DOCSLIB.ORG

UNIBA: Combining Distributional Semantic Models and Word Sense Disambiguation for Textual Similarity

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
UNIBA: Combining Distributional Semantic Models and Word Sense Disambiguation for Textual Similarity UNIBA: Combining Distributional Semantic Models and Word Sense Disambiguation for Textual Similarity Pierpaolo Basile and Annalina Caputo and Giovanni Semeraro Department of Computer Science University of Bari Aldo Moro Via, E. Orabona, 4 - 70125 Bari (Italy) firstname.surname @uniba.it { } Abstract based), lexical (word sense disambiguation), and distributional level. The idea is to combine in a This paper describes the UNIBA team unique system the semantic aspects that pertain participation in the Cross-Level Semantic text fragments. Similarity task at SemEval 2014. We pro- The following section gives more details about pose to combine the output of different se- the similarity measures and their combination in a mantic similarity measures which exploit unique score through supervised methods (Section Word Sense Disambiguation and Distribu- 2). Section 3 describes the system set up for the tional Semantic Models, among other lex- evaluation and comments on the reported results, ical features. The integration of similar- while Section 4 concludes the paper. ity measures is performed by means of two supervised methods based on Gaus- 2 System Description sian Process and Support Vector Machine. Our systems obtained very encouraging The idea behind our system is to combine the results, with the best one ranked 6th out output of several similarity measures/features by of 38 submitted systems. means of a supervised algorithm. Those features were grouped in three main categories. The fol- 1 Introduction lowing three sub-sections describe in detail each feature exploited by the system. Cross-Level Semantic Similarity (CLSS) is the task of computing the similarity between two text 2.1 Distributional Semantics Level fragments of different sizes. The task focuses on Distributional Semantic Models (DSM) are an the comparison between texts at different lexical easy way for building geometrical spaces of con- levels, i.e. between a larger and a smaller text. cepts, also known as Semantic (or Word) Spaces, The task comprises four different levels: 1) para- by skimming through huge corpora of text in or- graph to sentence; 2) sentence to phrase; 3) phrase der to learn the context of word usage. In the re- to word; 4) word to sense. The task objective is sulting space, semantic relatedness/similarity be- to provide a framework for evaluating general vs. tween two words is expressed by the opposite of level-specialized methods. the distance between points that represent those Our general approach consists in combining words. Thus, the semantic similarity can be com- scores coming from different semantic similarity puted as the cosine of the angle between the two algorithms. The combination is performed by a vectors that represent the words. This concept supervised method using the training data pro- of similarity can be extended to whole sentences vided by the task organizers. The data set com- by combining words through vector addition (+), prises pairs of text fragments that can be rated with which corresponds to the point-wise sum of the a score between 0 and 4, where 4 indicates the vector components. Our DSM measure (DSM) maximum level of similarity. is based on a SemanticSpace, represented by a We select algorithms which provide similarities co-occurrences matrix M, built by analysing the at different levels of semantics: surface (or string- distribution of words in the British National Cor- This work is licensed under a Creative Commons At- pus (BNC). Then, M is reduced using the Latent tribution 4.0 International Licence. Page numbers and pro- ceedings footer are added by the organisers. Licence details: Semantic Analysis (LSA) (Landauer and Dumais, http://creativecommons.org/licenses/by/4.0/ 1997). Vector addition and cosine similarity are 748 Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 748–753, Dublin, Ireland, August 23-24, 2014. then used for building the vector representation of this can be considered as a variation of the in- each text fragment and computing their pairwise verse document frequency (idf ) for retrieval similarity, respectively. that we named inverse gloss frequency (igf ). The igf for a word wk occurring gfk∗ times in 2.2 Lexical Semantics Level the set of extended glosses for all the senses Word Sense Disambiguation. Most of our in Si, the sense inventory of wi, is computed Si measures rely on the output of a Word Sense Dis- as IGFk = 1 + log2 | | . The final weight gfk∗ ambiguation (WSD) algorithm. Our newest ap- for the word wk appearing h times in the ex- proach to WSD, recently presented in Basile et tended gloss gij∗ is given by: