Extracting Concepts’ Relations and Users’ Preferences for Personalizing Query Disambiguation

For most Web searching applications, queries are commonly ambiguous because words usually contain several meanings. Traditional Word Sense Disambiguation (WSD) methods use statistic models or ontology-based knowledge models to find the most appropriate sense for the ambiguous word. Since queries are usually short, the contexts of the queries may not always provide enough information for disambiguating queries. Thus, more than one interpretation may be found for one ambiguous query. In this paper, we propose a cluster-based WSD method, which finds out all appropriate interpretations for the query. Because some senses of one ambiguous word usually have very close semantic relations, we group those similar senses together for explaining the ambiguous word in one interpretation. If the cluster-based WSD method generates several contradictory interpretations for one ambiguous query, we extract users’ preferences from clickthrough data, and determine suitable concepts or concepts’ clusters that meet users’ interests for explaining the ambiguous query.

To save time, healthcare providers frequently use abbreviations while authoring clinical documents. Nevertheless, abbreviations that authors deem unambiguous often confuse other readers, including clinicians, patients, and natural language processing (NLP) systems. Most current clinical NLP systems "post-process" notes long after clinicians enter them into electronic health record systems (EHRs). Such post-processing cannot guarantee 100% accuracy in abbreviation identification and disambiguation, since multiple alternative interpretations exist. Authors describe a prototype system for real-time Clinical Abbreviation Recognition and Disambiguation (rCARD) - i.e., a system that interacts with authors during note generation to verify correct abbreviation senses. The rCARD system design anticipates future integration with web-based clinical documentation systems to improve quality of healthcare records. When clinicians enter documents, rCARD will automatically recognize each abbreviation. For abbreviations with multiple possible senses, rCARD will show a ranked list of possible meanings with the best predicted sense at the top. The prototype application embodies three word sense disambiguation (WSD) methods to predict the correct senses of abbreviations. We then conducted three experments to evaluate rCARD, including 1) a performance evaluation of different WSD methods; 2) a time evaluation of real-time WSD methods; and 3) a user study of typing clinical sentences with abbreviations using rCARD. Using 4,721 sentences containing 25 commonly observed, highly ambiguous clinical abbreviations, our evaluation showed that the best profile-based method implemented in rCARD achieved a reasonable WSD accuracy of 88.8% (comparable to SVM - 89.5%) and the cost of time for the different WSD methods are also acceptable (ranging from 0.630 to 1.649 milliseconds within the same network). The preliminary user study also showed that the extra time costs by rCARD were about 5% of total document entry time and users did not feel a significant delay when using rCARD for clinical document entry. The study indicates that it is feasible to integrate a real-time, NLP-enabled abbreviation recognition and disambiguation module with clinical documentation systems.

BackgroundIn recent years, deep learning methods have been applied to many natural language processing tasks to achieve state-of-the-art performance. However, in the biomedical domain, they have not out-performed supervised word sense disambiguation (WSD) methods based on support vector machines or random forests, possibly due to inherent similarities of medical word senses.ResultsIn this paper, we propose two deep-learning-based models for supervised WSD: a model based on bi-directional long short-term memory (BiLSTM) network, and an attention model based on self-attention architecture. Our result shows that the BiLSTM neural network model with a suitable upper layer structure performs even better than the existing state-of-the-art models on the MSH WSD dataset, while our attention model was 3 or 4 times faster than our BiLSTM model with good accuracy. In addition, we trained “universal” models in order to disambiguate all ambiguous words together. That is, we concatenate the embedding of the target ambiguous word to the max-pooled vector in the universal models, acting as a “hint”. The result shows that our universal BiLSTM neural network model yielded about 90 percent accuracy.ConclusionDeep contextual models based on sequential information processing methods are able to capture the relative contextual information from pre-trained input word embeddings, in order to provide state-of-the-art results for supervised biomedical WSD tasks.

