Results 21 - 30
of
106
Using the Multilingual Central Repository for Graph-Based Word Sense Disambiguation
- Proc. Sixth Language Resources and Evaluation Conf
, 2008
"... This paper presents the results of a graph-based method for performing knowledge-based Word Sense Disambiguation (WSD). The technique exploits the structural properties of the graph underlying the chosen knowledge base. The method is general, in the sense that it is not tied to any particular knowle ..."
Abstract
-
Cited by 5 (2 self)
- Add to MetaCart
This paper presents the results of a graph-based method for performing knowledge-based Word Sense Disambiguation (WSD). The technique exploits the structural properties of the graph underlying the chosen knowledge base. The method is general, in the sense that it is not tied to any particular knowledge base, but in this work we have applied it to the Multilingual Central Repository (MCR, (Atserias et al., 2004)). The evaluation has been performed on the Senseval-3 all-words task (Snyder and Palmer, 2004). The main contributions of the paper are twofold: (1) We have evaluated the separate and combined performance of each type of relation in the MCR, and thus indirectly validated the contents of the MCR and their potential for WSD. (2) We obtain state-of-the-art results, and in fact yield the best results that can be obtained using publicly available data. 1.
On the Use of Automatically Acquired Examples for All-Nouns Word Sense Disambiguation
"... This article focuses on Word Sense Disambiguation (WSD), which is a Natural Language Processing task that is thought to be important for many Language Technology applications, such as Information Retrieval, Information Extraction, or Machine Translation. One of the main issues preventing the deploym ..."
Abstract
-
Cited by 5 (0 self)
- Add to MetaCart
(Show Context)
This article focuses on Word Sense Disambiguation (WSD), which is a Natural Language Processing task that is thought to be important for many Language Technology applications, such as Information Retrieval, Information Extraction, or Machine Translation. One of the main issues preventing the deployment of WSD technology is the lack of training examples for Machine Learning systems, also known as the Knowledge Acquisition Bottleneck. A method which has been shown to work for small samples of words is the automatic acquisition of examples. We have previously shown that one of the most promising example acquisition methods scales up and produces a freely available database of 150 million examples from Web snippets for all polysemous nouns in WordNet. This paper focuses on the issues that arise when using those examples, all alone or in addition to manually tagged examples, to train a supervised WSD system for all nouns. The extensive evaluation on both lexical-sample and all-words Senseval benchmarks shows that we are able to improve over commonly used baselines and to achieve top-rank performance. The good use of the prior distributions from the senses proved to be a crucial factor. 1.
Word sense disambiguation using sense examples automatically acquired from a second language
- IN PROCEEDINGS OF HLT/EMNLP
, 2005
"... We present a novel almost-unsupervised approach to the task of Word Sense Disambiguation (WSD). We build sense examples automatically, using large quantities of Chinese text, and English-Chinese and Chinese-English bilingual dictionaries, taking advantage of the observation that mappings between wor ..."
Abstract
-
Cited by 5 (0 self)
- Add to MetaCart
We present a novel almost-unsupervised approach to the task of Word Sense Disambiguation (WSD). We build sense examples automatically, using large quantities of Chinese text, and English-Chinese and Chinese-English bilingual dictionaries, taking advantage of the observation that mappings between words and meanings are often different in typologically distant languages. We train a classifier on the sense examples and test it on a gold standard English WSD dataset. The evaluation gives results that exceed previous state-of-the-art results for comparable systems. We also demonstrate that a little manual effort can improve the quality of sense examples, as measured by WSD accuracy. The performance of the classifier on WSD also improves as the number of training sense examples increases.
A Large-scale Pseudoword-based Evaluation Framework for State-of-the-Art Word Sense Disambiguation
"... The evaluation of several tasks in lexical semantics is often limited by the lack of large amounts of manual annotations, not only for training purposes, but also for testing purposes. Word Sense Disambiguation (WSD) is a case in point, as hand-labeled datasets are particularly hard and time-consumi ..."
Abstract
-
Cited by 5 (1 self)
- Add to MetaCart
(Show Context)
The evaluation of several tasks in lexical semantics is often limited by the lack of large amounts of manual annotations, not only for training purposes, but also for testing purposes. Word Sense Disambiguation (WSD) is a case in point, as hand-labeled datasets are particularly hard and time-consuming to create. Consequently, evaluations tend to be performed on a small scale, which does not allow for in-depth analysis of the factors that determine a systems ’ performance. In this paper we address this issue by means of a realistic simulation of large-scale evaluation for the WSD task. We do this by providing two main contributions: first, we put forward two novel approaches to the wide-coverage generation of semantically-aware pseudowords, i.e., artificial words capable of modeling real polysemous words; second, we leverage the most suitable type of pseudoword to create large pseudosense-annotated corpora, which enable a large-scale experimental framework for the comparison of state-of-the-art supervised and knowledge-based algorithms. Using this framework, we study the impact of supervision and knowledge on the two major disambiguation paradigms and perform an in-depth analysis of the factors which affect their performance. 1.
Semantic Composition with Quotient Algebras
- Proceedings of Geometric Models of Natural Language Semantics (GEMS-2010
, 2010
"... We describe an algebraic approach for computing with vector based semantics. The tensor product has been proposed as a method of composition, but has the undesirable property that strings of different length are incomparable. We consider how a quotient algebra of the tensor algebra can allow such co ..."