al. (2014), is based on the simplified Lesk algo- rithm (Vasilescu et al., 2004). Each word wi in 1 weight(wk, gij∗ ) = h IGFk (1) a sequence w1w2...wn is disambiguated individ- × × 1 + d ually by choosing the sense that maximizes the similarity between the gloss and the context of wi 2. Building the context. The context C for the (i.e. the whole text where w occurs). To boost i word wi is represented by all the words that the overlap between the context and the gloss, occur in the text. this last is expanded with glosses of related mean- ings, following the approach described in Baner- 3. Building the vector representations. The con- jee and Pedersen (2002). As sense inventory we text C and each extended gloss gij∗ are repre- choose BabelNet 1.1, a huge multilingual seman- sented as vectors in the SemanticSpace built tic network which comprises both WordNet and through the DSM described in Subsection Wikipedia (Navigli and Ponzetto, 2012). The al- 2.1. gorithm consists of the following steps: 4. Sense ranking. The algorithm computes the 1. Building the glosses. We retrieve all possible cosine similarity between the vector repre- word meanings for the target word wi that are sentation of each extended gloss gij∗ and that listed in BabelNet. BabelNet mixes senses of the context C. Then, the cosine similar- in WordNet and Wikipedia. First, senses ity is linearly combined with the probability in WordNet are searched for; if no sense is p(sij wi), which takes into account the sense found (as often happens with named enti- | distribution of sij given the word wi. The ties), senses for the target word are sought in sense distribution is computed as the num- Wikipedia. We preferred that strategy rather ber of times the word wi was tagged with than retrieving senses from both sources at the sense sij in SemCor, a collection of 352 once because this last approach produced documents manually annotated with Word- worse results when tuning the system. Once Net synsets. T he additive (Laplace) smooth- the set of senses S = s , s , ..., s as- i { i1 i2 ik} ing prevents zero probabilities, which can oc- sociated to the target word wi has been re- cur when some synsets do not appear in Sem- trieved, gloss expansion occurs. For each Cor. The probability is computed as follows: sense sij of wi, the algorithm builds the sense extended gloss gij∗ by appending the glosses t(wi, sij) + 1 of meanings related to s to its original gloss p(sij wi) = (2) ij | #wi + Si gij. The related meanings, with the exception | | of “antonym” senses, are the output of the The output of this step is a ranked list of BabelNet function “getRelatedMap”. More- synsets. over, each word in gij∗ is weighted by a func- tion inversely proportional to the distance be- The WSD measure (WSD) is computed on the top tween sij and its related meaning. The dis- of the output of the last step. For each text frag- tance d is computed as the number of edges ment, we build a Bag-of-Synset (BoS) as the sum, linking two senses in the graph. The func- over the whole text, of the weighted synsets as- tion takes also into account the frequencies sociated with each word. Then, we compute the of the words in all the glosses giving more WSD similarity as the cosine similarity between emphasis to the most discriminative words; the two BoS. 749 Graph. A sub-graph of BabelNet is built for the two texts; each text fragment starting from the synsets pro- vided by the WSD algorithm. For each word the MCS The most common subsequence between synset with the highest score is selected, then this the two texts; initial set is expanded with the related synsets in 2-gram, 3-gram For each text fragment, we BabelNet. We apply the Personalized Page Rank build the Bag-of-n-gram (with n varying in (Haveliwala, 2002) to each sub-graph where the 2, 3 ); then we compute the cosine similar- synset scores computed by the WSD algorithm are { } ity between the two Bag-of-n-gram repre- exploited as prior probabilities. The weighted rank sentations. of synsets provided by Page Rank is used to build the BoS of the two text fragments, then the Person- BOW For each tokenized text fragment, we build alized Page Rank (PPR) is computed as the cosine its Bag-of-Word, and then compute the co- similarity between them. sine similarity between the two BoW. Synset Distributional Space. Generally, sim- L1 The length in characters of the first text frag- ilarity measures between synsets rely on the ment; synsets hierarchy in a semantic network (e.g. WordNet). We define a new approach that is com- L2 The length in caracters of the second text frag- pletely different, and represents synsets as points ment; in a geometric space that we call SDS (Synset Dis- tributional Space). SDS is generated taking into DIFF The difference between L1 and L2. account the synset relationships, and similarity is defined as the synsets closeness in the space.
