DOCSLIB.ORG

Context-Aware Frame-Semantic Role Labeling

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Context-Aware Frame-Semantic Role Labeling Context-aware Frame-Semantic Role Labeling Michael Roth and Mirella Lapata School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB mroth,mlap @inf.ed.ac.uk { } Abstract including question answering (Shen and Lapata, 2007), text-to-scene generation (Coyne et al., 2012), Frame semantic representations have been stock price prediction (Xie et al., 2013), and so- useful in several applications ranging from cial network extraction (Agarwal et al., 2014). text-to-scene generation, to question answer- Whereas some tasks directly utilize information ing and social network analysis. Predicting encoded in the FrameNet resource, others make such representations from raw text is, how- ever, a challenging task and corresponding use of FrameNet indirectly through the output of models are typically only trained on a small SRL systems that are trained on data annotated set of sentence-level annotations. In this pa- with frame-semantic representations. While ad- per, we present a semantic role labeling sys- vances in machine learning have recently given tem that takes into account sentence and dis- rise to increasingly powerful SRL systems follow- course context. We introduce several new fea- ing the FrameNet paradigm (Hermann et al., 2014; tures which we motivate based on linguistic Tackstr¨ om¨ et al., 2015), little effort has been devoted insights and experimentally demonstrate that they lead to significant improvements over the to improve such models from a linguistic perspec- current state-of-the-art in FrameNet-based se- tive. mantic role labeling. In this paper, we explore insights from the lin- guistic literature suggesting a connection between 1 Introduction discourse and role labeling decisions and show how to incorporate these in an SRL system. Although The goal of semantic role labeling (SRL) is to iden- early theoretical work (Fillmore, 1976) has recog- tify and label the arguments of semantic predicates nized the importance of discourse context for the in a sentence according to a set of predefined re- assignment of semantic roles, most computational lations (e.g., “who” did “what” to “whom”). In approaches have shied away from such considera- addition to providing definitions and examples of tions. To see how context can be useful, consider as role labeled text, resources like FrameNet (Ruppen- an example the DELIVERY frame, which states that hofer et al., 2010) group semantic predicates into so- a THEME can be handed off to either a RECIPIENT called frames, i.e., conceptual structures describing or “more indirectly” to a GOAL. While the distinc- the background knowledge necessary to understand tion between the latter two roles might be clear for a situation, event or entity as a whole as well as some fillers (e.g., people vs. locations), there are oth- the roles participating in it. Accordingly, semantic ers where both roles are equally plausible and addi- roles are defined on a per-frame basis and are shared tional information is required to resolve the ambigu- among predicates. ity (e.g., countries). If we hear about a letter being In recent years, frame representations have been delivered to Greece, for instance, reliable cues might successfully applied in a range of downstream tasks, be whether the sender is a person or a country and 449 Transactions of the Association for Computational Linguistics, vol. 3, pp. 449–460, 2015. Action Editor: Diana McCarthy. Submission batch: 5/2015; Revision batch 7/2015; Published 8/2015. c 2015 Association for Computational Linguistics. Distributed under a CC-BY 4.0 license. Downloaded from http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00150 by guest on 23 September 2021 whether Greece refers to the geographic region or to (Roth and Woodsend, 2014; Lei et al., 2015; Foland the Greek government. and Martin, 2015) explore ways of using low-rank The example shows that context can generally in- vector and tensor approximations to represent lex- fluence the choice of correct role label. Accordingly, ical and syntactic features as well as combinations we assume that modeling contextual information, thereof. such as the meaning of a word in a given situation, To the best of our knowledge, there exists no can improve semantic role labeling performance. To prior work where features based on discourse con- validate this assumption, we explore different ways text are used to assign roles on the sentence level. of incorporating contextual cues in a SRL model and Discourse-like features have been previously ap- provide experimental support that demonstrates the plied in models that deal with so-called implicit ar- usefulness of such additional information. guments, i.e., roles which are not locally realized The remainder of this paper is structured as fol- but resolvable within the greater discourse context lows. In Section 2, we present related work on se- (Ruppenhofer et al., 2010; Gerber and Chai, 2012). mantic role labeling and the various