Elias Iosif

Unsupervised Semantic Similarity Computation between Terms Using Web Documents

In this work, Web-based metrics that compute the semantic similarity between words or terms are presented and compared with the state of the art. Starting from the fundamental assumption that similarity of context implies similarity of meaning, relevant Web documents are downloaded via a Web search engine and the contextual information of words of interest is compared (context-based similarity metrics). The proposed algorithms work automatically, do not require any human-annotated knowledge resources, e.g., ontologies, and can be generalized and applied to different languages. Context-based metrics are evaluated both on the Charles-Miller data set and on a medical term data set. It is shown that context-based similarity metrics significantly outperform co-occurrence-based metrics, in terms of correlation with human judgment, for both tasks. In addition, the proposed unsupervised context-based similarity computation algorithms are shown to be competitive with the state-of-the-art supervised semantic similarity algorithms that employ language-specific knowledge resources. Specifically, context-based metrics achieve correlation scores of up to 0.88 and 0.74 for the Charles-Miller and medical data sets, respectively. The effect of stop word filtering is also investigated for word and term similarity computation. Finally, the performance of context-based term similarity metrics is evaluated as a function of the number of Web documents used and for various feature weighting schemes.

Distributional Semantic Models for Affective Text Analysis

We present an affective text analysis model that can directly estimate and combine affective ratings of multi-word terms, with application to the problem of sentence polarity/semantic orientation detection. Starting from a hierarchical compositional method for generating sentence ratings, we expand the model by adding multi-word terms that can capture non-compositional semantics. The method operates similarly to a bigram language model, using bigram terms or backing off to unigrams based on a (degree of) compositionality criterion. The affective ratings for n-gram terms of different orders are estimated via a corpus-based method using distributional semantic similarity metrics between unseen words and a set of seed words. N-gram ratings are then combined into sentence ratings via simple algebraic formulas. The proposed framework produces state-of-the-art results for word-level tasks in English and German and the sentence-level news headlines classification SemEval07-Task14 task. The inclusion of bigram terms to the model provides significant performance improvement, even if no term selection is applied.

Ontology based information extraction from text

Information extraction systems employ ontologies as a means to describe formally the domain knowledge exploited by these systems for their operation. The aim of this survey is to study the contribution of ontologies to information extraction systems. We believe that this will help towards specifying a concrete methodology for ontology based information extraction exploiting all levels of ontological knowledge, from domain entities for named entity recognition, to the use of conceptual hierarchies for pattern generalization, to the use of properties and non-taxonomic relations for pattern acquisition, and finally to the use of the domain model itself for integrating extracted entities and instances of relations, as well as for discovering implicit information and detecting inconsistencies.

UNSUPERVISED COMBINATION OF METRICS FOR SEMANTIC CLASS INDUCTION

In this paper, unsupervised algorithms for combining semantic similarity metrics are proposed for the problem of automatic class induction. The automatic class induction algorithm is based on the work of Pargellis et al,. The semantic similarity metrics that are evaluated and combined are based on narrow- and wide-context vector- product similarity. The metrics are combined using linear weights that are computed on the fly and are updated at each iteration of the class induction algorithm, forming a corpus-independent metric. Specifically, the weight of each metric is selected to be inversely proportional to the inter-class similarity of the classes induced by that metric and for the current iteration of the algorithm. The proposed algorithms are evaluated on two corpora: a semantically heterogeneous news domain (HR-Net) and an application-specific travel reservation corpus (ATIS). It is shown, that the (unsupervised) adaptive weighting scheme outperforms the (supervised) fixed weighting scheme. Up to 50% relative error reduction is achieved by the adaptive weighting scheme.

Combining statistical similarity measures for automatic induction of semantic classes

In this paper, an unsupervised semantic class induction algorithm is proposed that is based on the principle that similarity of context implies similarity of meaning. Two semantic similarity metrics that are variations of the vector product distance are used in order to measure the semantic distance between words and to automatically generate semantic classes. The first metric computes wide-context similarity between words using a bag-of-words model, while the second metric computes narrow-context similarity using a bigram language model. A hybrid metric that is defined as the linear combination of the wide and narrow-context metrics is also proposed and evaluated. To cluster words into semantic classes an iterative clustering algorithm is used. The semantic metrics are evaluated on two corpora: a semantically heterogeneous Web news domain (HR-Net) and an application-specific travel reservation corpus (ATIS). For the hybrid metric, semantic class member precision of 85% is achieved at 17% recall for the HR-Net task and precision of 85% is achieved at 55% recall for the ATIS task