Abstract
-
Cited by 5 (2 self)
- Add to MetaCart
(Show Context)
We describe an algebraic approach for computing with vector based semantics. The tensor product has been proposed as a method of composition, but has the undesirable property that strings of different length are incomparable. We consider how a quotient algebra of the tensor algebra can allow such comparisons to be made, offering the possibility of data-driven models of semantic composition. 1
Decorrelation and Shallow Semantic Patterns for Distributional Clustering of Nouns and Verbs
"... Distributional approximations to lexical semantics are very useful not only in helping the creation of lexical semantic resources (Kilgariff et al., 2004; Snow et al., 2006), but also when directly applied in tasks that can benefit from large-coverage semantic knowledge such as coreference resolutio ..."
Abstract
-
Cited by 4 (1 self)
- Add to MetaCart
(Show Context)
Distributional approximations to lexical semantics are very useful not only in helping the creation of lexical semantic resources (Kilgariff et al., 2004; Snow et al., 2006), but also when directly applied in tasks that can benefit from large-coverage semantic knowledge such as coreference resolution (Poesio et al., 1998; Gasperin and Vieira, 2004; Versley, 2007), word sense disambiguation (Mc-Carthy et al., 2004) or semantical role labeling (Gordon and Swanson, 2007). We present a model that is built from Webbased corpora using both shallow patterns for grammatical and semantic relations and a window-based approach, using singular value decomposition to decorrelate the feature space which is otherwise too heavily influenced by the skewed topic distribution of Web corpora. 1
A Structured Distributional Semantic Model: Integrating Structure with Semantics
"... In this paper we present a novel approach (SDSM) that incorporates structure in distributional semantics. SDSM represents meaning as relation specific distributions over syntactic neighborhoods. We empirically show that the model can effectively represent the semantics of single words and provides s ..."
Abstract
-
Cited by 4 (0 self)
- Add to MetaCart
(Show Context)
In this paper we present a novel approach (SDSM) that incorporates structure in distributional semantics. SDSM represents meaning as relation specific distributions over syntactic neighborhoods. We empirically show that the model can effectively represent the semantics of single words and provides significant advantages when dealing with phrasal units that involve word composition. In particular, we demonstrate that our model outperforms both state-of-the-art window-based word embeddings as well as simple approaches for composing distributional semantic representations on an artificial task of verb sense disambiguation and a real-world application of judging event coreference. 1
The effects of semantic annotations on precision parse ranking
- In Proc. of the First Joint Conference on Lexical and Computational Semantics (*SEM
, 2012
"... We investigate the effects of adding semantic annotations including word sense hypernyms to the source text for use as an extra source of information in HPSG parse ranking for the English Resource Grammar. The semantic annotations are coarse semantic categories or entries from a distributional thesa ..."
Abstract
-
Cited by 4 (1 self)
- Add to MetaCart
We investigate the effects of adding semantic annotations including word sense hypernyms to the source text for use as an extra source of information in HPSG parse ranking for the English Resource Grammar. The semantic annotations are coarse semantic categories or entries from a distributional thesaurus, assigned either heuristically or by a pre-trained tagger. We test this using two test corpora in different domains with various sources of training data. The best reduces error rate in dependency F-score by 1 % on average, while some methods produce substantial decreases in performance.
Learning an Expert from Human Annotations in Statistical Machine Translation: the Case of Out-of-Vocabulary Words
"... We present a general method for incorporating an “expert ” model into a Statistical Machine Translation (SMT) system, in order to improve its performance on a particular “area of expertise”, and apply this method to the specific task of finding adequate replacements for Out-of-Vocabulary (OOV) words ..."
Abstract
-
Cited by 3 (1 self)
- Add to MetaCart
(Show Context)
We present a general method for incorporating an “expert ” model into a Statistical Machine Translation (SMT) system, in order to improve its performance on a particular “area of expertise”, and apply this method to the specific task of finding adequate replacements for Out-of-Vocabulary (OOV) words. Candidate replacements are paraphrases and entailed phrases, obtained using monolingual resources. These candidate replacements are transformed into “dynamic biphrases”, generated at decoding time based on the context of each source sentence. Standard SMT features are enhanced with a number of new features aimed at scoring translations produced by using different replacements. Active learning is used to discriminatively train the model parameters from human assessments of the quality of translations. The learning framework yields an SMT system which is able to deal with sentences containing OOV words but also guarantees that the performance is not degraded for input sentences without OOV words. Results of experiments on English-French translation show that this method outperforms previous work addressing OOV words in terms of acceptability. 1
Acquiring Applicable Common Sense Knowledge from the Web
"... In this paper, a framework for acquiring common sense knowledge from the Web is presented. Common sense knowledge includes information about the world that humans use in their everyday lives. To acquire this knowledge, relationships between nouns are retrieved by using search phrases with automatica ..."
Abstract
-
Cited by 3 (1 self)
- Add to MetaCart
(Show Context)
In this paper, a framework for acquiring common sense knowledge from the Web is presented. Common sense knowledge includes information about the world that humans use in their everyday lives. To acquire this knowledge, relationships between nouns are retrieved by using search phrases with automatically filled constituents. Through empirical analysis of the acquired nouns over Word-Net, probabilities are produced for relationships between a concept and a word rather than between two words. A specific goal of our acquisition method is to acquire knowledge that can be successfully applied to NLP problems. We test the validity of the acquired knowledge by means of an application to the problem of word sense disambiguation. Results show that the knowledge can be used to improve the accuracy of a state of the art unsupervised disambiguation system. 1