features applied Successful features for resolving implicit arguments in traditional SRL systems. In Section 3, we provide include the distance between mentions and any dis- additional background on the FrameNet resource. course relations occurring between them (Gerber Sections 4 and 5 describe our baseline system and and Chai, 2012), roles assigned to mentions in the contextual extensions, respectively, and Section 6 previous context, the discourse prominence of the presents our experimental results. We conclude the denoted entity (Silberer and Frank, 2012), and its paper by discussing in more detail the output of our centering status (Laparra and Rigau, 2013). None system and highlighting avenues for future work. of these features have been used in a standard SRL system to date (and trivially, not all of them will be 2 Related Work helpful as, for example, the number of sentences be- tween a predicate and an argument is always zero Early work in SRL dates back to Gildea and Juraf- within a sentence). In this paper, we extend the sky (2002), who were the first to model role assign- contextual features used for resolving implicit ar- ment to verb arguments based on FrameNet. Their guments to the SRL task and show how a set of model makes use of lexical and syntactic features, discourse-level enhancements can be added to a tra- including binary indicators for the words involved, ditional sentence-level SRL model. syntactic categories, dependency paths as well as po- sition and voice in a given sentence. Most subse- 3 FrameNet quent work in SRL builds on Gildea and Jurafsky’s feature set, often with the addition of features that The Berkeley FrameNet project (Ruppenhofer et al., describe relevant syntactic structures in more de- 2010) develops a semantic lexicon and an annotated tail, e.g., the argument’s leftmost/rightmost depen- example corpus based on Fillmore’s (1976) theory dent (Johansson and Nugues, 2008). of frame semantics. Annotations consist of frame- More sophisticated features include the use of evoking elements (i.e., words in a sentence that are convolution kernels (Moschitti, 2004; Croce et associated with a conceptual frame) and frame ele- al., 2011) in order to represent predicate-argument ments (i.e., instantiations of semantic roles, which structures and their lexical similarities more accu- are defined per frame and filled by words or word rately. Beyond lexical and syntactic information, sequences in a given sentence). For example, the a few approaches employ additional semantic fea- DELIVERY frame describes a scene or situation in tures based on annotated word senses (Che et al., which a DELIVERER hands off a THEME to a RE- 2010) and selectional preferences (Zapirain et al., CIPIENT or a GOAL.1 In total, there are 1,019 2013). Deschacht and Moens (2009) and Huang frames and 8,886 frame elements defined in the lat- and Yates (2010) use sentence-internal sequence in- formation, in the form of latent states in a hidden 1See https://framenet2.icsi.berkeley.edu/ markov model. More recently, a few approaches for a comprehensive list of frames and their definitions. 450 Downloaded from http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00150 by guest on 23 September 2021 est publicly available version of FrameNet.2 An av- roles and implement I/O methods to read and gen- erage number of 11.6 different frame-evoking ele- erate FrameNet XML files. For direct compari- ments are provided for each frame (11,829 in total). son with the previous state-of-the-art for FrameNet- Following previous work on FrameNet-based SRL, based SRL, we further implement additional fea- we use the full text annotation data set, which con- tures used in the SEMAFOR system (Das et tains 23,087 frame instances. al., 2014) and combine the role labeling compo- Semantic annotations for frame instances and nents of mate-tools with SEMAFOR’s preprocess- fillers of frame elements are generally provided at ing toolchain.3 All features used in our system are the level of word sequences, which can be single listed in Table 1. words, complete or incomplete phrases, and entire The main differences between our adaptation of clauses (Ruppenhofer et al., 2010, Chapter 4). An mate-tools and SEMAFOR are as follows: whereas instance of the DELIVERY frame, with annotations the latter implements identification and labeling of of the frame-evoking element (underlined) and in- role fillers in one step, mate-tools follow the in- stantiated frame elements (in brackets), is given in sight that these two steps are conceptually differ- the example below: ent (Xue and Palmer, 2004) and should be modeled separately. Accordingly, mate-tools contain a global (1) The Soviet Union agreed to speed up [oil]THEME reranking component which takes into account iden- deliveriesDELIVERY [to Yugoslavia]RECIPIENT. tification and labeling decisions while SEMAFOR only uses reranking techniques to filter overlapping Note that the oil deliveries here concern Yugoslavia argument predictions and other constraints (see Das as a geopolitical entity and hence the RECIPIENT et al., 2014 for details).