This paper presents a method of word sense disambiguation that assigns a target word the sense that is most related to the senses of its neighbor words. We explore the use of measures of relatedness between word senses based on a novel hybrid approach. First, we investigate how to “literally” and “regularly” express a “concept”. We apply set algebra to Wordnet's synsets cooperating with Wordnet's word ontology. In this way we establish regular rules for constructing various representations (lexical notations) of a concept using Boolean operators and word forms in various synset(s) defined in Wordnet. Then we establish a formal mechanism for quantifying and estimating the semantic relatedness between concepts – we facilitate “concept distribution statistics” to determine the degree of semantic relatedness between two lexically expressed concepts. Human languages have words that can mean different things in different contexts, such words with multiple meanings are potentially “ambiguous”. The process of “deciding which of several meanings of a term is intended in a given context” is known as “Word Sense Disambiguation (WSD)”. The proposed method is not supervised, and does not require any manually created sense‐tagged training examples. The experimental results showed good performance on Semcor, a subset of the Brown corpus. We observe that measures of semantic relatedness are useful sources of information for word sense disambiguation.

This paper describes our system participating in the SemEval-2017 Task 7, for the subtasks of homographic pun location and homographic pun interpretation. For pun interpretation, we use a knowledge-based Word Sense Disambiguation (WSD) method based on sense embeddings. Pun-based jokes can be divided into two parts, each containing information about the two distinct senses of the pun. To exploit this structure we split the context that is input to the WSD system into two local contexts and find the best sense for each of them. We use the output of pun interpretation for pun location. As we expect the two meanings of a pun to be very dissimilar, we compute sense embedding cosine distances for each sense-pair and select the word that has the highest distance. We describe experiments on different methods of splitting the context and compare our method to several baselines. We find evidence supporting our hypotheses and obtain competitive results for pun interpretation.

Word-sense recognition and disambiguation (WERD) is the task of identifying word phrases and their senses in natural language text. Though it is well understood how to disambiguate noun phrases, this task is much less studied for verbs and verbal phrases. We present Werdy, a framework for WERD with particular focus on verbs and verbal phrases. Our framework first identifies multi-word expressions based on the syntactic structure of the sentence; this allows us to recognize both contiguous and non-contiguous phrases. We then generate a list of candidate senses for each word or phrase, using novel syntactic and semantic pruning techniques. We also construct and leverage a new resource of pairs of senses for verbs and their object arguments. Finally, we feed the so-obtained candidate senses into standard word-sense disambiguation (WSD) methods, and boost their precision and recall. Our experiments indicate that Werdy significantly increases the performance of existing WSD methods.

Word sense disambiguation (WSD) has always being a key problem and one of difficult points in natural language processing. WSD is usually considered to be a pattern classification to be research. Feature selection is an important sector of WSD process. We review naive Bayes model (NBM) seriously, and the feature selection method adopted in this paper is directed at Bayesian Assumption to improve NBM. Positional information concealed in the context of ambiguous word is mined via information gain calculation, to increase the knowledge acquisition efficiency of Bayesian model and to improve the effect of word-sense classification. Eight ambiguous words are tested in our experiment; the experimental results of improved Bayesian model are higher 3.5 per cent than the ones of NBM. The accuracy rise is bigger and the improvement effect is outstanding; and these results prove also the method put forward in this paper is efficacious.

Word sense disambiguation is important for many applications in natural language processing fields including machine translation, information retrieval and automatic summarization. In this paper, left word unit and right word unit are extracted for improving the quality of word sense disambiguation (WSD) starting from the target polysemous word. Their semantic knowledge is mined from Tongyici Cilin which is a Chinese semantic lexicon. A new method of word sense disambiguation is proposed with semantic information of left word unit and right word unit. The classifier of word sense disambiguation is built based on bayesian model. SemEval-2007: Task#5 is used as training corpus and test corpus. Experimental results show that the disambiguation classifier’s precision is improved and demonstrate the effectiveness of the method.

Word sense disambiguation (WSD) is a fundamental natural language processing task. Unsupervised knowledge-based WSD only relies on a lexical knowledge base as the sense inventory and has wider practical use than supervised WSD that requires a mass of sense-annotated data. HowNet is the most widely used lexical knowledge base in Chinese WSD. Because of its uniqueness, however, most of existing unsupervised WSD methods cannot work for HowNet-based WSD, and the tailor-made methods have not obtained satisfying results. In this paper, we propose a new unsupervised method for HowNet-based Chinese WSD, which exploits the masked language model task of pre-trained language models. In experiments, considering existing evaluation dataset is small and out-of-date, we build a new and larger HowNet-based WSD dataset. Experimental results demonstrate that our model achieves significantly better performance than all the baseline methods. All the code and data of this paper are available at https://github.com/thunlp/SememeWSD.