Unsupervised Semantic Similarity Computation using Web Search Engines

In this paper, we propose two novel web-based metrics for semantic similarity computation between words. Both metrics use a web search engine in order to exploit the retrieved information for the words of interest. The first metric considers only the page counts returned by a search engine, based on the work of [1]. The second downloads a number of the top ranked documents and applies widecontext and narrow-context metrics. The proposed metrics work automatically, without consulting any human annotated knowledge resource. The metrics are compared with WordNet-based methods. The metrics performance is evaluated in terms of correlation with respect to the pairs of the commonly used Charles - Miller dataset. The proposed wide-context metric achieves 71% correlation, which is the highest score achieved among the fully unsupervised metrics in the literature up to date.

Similarity computation using semantic networks created from web-harvested data

We investigate language-agnostic algorithms for the const ruction of unsupervised distributional semantic models using web-harvested corpora. Specifically, a corpus is created from web document snippets and the relevant semantic similarity statistics a re encoded in a semantic network. We propose the notion of semantic neighborhoods that are defined us ing co-occurrence or context similarity features. Three neighborhood-based similarity metrics ar e proposed, motivated by the hypotheses of attributional and maximum sense similarity. The propose d metrics are evaluated against human similarity ratings achieving state-of-the-art results.

PREDICTING AUDIO-VISUAL SALIENT EVENTS BASED ON VISUAL, AUDIO AND TEXT MODALITIES FOR MOVIE SUMMARIZATION

In this paper, we present a new and improved synergistic approach to the problem of audio-visual salient event detection and movie summarization based on visual, audio and text modalities. Spatio-temporal visual saliency is estimated through a perceptually inspired frontend based on 3D (space, time) Gabor filters and frame-wise features are extracted from the saliency volumes. For the auditory salient event detection we extract features based on Teager-Kaiser Energy Operator, while text analysis incorporates part-of-speech tagging and affective modeling of single words on the movie subtitles. For the evaluation of the proposed system, we employ an elementary and non-parametric classification technique like KNN. Detection results are reported on the MovSum database, using objective evaluations against ground-truth denoting the perceptually salient events, and human evaluations of the movie summaries. Our evaluation verifies the appropriateness of the proposed methods compared to our baseline system. Finally, our newly proposed summarization algorithm produces summaries that consist of salient and meaningful events, also improving the comprehension of the semantics.

Tweester at SemEval-2016 Task 4: Sentiment Analysis in Twitter using Semantic-Affective Model Adaptation

We describe our submission to SemEval2016 Task 4: Sentiment Analysis in Twitter. The proposed system ranked first for the subtask B. Our system comprises of multiple independent models such as neural networks, semantic-affective models and topic modeling that are combined in a probabilistic way. The novelty of the system is the employment of a topic modeling approach in order to adapt the semantic-affective space for each tweet. In addition, significant enhancements were made in the main system dealing with the data preprocessing and feature extraction including the employment of word embeddings. Each model is used to predict a tweet’s sentiment (positive, negative or neutral) and a late fusion scheme is adopted for the final decision.

Toward the Automatic Extraction of Policy Networks Using Web Links and Documents

Policy networks are widely used by political scientists and economists to explain various financial and social phenomena, such as the development of partnerships between political entities or institutions from different levels of governance. The analysis of policy networks demands a series of arduous and time-consuming manual steps including interviews and questionnaires. In this paper, we estimate the strength of relations between actors in policy networks using features extracted from data harvested from the web. Features include webpage counts, outlinks, and lexical information extracted from web documents or web snippets. The proposed approach is automatic and does not require any external knowledge source, other than the specification of the word forms that correspond to the political actors. The features are evaluated both in isolation and jointly for both positive and negative (antagonistic) actor relations. The proposed algorithms are evaluated on two EU policy networks from the political science literature. Performance is measured in terms of correlation and mean square error between the human rated and the automatically extracted relations. Correlation of up to 0.74 is achieved for positive relations. The extracted networks are validated by political scientists and useful conclusions about the evolution of the networks over time are drawn.