Load more

Recommended publications
  • Combining Semantic and Lexical Measures to Evaluate Medical Terms Similarity?
    Combining semantic and lexical measures to evaluate medical terms similarity? Silvio Domingos Cardoso1;2, Marcos Da Silveira1, Ying-Chi Lin3, Victor Christen3, Erhard Rahm3, Chantal Reynaud-Dela^ıtre2, and C´edricPruski1 1 LIST, Luxembourg Institute of Science and Technology, Luxembourg fsilvio.cardoso,marcos.dasilveira,[email protected] 2 LRI, University of Paris-Sud XI, France [email protected] 3 Department of Computer Science, Universit¨atLeipzig, Germany flin,christen,[email protected] Abstract. The use of similarity measures in various domains is corner- stone for different tasks ranging from ontology alignment to information retrieval. To this end, existing metrics can be classified into several cate- gories among which lexical and semantic families of similarity measures predominate but have rarely been combined to complete the aforemen- tioned tasks. In this paper, we propose an original approach combining lexical and ontology-based semantic similarity measures to improve the evaluation of terms relatedness. We validate our approach through a set of experiments based on a corpus of reference constructed by domain experts of the medical field and further evaluate the impact of ontology evolution on the used semantic similarity measures. Keywords: Similarity measures · Ontology evolution · Semantic Web · Medical terminologies 1 Introduction Measuring the similarity between terms is at the heart of many research inves- tigations. In ontology matching, similarity measures are used to evaluate the relatedness between concepts from different ontologies [9]. The outcomes are the mappings between the ontologies, increasing the coverage of domain knowledge and optimize semantic interoperability between information systems. In informa- tion retrieval, similarity measures are used to evaluate the relatedness between units of language (e.g., words, sentences, documents) to optimize search [39].
    [Show full text]
  • Evaluating Lexical Similarity to Build Sentiment Similarity
    Evaluating Lexical Similarity to Build Sentiment Similarity Grégoire Jadi∗, Vincent Claveauy, Béatrice Daille∗, Laura Monceaux-Cachard∗ ∗ LINA - Univ. Nantes {gregoire.jadi beatrice.daille laura.monceaux}@univ-nantes.fr y IRISA–CNRS, France [email protected] Abstract In this article, we propose to evaluate the lexical similarity information provided by word representations against several opinion resources using traditional Information Retrieval tools. Word representation have been used to build and to extend opinion resources such as lexicon, and ontology and their performance have been evaluated on sentiment analysis tasks. We question this method by measuring the correlation between the sentiment proximity provided by opinion resources and the semantic similarity provided by word representations using different correlation coefficients. We also compare the neighbors found in word representations and list of similar opinion words. Our results show that the proximity of words in state-of-the-art word representations is not very effective to build sentiment similarity. Keywords: opinion lexicon evaluation, sentiment analysis, spectral representation, word embedding 1. Introduction tend or build sentiment lexicons. For example, (Toh and The goal of opinion mining or sentiment analysis is to iden- Wang, 2014) uses the syntactic categories from WordNet tify and classify texts according to the opinion, sentiment or as features for a CRF to extract aspects and WordNet re- emotion that they convey. It requires a good knowledge of lations such as antonymy and synonymy to extend an ex- the sentiment properties of each word. This properties can isting opinion lexicons. Similarly, (Agarwal et al., 2011) be either discovered automatically by machine learning al- look for synonyms in WordNet to find the polarity of words gorithms, or embedded into language resources.