Load more

Recommended publications
  • Classifying Relevant Social Media Posts During Disasters Using Ensemble of Domain-Agnostic and Domain-Specific Word Embeddings
    AAAI 2019 Fall Symposium Series: AI for Social Good 1 Classifying Relevant Social Media Posts During Disasters Using Ensemble of Domain-agnostic and Domain-specific Word Embeddings Ganesh Nalluru, Rahul Pandey, Hemant Purohit Volgenau School of Engineering, George Mason University Fairfax, VA, 22030 fgn, rpandey4, [email protected] Abstract to provide relevant intelligence inputs to the decision-makers (Hughes and Palen 2012). However, due to the burstiness of The use of social media as a means of communication has the incoming stream of social media data during the time of significantly increased over recent years. There is a plethora of information flow over the different topics of discussion, emergencies, it is really hard to filter relevant information which is widespread across different domains. The ease of given the limited number of emergency service personnel information sharing has increased noisy data being induced (Castillo 2016). Therefore, there is a need to automatically along with the relevant data stream. Finding such relevant filter out relevant posts from the pile of noisy data coming data is important, especially when we are dealing with a time- from the unconventional information channel of social media critical domain like disasters. It is also more important to filter in a real-time setting. the relevant data in a real-time setting to timely process and Our contribution: We provide a generalizable classification leverage the information for decision support. framework to classify relevant social media posts for emer- However, the short text and sometimes ungrammatical nature gency services. We introduce the framework in the Method of social media data challenge the extraction of contextual section, including the description of domain-agnostic and information cues, which could help differentiate relevant vs.
    [Show full text]
  • Injection of Automatically Selected Dbpedia Subjects in Electronic
    Injection of Automatically Selected DBpedia Subjects in Electronic Medical Records to boost Hospitalization Prediction Raphaël Gazzotti, Catherine Faron Zucker, Fabien Gandon, Virginie Lacroix-Hugues, David Darmon To cite this version: Raphaël Gazzotti, Catherine Faron Zucker, Fabien Gandon, Virginie Lacroix-Hugues, David Darmon. Injection of Automatically Selected DBpedia Subjects in Electronic Medical Records to boost Hos- pitalization Prediction. SAC 2020 - 35th ACM/SIGAPP Symposium On Applied Computing, Mar 2020, Brno, Czech Republic. 10.1145/3341105.3373932. hal-02389918 HAL Id: hal-02389918 https://hal.archives-ouvertes.fr/hal-02389918 Submitted on 16 Dec 2019 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. Injection of Automatically Selected DBpedia Subjects in Electronic Medical Records to boost Hospitalization Prediction Raphaël Gazzotti Catherine Faron-Zucker Fabien Gandon Université Côte d’Azur, Inria, CNRS, Université Côte d’Azur, Inria, CNRS, Inria, Université Côte d’Azur, CNRS, I3S, Sophia-Antipolis, France I3S, Sophia-Antipolis, France
    [Show full text]
  • Semantic Role Labeling 2
    Semantic Role Labeling 2 Outline • Semantic role theory • Designing semantic role annotation project ▫ Granularity ▫ Pros and cons of different role schemas ▫ Multi-word expressions 3 Outline • Semantic role theory • Designing semantic role annotation project ▫ Granularity ▫ Pros and cons of different role schemas ▫ Multi-word expressions 4 Semantic role theory • Predicates tie the components of a sentence together • Call these components arguments • [John] opened [the door]. 