, achieving the highest reported F-scores for a number of corpora. 1

Recently, there has been substantial interest in using large amounts of unlabeled data to learn word representations which can then be used as features in supervised classifiers for NLP tasks. However, most current approaches are slow to train, do not model the context of the word, and lack theoretical grounding. In this paper, we present a new learning method, Low Rank Multi-View Learning (LR-MVL) which uses a fast spectral method to estimate low dimensional context-specific word representations from unlabeled data. These representation features can then be used with any supervised learner. LR-MVL is extremely fast, gives guaranteed convergence to a global optimum, is theoretically elegant, and achieves state-ofthe-art performance on named entity recognition (NER) and chunking problems. 1 Introduction and Related Work Over the past decade there has been increased interest in using unlabeled data to supplement the labeled data in semi-supervised learning settings to overcome the inherent data sparsity and get improved generalization accuracies in high dimensional domains like NLP. Approaches like [1, 2]

Abstract not found

We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This versatility is achieved by trying to avoid task-specific engineering and therefore disregarding a lot of prior knowledge. Instead of exploiting man-made input features carefully optimized for each task, our system learns internal representations on the basis of vast amounts of mostly unlabeled training data. This work is then used as a basis for building a freely available tagging system with good performance and minimal computational requirements.

This paper proposes a fast and simple unsupervised word segmentation algorithm that utilizes the local predictability of adjacent character sequences, while searching for a leasteffort representation of the data. The model uses branching entropy as a means of constraining the hypothesis space, in order to efficiently obtain a solution that minimizes the length of a two-part MDL code. An evaluation with corpora in Japanese, Thai, English, and the ”CHILDES ” corpus for research in language development reveals that the algorithm achieves an accuracy, comparable to that of the state-of-the-art methods in unsupervised word segmentation, in a significantly reduced computational time. 1

Abstract. This paper examines how one can obtain state of the art Chinese word segmentation using global linear models. We provide experimental comparisons that give a detailed road-map for obtaining state of the art accuracy on various datasets. In particular, we compare the use of reranking with full beam search; we compare various methods for learning weights for features that are full sentence features, such as language model features; and, we compare an Averaged Perceptron global linear model with the Exponentiated Gradient max-margin algorithm. 1

recognition

Analyzing the logical structure of a sentence is important for understanding natural language. In this paper, we present a task of Recognition of Requisite Part and Effectuation Part in Law Sentences, or RRE task for short, which is studied in research on Legal Engineering. The goal of this task is to recognize the structure of a law sentence. We empirically investigate how the RRE task is conducted with respect to various supervised machine learning models. We also compared the impact of unlabeled data to RRE tasks. Experimental results for Japanese legal text domains showed that sequence learning models are suitable for RRE tasks and unlabled data also significantly contribute to the performance of RRE tasks. 1

Word classes automatically induced from distributional evidence have proved useful many NLP tasks including Named Entity Recognition, parsing and sentence retrieval. The Brown hard clustering algorithm is commonly used in this scenario. Here we propose to use Latent Dirichlet Allocation in order to induce soft, probabilistic word classes. We compare our approach against Brown in terms of efficiency. We also compare the usefulness of the induced Brown and LDA word classes for the semi-supervised learning of three NLP tasks: fine-grained Named Entity Recognition, Morphological Analysis and semantic Relation Classification. We show that using LDA for word class induction scales better with the number of classes than the Brown algorithm and the resulting classes outperform Brown on the three tasks. 1

The paper presents a feature-rich approach to the automatic recognition and categorization of named entities (persons, organizations, locations, and miscellaneous) in news text for Bulgarian. We combine well-established features used for other languages with language-specific lexical, syntactic and morphological information. In particular, we make use of the rich tagset annotation of the BulTreeBank (680 morpho-syntactic tags), from which we derive suitable task-specific tagsets (local and nonlocal). We further add domain-specific gazetteers and additional unlabeled data, achieving F1=89.4%, which is comparable to the state-of-the-art results for English.