    [Show full text]
  • Using Prior Knowledge to Guide BERT's Attention in Semantic
    Using Prior Knowledge to Guide BERT’s Attention in Semantic Textual Matching Tasks Tingyu Xia Yue Wang School of Artificial Intelligence, Jilin University School of Information and Library Science Key Laboratory of Symbolic Computation and Knowledge University of North Carolina at Chapel Hill Engineering, Jilin University [email protected] [email protected] Yuan Tian∗ Yi Chang∗ School of Artificial Intelligence, Jilin University School of Artificial Intelligence, Jilin University Key Laboratory of Symbolic Computation and Knowledge International Center of Future Science, Jilin University Engineering, Jilin University Key Laboratory of Symbolic Computation and Knowledge [email protected] Engineering, Jilin University [email protected] ABSTRACT 1 INTRODUCTION We study the problem of incorporating prior knowledge into a deep Measuring semantic similarity between two pieces of text is a fun- Transformer-based model, i.e., Bidirectional Encoder Representa- damental and important task in natural language understanding. tions from Transformers (BERT), to enhance its performance on Early works on this task often leverage knowledge resources such semantic textual matching tasks. By probing and analyzing what as WordNet [28] and UMLS [2] as these resources contain well- BERT has already known when solving this task, we obtain better defined types and relations between words and concepts. Recent understanding of what task-specific knowledge BERT needs the works have shown that deep learning models are more effective most and where it is most needed. The analysis further motivates on this task by learning linguistic knowledge from large-scale text us to take a different approach than most existing works. Instead of data and representing text (words and sentences) as continuous using prior knowledge to create a new training task for fine-tuning trainable embedding vectors [10, 17].
    [Show full text]
  • Latent Semantic Analysis for Text-Based Research
    Behavior Research Methods, Instruments, & Computers 1996, 28 (2), 197-202 ANALYSIS OF SEMANTIC AND CLINICAL DATA Chaired by Matthew S. McGlone, Lafayette College Latent semantic analysis for text-based research PETER W. FOLTZ New Mexico State University, Las Cruces, New Mexico Latent semantic analysis (LSA) is a statistical model of word usage that permits comparisons of se­ mantic similarity between pieces of textual information. This papersummarizes three experiments that illustrate how LSA may be used in text-based research. Two experiments describe methods for ana­ lyzinga subject's essay for determining from what text a subject learned the information and for grad­ ing the quality of information cited in the essay. The third experiment describes using LSAto measure the coherence and comprehensibility of texts. One of the primary goals in text-comprehension re­ A theoretical approach to studying text comprehen­ search is to understand what factors influence a reader's sion has been to develop cognitive models ofthe reader's ability to extract and retain information from textual ma­ representation ofthe text (e.g., Kintsch, 1988; van Dijk terial. The typical approach in text-comprehension re­ & Kintsch, 1983). In such a model, semantic information search is to have subjects read textual material and then from both the text and the reader's summary are repre­ have them produce some form of summary, such as an­ sented as sets ofsemantic components called propositions. swering questions or writing an essay. This summary per­ Typically, each clause in a text is represented by a single mits the experimenter to determine what information the proposition.
    [Show full text]
  • Ying Liu, Xi Yang
    Liu, Y. & Yang, X. (2018). A similar legal case retrieval Liu & Yang system by multiple speech question and answer. In Proceedings of The 18th International Conference on Electronic Business (pp. 72-81). ICEB, Guilin, China, December 2-6. A Similar Legal Case Retrieval System by Multiple Speech Question and Answer (Full paper) Ying Liu, School of Computer Science and Information Engineering, Guangxi Normal University, China, [email protected] Xi Yang*, School of Computer Science and Information Engineering, Guangxi Normal University, China, [email protected] ABSTRACT In real life, on the one hand people often lack legal knowledge and legal awareness; on the other hand lawyers are busy, time- consuming, and expensive. As a result, a series of legal consultation problems cannot be properly handled. Although some legal robots can answer some problems about basic legal knowledge that are matched by keywords, they cannot do similar case retrieval and sentencing prediction according to the criminal facts described in natural language. To overcome the difficulty, we propose a similar case retrieval system based on natural language understanding. The system uses online speech synthesis of IFLYTEK and speech reading and writing technology, integrates natural language semantic processing technology and multiple rounds of question-and-answer dialogue mechanism to realise the legal knowledge question and answer with the memory-based context processing ability, and finally retrieves a case that is most similar to the criminal facts that the user consulted. After trial use, the system has a good level of human-computer interaction and high accuracy of information retrieval, which can largely satisfy people's consulting needs for legal issues.