5 Discovering meaning • Syntax only gets you so far in answering “Who did what to whom?” John opened the door. Syntax: NPSUB V NPOBJ The door opened. Syntax: NPSUB V 6 Discovering meaning • Syntax only gets you so far in answering “Who did what to whom?” John opened the door. Syntax: NPSUB V NPOBJ Semantic roles: Opener REL thing opened The door opened. Syntax: NPSUB V Semantic roles: thing opened REL 7 Can the lexicon account for this? • Is there a different sense of open for each combination of roles and syntax? • Open 1: to cause something to become open • Open 2: become open • Are these all the senses we would need? (1) John opened the door with a crowbar. Open1? (2) They tried the tools in John’s workshop one after the other, and finally the crowbar opened the door. Still Open1? 8 Fillmore’s deep cases • Correspondence between syntactic case and semantic role that participant plays • “Deep cases”: Agentive, Objective, Dative, Instrument, Locative, Factitive • Loosely associated with syntactic cases; transformations result in the final surface case 9 The door opened. Syntax: NPSUB V Semantic roles: Objective REL John opened the door. Syntax: NPSUB V NPOBJ Semantic roles: Agentive REL Objective The crowbar opened the door.
    [Show full text]
  • Information Extraction Based on Named Entity for Tourism Corpus
    Information Extraction based on Named Entity for Tourism Corpus Chantana Chantrapornchai Aphisit Tunsakul Dept. of Computer Engineering Dept. of Computer Engineering Faculty of Engineering Faculty of Engineering Kasetsart University Kasetsart University Bangkok, Thailand Bangkok, Thailand [email protected] [email protected] Abstract— Tourism information is scattered around nowa- The ontology is extracted based on HTML web structure, days. To search for the information, it is usually time consuming and the corpus is based on WordNet. For these approaches, to browse through the results from search engine, select and the time consuming process is the annotation which is to view the details of each accommodation. In this paper, we present a methodology to extract particular information from annotate the type of name entity. In this paper, we target at full text returned from the search engine to facilitate the users. the tourism domain, and aim to extract particular information Then, the users can specifically look to the desired relevant helping for ontology data acquisition. information. The approach can be used for the same task in We present the framework for the given named entity ex- other domains. The main steps are 1) building training data traction. Starting from the web information scraping process, and 2) building recognition model. First, the tourism data is gathered and the vocabularies are built. The raw corpus is used the data are selected based on the HTML tag for corpus to train for creating vocabulary embedding. Also, it is used building. The data is used for model creation for automatic for creating annotated data.
    [Show full text]
  • ACL 2019 Social Media Mining for Health Applications (#SMM4H)
    ACL 2019 Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task Proceedings of the Fourth Workshop August 2, 2019 Florence, Italy c 2019 The Association for Computational Linguistics Order copies of this and other ACL proceedings from: Association for Computational Linguistics (ACL) 209 N. Eighth Street Stroudsburg, PA 18360 USA Tel: +1-570-476-8006 Fax: +1-570-476-0860 [email protected] ISBN 978-1-950737-46-8 ii Preface Welcome to the 4th Social Media Mining for Health Applications Workshop and Shared Task - #SMM4H 2019. The total number of users of social media continues to grow worldwide, resulting in the generation of vast amounts of data. Popular social networking sites such as Facebook, Twitter and Instagram dominate this sphere. According to estimates, 500 million tweets and 4.3 billion Facebook messages are posted every day 1. The latest Pew Research Report 2, nearly half of adults worldwide and two- thirds of all American adults (65%) use social networking. The report states that of the total users, 26% have discussed health information, and, of those, 30% changed behavior based on this information and 42% discussed current medical conditions. Advances in automated data processing, machine learning and NLP present the possibility of utilizing this massive data source for biomedical and public health applications, if researchers address the methodological challenges unique to this media. In its fourth iteration, the #SMM4H workshop takes place in Florence, Italy, on August 2, 2019, and is co-located with the