This work presents a supervised prepositional phrase (PP) attachment disambiguation system that uses contextualized distributional information as the distance metric for a nearest-neighbor classifier. Contextualized word vectors constructed from the GigaWord Corpus provide a method for implicit Word Sense Disambiguation (WSD), whose reliability helps this system outperform baselines and achieve comparable results to those of systems with full WSD modules. This suggests that targeted WSD methods are preferable to ignoring sense information and also to implementing WSD as an independent module in a pipeline.

In natural language processing, languages have a number of ambiguous words and solving such kind of problem for the language can help the development of word sense disambiguation using corpus­based Approach. Due to the absence of automatic word sense disambiguation to the language can be a challenge for the development of natural language processing applications of the language. So, this study was to design a word sense disambiguation prototype model for Geez Language words using Corpus-Based technique to extract training sets that minimize the quantity of the desired human intervention. because of the inaccessibility of the Geez wordNet and annotated datasets, six words were Chosen.These words were ሀለፈ(Halafe), ቆመ(ḱome), ባረከ(bareke), አስተርዓየ(astaraya), ገብረ(gebire), ሰዓለ(Se’ale).Separate information sets victimization six ambiguous words were ready for the event of this Geez WSD model. the ultimate classification task was done on the absolutely labeled coaching set victimization Adaboost, SMO, and AD tree classification algorithms on the WEKA package.We compared the Corpus-­based machine learning approachs which are unsupervised, supervised and semi-supervised and we found that semi­-supervised machine learning approach achieved the best performance. The proposed method achieved an average performance of 92.1%, 91.3%, 91% and 91.1% for Precision, Recall, F1­-score and Accuracy using ADTree algorithm respectively. Window size of 4-­4 has been the optimal window size to identify the meaning of the selected ambiguous words of Geez language using ADTree algorithm.

Sprinkled semantic diffusion kernel for word sense disambiguation

This paper presents a method of word sense disambiguation that assigns a target word the sense that is most related to the senses of its neighbor words. We explore the use of measures of relatedness between word senses based on a novel hybrid approach. First, we investigate how to literally and regularly express a concept. We apply set algebra to Wordnet’s synsets cooperating with Wordnet’s word ontology. In this way we establish regular rules for constructing various representations (lexical notations) of a using Boolean operators and various word forms in synset(s). Then we construct a formal mechanism for quantifying and estimating the semantic relatedness between concepts - we facilitate concept distribution statistics to determine the degree of semantic relatedness between two lexically expressed concepts. Then we applied the measure of semantic relatedness to the WSD task. The experimental results showed good performance on Semcor, a subset of Brown corpus. We observe that measures of semantic relatedness are useful sources of information for word sense disambiguation.

This paper describes EPROP, a novel technique requiring little prior knowledge for word sense disambiguation of semantic relations between pairs of ambiguous concepts in knowledge bases. Our method makes inferences by aggregating evidences from ambiguous word interpretations and propagating the acquired knowledge over a taxonomy to generalize or specialize this knowledge. This propagation process allows the estimation of the degree of belief for each possible word sense assignment given the available evidence. EPROP only requires a sense inventory structured as a taxonomy to disambiguate a knowledge base by combining evidence from the ambiguous facts stored in the knowledge base. We have performed different experiments that show that our method achieves good results on the disambiguation of the semantic relations included in WordNet and ConceptNet. We also show how our method can be used to improve the performance of state-of-the-art word sense disambiguation methods.

Similarity calculation between Business Process Models (BPM) has an important role in the process of managing BPM repository. One of its uses is to facilitate the searching process of a model in the repository. Similarity calculation between business processes is closely related with semantic string similarity. Semantic string similarity is usually performed by utilizing a lexical database, such as WordNet, to find the semantic meaning of words. The problem in WordNet is that this lexical database contains terms wich have more than one meaning or polysemous. Selecting the wrong meaning will decrease the accuracy of similarity calculation process. In this study, we will try to improve the accuracy of similarity calculation of business processes using Word Sense Disambiguation (WSD). The main purpose is to eliminate the ambiguity of polysemous words before calculating the similarity value. WSD is performed by unsupervised methods based on the value of graph connectivity. Then, we used a lexical database that is focused in the business and industry field. The results from this study is able to achieve higher accuracy of the sense selection process for terms especially terms that are related to business and industrial domains. It will also increase the accuracy of similarity value calculation between the business process models .