    [Show full text]
  • Untangling Semantic Similarity: Modeling Lexical Processing Experiments with Distributional Semantic Models
    Untangling Semantic Similarity: Modeling Lexical Processing Experiments with Distributional Semantic Models. Farhan Samir Barend Beekhuizen Suzanne Stevenson Department of Computer Science Department of Language Studies Department of Computer Science University of Toronto University of Toronto, Mississauga University of Toronto ([email protected]) ([email protected]) ([email protected]) Abstract DSMs thought to instantiate one but not the other kind of sim- Distributional semantic models (DSMs) are substantially var- ilarity have been found to explain different priming effects on ied in the types of semantic similarity that they output. Despite an aggregate level (as opposed to an item level). this high variance, the different types of similarity are often The underlying conception of semantic versus associative conflated as a monolithic concept in models of behavioural data. We apply the insight that word2vec’s representations similarity, however, has been disputed (Ettinger & Linzen, can be used for capturing both paradigmatic similarity (sub- 2016; McRae et al., 2012), as has one of the main ways in stitutability) and syntagmatic similarity (co-occurrence) to two which it is operationalized (Gunther¨ et al., 2016). In this pa- sets of experimental findings (semantic priming and the effect of semantic neighbourhood density) that have previously been per, we instead follow another distinction, based on distri- modeled with monolithic conceptions of DSM-based seman- butional properties (e.g. Schutze¨ & Pedersen, 1993), namely, tic similarity. Using paradigmatic and syntagmatic similarity that between syntagmatically related words (words that oc- based on word2vec, we show that for some tasks and types of items the two types of similarity play complementary ex- cur in each other’s near proximity, such as drink–coffee), planatory roles, whereas for others, only syntagmatic similar- and paradigmatically related words (words that can be sub- ity seems to matter.
    [Show full text]
  • Measuring Semantic Similarity of Words Using Concept Networks
    Measuring semantic similarity of words using concept networks Gabor´ Recski Eszter Iklodi´ Research Institute for Linguistics Dept of Automation and Applied Informatics Hungarian Academy of Sciences Budapest U of Technology and Economics H-1068 Budapest, Benczur´ u. 33 H-1117 Budapest, Magyar tudosok´ krt. 2 [email protected] [email protected] Katalin Pajkossy Andras´ Kornai Department of Algebra Institute for Computer Science Budapest U of Technology and Economics Hungarian Academy of Sciences H-1111 Budapest, Egry J. u. 1 H-1111 Budapest, Kende u. 13-17 [email protected] [email protected] Abstract using word embeddings and WordNet. In Sec- tion 3 we briefly introduce the 4lang resources We present a state-of-the-art algorithm and the formalism it uses for encoding the mean- for measuring the semantic similarity of ing of words as directed graphs of concepts, then word pairs using novel combinations of document our efforts to develop novel 4lang- word embeddings, WordNet, and the con- based similarity features. Besides improving the cept dictionary 4lang. We evaluate our performance of existing systems for measuring system on the SimLex-999 benchmark word similarity, the goal of the present project is to data. Our top score of 0.76 is higher than examine the potential of 4lang representations in any published system that we are aware of, representing non-trivial lexical relationships that well beyond the average inter-annotator are beyond the scope of word embeddings and agreement of 0.67, and close to the 0.78 standard linguistic ontologies. average correlation between a human rater Section 4 presents our results and pro- and the average of all other ratings, sug- vides rough error analysis.
