Conditional random fields for sequence labeling offer advantages over both generative models like HMMs and classifiers applied at each sequence position. Among sequence labeling tasks in language processing, shallow parsing has received much attention, with the development of standard evaluation datasets and extensive comparison among methods. We show here how to train a conditional random field to achieve performance as good as any reported base noun-phrase chunking method on the CoNLL task, and better than any reported single model. Improved training methods based on modern optimization algorithms were critical in achieving these results. We present extensive comparisons between models and training methods that confirm and strengthen previous results on shallow parsing and training methods for maximum-entropy models.

Abstract — In this paper, we propose an automatic video retrieval method based on high-level concept detectors. Research in video analysis has reached the point where over 100 concept detectors can be learned in a generic fashion, albeit with mixed performance. Such a set of detectors is very small still compared to ontologies aiming to capture the full vocabulary a user has. We aim to throw a bridge between the two fields by building a multimedia thesaurus, i.e. a set of machine learned concept detectors that is enriched with semantic descriptions and semantic structure obtained from WordNet. Given a multimodal user query, we identify three strategies to select a relevant detector from this thesaurus, namely: text matching, ontology querying, and semantic visual querying. We evaluate the methods against the automatic search task of the TRECVID 2005 video retrieval benchmark, using a news video archive of 85 hours in combination with a thesaurus of 363 machine learned concept detectors. We assess the influence of thesaurus size on video search performance, evaluate and compare the multimodal selection strategies for concept detectors, and finally discuss their combined potential using oracle fusion. The set of queries in the TRECVID 2005 corpus is too small to be definite in our conclusions, but the results suggest promising new lines of research. Index Terms — Video retrieval, concept learning, knowledge modeling, content analysis and indexing, multimedia information systems I.

We present results from a variety of learned information extraction systems for identifying human protein names in Medline abstracts and subsequently extracting interactions between the proteins. We demonstrate that machine learning approaches using support vector machines and hidden Markov models are able to identify human proteins with higher accuracy than several previous approaches. We also demonstrate that various rule induction methods are able to identify protein interactions with higher precision than manually-developed rules.

This article introduces the problem of partial or shallow parsing (assigning partial syntactic structure to sentences) and explains why it is an important natural language processing (NLP) task. The complexity of the task makes Machine Learning an attractive option in comparison to the handcrafting of rules. On the other hand, because of the same task complexity, shallow parsing makes an excellent benchmark problem for evaluating machine learning algorithms. We sketch the origins of shallow parsing as a specific task for machine learning of language, and introduce the articles accepted for this special issue, a representative sample of current research in this area. Finally, future directions for machine learning of shallow parsing are suggested.

Abstract. Several phrase chunkers have been proposed over the past few years. Some state-of-the-art chunkers achieved better performance via integrating external resources, e.g., parsers and additional training data, or combining multiple learners. However, in many languages and domains, such external materials are not easily available and the combination of multiple learners will increase the cost of training and testing. In this paper, we propose a mask method to improve the chunking accuracy. The experimental results show that our chunker achieves better performance in comparison with other deep parsers and chunkers. For CoNLL-2000 data set, our system achieves 94.12 in F rate. For the base-chunking task, our system reaches 92.95 in F rate. When porting to Chinese, the performance of the base-chunking task is 92.36 in F rate. Also, our chunker is quite efficient. The complete chunking time of a 50K words document is about 50 seconds. 1

We describe ongoing work on sentence summarization in the European MUSA project and the Flemish ATraNoS project. Both projects aim at automatic generation of TV subtitles for hearing-impaired people. This involves speech recognition, a topic which is not covered in this paper, and summarizing sentences in such a way that they fit in the available space for subtitles. The target language is equal to the source language: Dutch in ATraNoS and English in MUSA. A separate part of MUSA deals with translating the English subtitles to French and Greek. We compare two methods for monolingual sentence length reduction: one based on learning sentence reduction from a parallel corpus and one based on hand-crafted deletion rules.

Abstract not found

This work analyzes the relative advantages of different metaheuristic approaches to the well known natural language processing problem of part-of-speech tagging. This consists of assigning to each word of a text its disambiguated part-of-speech according to the context in which the word is used. We have applied a classic genetic algorithm (GA), a CHC algorithm, and a Simulated Annealing (SA). Different ways of encoding the solutions to the problem (integer and binary) have been studied, as well as the impact of using parallelism for each of the considered methods. We have performed experiments on different linguistic corpora and compared the results obtained against other popular approaches plus a classic dynamic programming algorithm. Our results claim for the high performances achieved by the parallel algorithms compared to the sequential ones, and estate the singular advantages for every technique. Our algorithms and some of its components can be used to represent a new set of state-of-the-art procedures for complex tagging scenarios. Key words: Genetic algorithms, CHC algorithm, natural language processing, part-of-speech tagging, parallelism.

Functional chunks are defined as a series of non-overlapping, non-nested segments of text in a sentence, representing the implicit grammatical relations between the sentence-level predicates and their arguments. Its top-down scheme and complexity of internal constitutions bring in a new challenge for automatic parser. In this paper, a new parsing model is proposed to formulate the complete chunking problem as a series of boundary detection sub tasks. Each of these sub tasks is only in charge of detecting one type of the chunk boundaries. As each sub task could be modeled as a binary classification problem, a lot of machine learning techniques could be applied. In our experiments, we only focus on the subject-predicate (SP) and predicateobject (PO) boundary detection sub tasks. By applying SVM algorithm to these sub tasks, we have achieved the best F-Score of 76.56 % and 82.26 % respectively. 1

Abstract. This paper presents a practical tri-training method for Chinese chunking using a small amount of labeled training data and a much larger pool of unlabeled data. We propose a novel selection method for tri-training learning in which newly labeled sentences are selected by comparing the agreements of three classifiers. In detail, in each iteration, a new sample is selected for a classifier if the other two classifiers agree on the labels while itself disagrees. We compare the proposed tri-training learning approach with co-training learning approach on Upenn Chinese Treebank V4.0(CTB4). The experimental results show that the proposed approach can improve the performance significantly. 1