    [Show full text]
  • A Second Look at Word Embeddings W4705: Natural Language Processing
    A second look at word embeddings W4705: Natural Language Processing Fei-Tzin Lee October 23, 2019 Fei-Tzin Lee Word embeddings October 23, 2019 1 / 39 Overview Last time... • Distributional representations (SVD) • word2vec • Analogy performance Fei-Tzin Lee Word embeddings October 23, 2019 2 / 39 Overview This time • Homework-related topics • Non-homework topics Fei-Tzin Lee Word embeddings October 23, 2019 3 / 39 Overview Outline 1 GloVe 2 How good are our embeddings? 3 The math behind the models? 4 Word embeddings, new and improved Fei-Tzin Lee Word embeddings October 23, 2019 4 / 39 GloVe Outline 1 GloVe 2 How good are our embeddings? 3 The math behind the models? 4 Word embeddings, new and improved Fei-Tzin Lee Word embeddings October 23, 2019 5 / 39 GloVe A recap of GloVe Our motivation: • SVD places too much emphasis on unimportant matrix entries • word2vec never gets to look at global co-occurrence statistics Can we create a new model that balances the strengths of both of these to better express linear structure? Fei-Tzin Lee Word embeddings October 23, 2019 6 / 39 GloVe Setting We'll use more or less the same setting as in previous models: • A corpus D • A word vocabulary V from which both target and context words are drawn • A co-occurrence matrix Mij , from which we can calculate conditional probabilities Pij = Mij =Mi Fei-Tzin Lee Word embeddings October 23, 2019 7 / 39 GloVe The GloVe objective, in overview Idea: we want to capture not individual probabilities of co-occurrence, but ratios of co-occurrence probability between pairs (wi ; wk ) and (wj ; wk ).
    [Show full text]
  • Cw2vec: Learning Chinese Word Embeddings with Stroke N-Gram Information
    The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information Shaosheng Cao,1,2 Wei Lu,2 Jun Zhou,1 Xiaolong Li1 1 AI Department, Ant Financial Services Group 2 Singapore University of Technology and Design {shaosheng.css, jun.zhoujun, xl.li}@antfin.com [email protected] Abstract We propose cw2vec, a novel method for learning Chinese word embeddings. It is based on our observation that ex- ploiting stroke-level information is crucial for improving the learning of Chinese word embeddings. Specifically, we de- sign a minimalist approach to exploit such features, by us- ing stroke n-grams, which capture semantic and morpholog- ical level information of Chinese words. Through qualita- tive analysis, we demonstrate that our model is able to ex- Figure 1: Radical v.s. components v.s. stroke n-gram tract semantic information that cannot be captured by exist- ing methods. Empirical results on the word similarity, word analogy, text classification and named entity recognition tasks show that the proposed approach consistently outperforms Bojanowski et al. 2016; Cao and Lu 2017). While these ap- state-of-the-art approaches such as word-based word2vec and proaches were shown effective, they largely focused on Eu- GloVe, character-based CWE, component-based JWE and ropean languages such as English, Spanish and German that pixel-based GWE. employ the Latin script in their writing system. Therefore the methods developed are not directly applicable to lan- guages such as Chinese that employ a completely different 1. Introduction writing system. Word representation learning has recently received a sig- In Chinese, each word typically consists of less charac- nificant amount of attention in the field of natural lan- ters than English1, where each character conveys fruitful se- guage processing (NLP).