    [Show full text]
  • Semantic Similarity Between Sentences
    International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 04 Issue: 01 | Jan -2017 www.irjet.net p-ISSN: 2395-0072 SEMANTIC SIMILARITY BETWEEN SENTENCES PANTULKAR SRAVANTHI1, DR. B. SRINIVASU2 1M.tech Scholar Dept. of Computer Science and Engineering, Stanley College of Engineering and Technology for Women, Telangana- Hyderabad, India 2Associate Professor - Dept. of Computer Science and Engineering, Stanley College of Engineering and Technology for Women, Telangana- Hyderabad, India ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - The task of measuring sentence similarity is [1].Sentence similarity is one of the core elements of Natural defined as determining how similar the meanings of two Language Processing (NLP) tasks such as Recognizing sentences are. Computing sentence similarity is not a trivial Textual Entailment (RTE)[2] and Paraphrase Recognition[3]. task, due to the variability of natural language - expressions. Given two sentences, the task of measuring sentence Measuring semantic similarity of sentences is closely related to similarity is defined as determining how similar the meaning semantic similarity between words. It makes a relationship of two sentences is. The higher the score, the more similar between a word and the sentence through their meanings. The the meaning of the two sentences. WordNet and similarity intention is to enhance the concepts of semantics over the measures play an important role in sentence level similarity syntactic measures that are able to categorize the pair of than document level[4]. sentences effectively. Semantic similarity plays a vital role in Natural language processing, Informational Retrieval, Text 1.1 Problem Description Mining, Q & A systems, text-related research and application area.
    [Show full text]
  • Semantic Sentence Similarity: Size Does Not Always Matter
    INTERSPEECH 2021 30 August – 3 September, 2021, Brno, Czechia Semantic sentence similarity: size does not always matter Danny Merkx, Stefan L. Frank, Mirjam Ernestus Centre for Language Studies, Radboud University, Nijmegen, The Netherlands [email protected], [email protected], [email protected] Abstract liest VGS models, used a database of around 8,000 utterances This study addresses the question whether visually [15]. Harwath and colleagues introduced the first ‘modern’ neu- grounded speech recognition (VGS) models learn to capture ral network based approach which was trained on the Flickr8k sentence semantics without access to any prior linguistic knowl- Audio Caption corpus, a corpus with 40,000 utterances [16]. edge. We produce synthetic and natural spoken versions of a This corpus was quickly followed up by Places Audio Captions well known semantic textual similarity database and show that (400,000 utterances) [17] and, most recently, by SpokenCOCO our VGS model produces embeddings that correlate well with (600,000 utterances) [14]. human semantic similarity judgements. Our results show that However, previous work on visual grounding using writ- a model trained on a small image-caption database outperforms ten captions has shown that larger databases do not always re- two models trained on much larger databases, indicating that sult in better models. In [18], we compared models trained on database size is not all that matters. We also investigate the im- the written captions of Flickr8k [19] and MSCOCO [20]. We portance of having multiple captions per image and find that showed that, although the much larger MSCOCO (600k sen- this is indeed helpful even if the total number of images is tences) achieved better performance on the training task, the lower, suggesting that paraphrasing is a valuable learning sig- model trained on the smaller Flickr database performed better nal.
    [Show full text]
  • Word Embeddings for Semantic Similarity: Comparing LDA with Word2vec
    Word embeddings for semantic similarity: comparing LDA with Word2vec Luandrie Potgieter1 and Alta de Waal12 1 Department of Statistics, University of Pretoria 2 Center for Artificial Intelligence Research (CAIR) 1 Introduction Distributional semantics is a subfield in Natural Language Processing (NLP) that studies methods to derive meaning, and semantic representations for text. These representations can be thought of as statistical distributions of words assuming that it characterises semantic behaviour. These statistical distributions are often referred to as embeddings, or lower dimensional representations of the text. The two main categories of embeddings are count-based and prediction-based methods. Count-based methods most often result in global word embeddings as it utilizes the frequency of words in documents. Prediction-based embeddings on the other hand are often referred to as local embeddings as it takes into account a window of words adjacent to the word of interest. Once a corpus is represented by its semantic distribution (which is in a vector space), all kinds of similarity measures can be applied. This again leads to other NLP applications such as collaborative filtering, aspect-based sentiment analysis, intent classification for chatbots and machine translation. In this research, we investigate the appropriateness of Latent Dirichlet Allo- cation (LDA) [1] and word2vec [4] embeddings as semantic representations of a corpus. Once the semantic representation of a corpus is obtained, the distances between the documents and query documents are obtained by means of dis- tance measures such as cosine, Euclidean or Jensen-Shannon. We expect short distances between documents with similar semantic representations and longer distances between documents with different semantic representations.
