Combining Contextual Features for Word Sense Disambiguation

This paper presents a high-performance broad-coverage supervised word sense disambiguation (WSD) system for English verbs that uses linguistically motivated features and a smoothed maximum entropy machine learning model. We describe three specific enhancements to our system's treatment of linguistically motivated features which resulted in the best published results on SENSEVAL-2 verbs. We then present the results of training our system on OntoNotes data, both the SemEval-2007 task and additional data. OntoNotes data is designed to provide clear sense distinctions, based on using explicit syntactic and semantic criteria to group WordNet senses, with sufficient examples to constitute high quality, broad coverage training data. Using similar syntactic and semantic features for WSD, we achieve performance comparable to that of human taggers, and competitive with the top results for the SemEval-2007 task. Empirical analysis of our results suggests that clarifying sense boundaries and/or increasing the number of training instances for certain verbs could further improve system performance.

Proceedings of the Nineteenth Conference on Computational Natural Language Learning, 2015

Supervised word sense disambiguation (WSD) systems are usually the best performing systems when evaluated on standard benchmarks. However, these systems need annotated training data to function properly. While there are some publicly available open source WSD systems, very few large annotated datasets are available to the research community. The two main goals of this paper are to extract and annotate a large number of samples and release them for public use, and also to evaluate this dataset against some word sense disambiguation and induction tasks. We show that the open source IMS WSD system trained on our dataset achieves stateof-the-art results in standard disambiguation tasks and a recent word sense induction task, outperforming several task submissions and strong baselines.

2004

Although syntactic features offer more specific information about the context surrounding a target word in a Word Sense Disambiguation (WSD) task, in general, they have not distinguished themselves much above positional features such as bag-of-words. In this paper we offer two methods for increasing the recall rate when using syntactic features on the WSD task by: 1) using an algorithm for discovering in the corpus every possible syntactic feature involving a target word, and 2) using wildcards in place of the lemmas in the templates of the syntactic features. In the best experimental results on the SENSEVAL-2 data we achieved an Fmeasure of 53.1% which is well above the mean F-measure performance of official SENSEVAL-2 entries, of 44.2%. These results are encouraging considering that only one kind of feature is used and only a simple Support Vector Machine (SVM) running with the defaults is used for the machine learning.

2004

The success of supervised learning approaches to word sense disambiguation is largely dependent on the features used to represent the context in which an ambiguous word occurs. Previous work has reached mixed conclusions; some suggest that combinations of syntactic and lexical features will perform most effectively. However, others have shown that simple lexical features perform well on their own. This paper evaluates the effect of using different lexical and syntactic features both individually and in combination. We show that it is possible for a very simple ensemble that utilizes a single lexical feature and a sequence of part of speech features to result in disambiguation accuracy that is near state of the art.

In this paper, we describe our experiments on statistical word sense disambiguation (WSD) using two systems based on different approaches: Naïve Bayes on word tokens and Maximum Entropy on local syntactic and semantic features. In the first approach, we consider a context window and a sub-window within it around the word to disambiguate. Within the outside window, only content words are considered, but within the sub-window, all words are taken into account. Both window sizes are tuned by the system for each word to disambiguate and accuracies of 75% and 67% were respectively obtained for coarse and fine grained evaluations. In the second system, sense resolution is done using an approximate syntactic structure as well as semantics of neighboring nouns as features to a Maximum Entropy learner. Accuracies of 70% and 63% were obtained for coarse and fine grained evaluations.

Journal of Natural Language Processing, 2009

Traditionally, many researchers have addressed word sense disambiguation (WSD) as an independent classification problem for each word in a sentence. However, the problem with their approaches is that they disregard the interdependencies of word senses. Additionally, since they construct an individual sense classifier for each word, their method is limited in its applicability to the word senses for which training instances are served. In this paper, we propose a supervised WSD model based on the syntactic dependencies of word senses. In particular, we assume that strong dependencies between the sense of a syntactic head and those of its dependents exist. We describe these dependencies on the tree-structured conditional random fields (T-CRFs), and obtain the most appropriate assignment of senses optimized over the sentence. Furthermore, we incorporate these sense dependencies in combination with various coarse-grained sense tag sets, which are expected to relieve the data sparseness problem, and enable our model to work even for words that do not appear in the training data. In experiments, we display the appropriateness of considering the syntactic dependencies of senses, as well as the improvements by the use of coarse-grained tag sets. The performance of our model is shown to be comparable to those of state-ofthe-art WSD systems. We also present an in-depth analysis of the effectiveness of the sense dependency features by showing intuitive examples.

Proc. of the 4th …, 2007

In this paper, we described the PNNL Word Sense Disambiguation system as applied to the English all-word task in SemEval 2007. We use a supervised learning approach, employing a large number of features and using Information Gain for dimension ...

2006

In the Natural Language Processing (NLP) community, Word Sense Disambiguation (WSD) has been described as the task which selects the appropriate meaning (sense) to a given word in a text or discourse where this meaning is distinguishable from other senses potentially attributable to that word. These senses could be seen as the target labels of a classification problem. That is, Machine Learning (ML) seems to be a possible way to tackle this problem.

2021

Current state-of-the-art supervised word sense disambiguation (WSD) systems (such as GlossBERT and bi-encoder model) yield surprisingly good results by purely leveraging pretrained language models and short dictionary definitions (or glosses) of the different word senses. While concise and intuitive, the sense gloss is just one of many ways to provide information about word senses. In this paper, we focus on enhancing the sense representations via incorporating synonyms, example phrases or sentences showing usage of word senses, and sense gloss of hypernyms. We show that incorporating such additional information boosts the performance on WSD. With the proposed enhancements, our system achieves an F1 score of 82.0% on the standard benchmark test dataset of the English all-words WSD task, surpassing previous published scores on this benchmark dataset.

Proceedings of the workshop on Human Language Technology - HLT '94, 1994

This paper presents and evaluates models created according to a schema that provides a description of the joint distribution of the values of sense tags and contextual features that is potentially applicable to a wide range of content words. The models are evaluated through a series of experiments, the results of which suggest that the schema is particularly well suited to nouns but that it is also applicable to words in other syntactic categories.