    [Show full text]
  • Event-Based Knowledge Reconciliation Using Frame Embeddings And
    Knowledge-Based Systems 135 (2017) 192–203 Contents lists available at ScienceDirect Knowle dge-Base d Systems journal homepage: www.elsevier.com/locate/knosys Event-base d knowle dge reconciliation using frame emb e ddings and frame similarity ∗ Mehwish Alam a, Diego Reforgiato Recupero b,d, , Misael Mongiovi c, Aldo Gangemi a,d, Petar Ristoski e a Université Paris 13, 99 avenue JB Clément, Villetaneuse, Paris 93430, France b Università degli Studi di Cagliari, Department of Mathematics and Computer Science, Via Ospedale 72, Cagliari 09124, Italy c CNR, ISTC, Catania, Italy d CNR, ISTC, Via S. Martino della Battaglia 44, Rome, Italy e University of Mannheim, Mannheim, Germany a r t i c l e i n f o a b s t r a c t Article history: This paper proposes an evolution over MERGILO, a tool for reconciling knowledge graphs extracted from Received 6 April 2017 text, using graph alignment and word similarity. The reconciled knowledge graphs are typically used Revised 9 August 2017 for multi-document summarization, or to detect knowledge evolution across document series. The main Accepted 14 August 2017 point of improvement focuses on event reconciliation i.e., reconciling knowledge graphs generated by text Available online 16 August 2017 about two similar events described differently. In order to gather a complete semantic representation of Keywords: events, we use FRED semantic web machine reader, jointly with Framester, a linguistic linked data hub Knowledge reconciliation represented using a novel formal semantics for frames. Framester is used to enhance the extracted event Frame semantics knowledge with semantic frames.
    [Show full text]
  • Mathlingbudapest: Concept Networks for Semantic Similarity
    MathLingBudapest: Concept Networks for Semantic Similarity Gabor´ Recski Judit Acs´ Research Institute for Linguistics HAS Research Institute for Linguistics and Hungarian Academy of Sciences Dept. of Automation and Applied Informatics Benczur´ u. 33 Budapest U of Technology and Economics 1068 Budapest, Hungary Magyar tudosok´ krt. 2 (Bldg. Q.) [email protected] 1117 Budapest, Hungary [email protected] Abstract on Semeval Task 2a (Semantic Textual Similarity for English). All components of our system are We present our approach to measuring seman- available for download under an MIT license from tic similarity of sentence pairs used in Se- GitHub12. Section 2 describes the system architec- meval 2015 tasks 1 and 2. We adopt the ture and points out the main differences between our sentence alignment framework of (Han et al., system and that in (Han et al., 2013), section 3 out- 2013) and experiment with several measures of word similarity. We hybridize the common lines our word similarity metric derived from the vector-based models with definition graphs 4lang concept lexicon. We present the evaluation from the 4lang concept dictionary and de- of our systems on both tasks in section 4, and section vise a measure of graph similarity that yields 5 provides a brief conclusion. good results on training data. We did not ad- dress the specific challenges posed by Twitter 2 Architecture data, and this is reflected in placing 11th from 30 in Task 1, but our systems perform fairly Our framework for determining the semantic simi- well on the generic datasets of Task 2, with the larity of two sentences is based on the system pre- hybrid approach placing 11th among 78 runs.
    [Show full text]