    [Show full text]
  • Effects of Pre-Trained Word Embeddings on Text-Based Deception Detection
    2020 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress Effects of Pre-trained Word Embeddings on Text-based Deception Detection David Nam, Jerin Yasmin, Farhana Zulkernine School of Computing Queen’s University Kingston, Canada Email: {david.nam, jerin.yasmin, farhana.zulkernine}@queensu.ca Abstract—With e-commerce transforming the way in which be wary of any deception that the reviews might present. individuals and businesses conduct trades, online reviews have Deception can be defined as a dishonest or illegal method become a great source of information among consumers. With in which misleading information is intentionally conveyed 93% of shoppers relying on online reviews to make their purchasing decisions, the credibility of reviews should be to others for a specific gain [2]. strongly considered. While detecting deceptive text has proven Companies or certain individuals may attempt to deceive to be a challenge for humans to detect, it has been shown consumers for various reasons to influence their decisions that machines can be better at distinguishing between truthful about purchasing a product or a service. While the motives and deceptive online information by applying pattern analysis for deception may be hard to determine, it is clear why on a large amount of data. In this work, we look at the use of several popular pre-trained word embeddings (Word2Vec, businesses may have a vested interest in producing deceptive GloVe, fastText) with deep neural network models (CNN, reviews about their products.
    [Show full text]
  • Syntax Role for Neural Semantic Role Labeling
    Syntax Role for Neural Semantic Role Labeling Zuchao Li Hai Zhao∗ Shanghai Jiao Tong University Shanghai Jiao Tong University Department of Computer Science and Department of Computer Science and Engineering Engineering [email protected] [email protected] Shexia He Jiaxun Cai Shanghai Jiao Tong University Shanghai Jiao Tong University Department of Computer Science and Department of Computer Science and Engineering Engineering [email protected] [email protected] Semantic role labeling (SRL) is dedicated to recognizing the semantic predicate-argument struc- ture of a sentence. Previous studies in terms of traditional models have shown syntactic informa- tion can make remarkable contributions to SRL performance; however, the necessity of syntactic information was challenged by a few recent neural SRL studies that demonstrate impressive performance without syntactic backbones and suggest that syntax information becomes much less important for neural semantic role labeling, especially when paired with recent deep neural network and large-scale pre-trained language models. Despite this notion, the neural SRL field still lacks a systematic and full investigation on the relevance of syntactic information in SRL, for both dependency and both monolingual and multilingual settings. This paper intends to quantify the importance of syntactic information for neural SRL in the deep learning framework. We introduce three typical SRL frameworks (baselines), sequence-based, tree-based, and graph-based, which are accompanied by two categories of exploiting syntactic information: syntax pruning- based and syntax feature-based. Experiments are conducted on the CoNLL-2005, 2009, and 2012 benchmarks for all languages available, and results show that neural SRL models can still benefit from syntactic information under certain conditions.
    [Show full text]
  • Semantic Role Labeling Tutorial NAACL, June 9, 2013
    Semantic Role Labeling Tutorial NAACL, June 9, 2013 Part 1: Martha Palmer, University of Colorado Part 2: Shumin Wu, University of Colorado Part 3: Ivan Titov, Universität des Saarlandes 1 Outline } Part 1 Linguistic Background, Resources, Annotation Martha Palmer, University of Colorado } Part 2 Supervised Semantic Role Labeling and Leveraging Parallel PropBanks Shumin Wu, University of Colorado } Part 3 Semi- , unsupervised and cross-lingual approaches Ivan Titov, Universität des Saarlandes, Universteit van Amsterdam 2 Motivation: From Sentences to Propositions Who did what to whom, when, where and how? Powell met Zhu Rongji battle wrestle join debate Powell and Zhu Rongji met consult Powell met with Zhu Rongji Proposition: meet(Powell, Zhu Rongji) Powell and Zhu Rongji had a meeting meet(Somebody1, Somebody2) . When Powell met Zhu Rongji on Thursday they discussed the return of the spy plane. meet(Powell, Zhu) discuss([Powell, Zhu], return(X, plane)) Capturing semantic roles SUBJ } Dan broke [ the laser pointer.] SUBJ } [ The windows] were broken by the hurricane. SUBJ } [ The vase] broke into pieces when it toppled over. PropBank - A TreeBanked Sentence (S (NP-SBJ Analysts) S (VP have (VP been VP (VP expecting (NP (NP a GM-Jaguar pact) have VP (SBAR (WHNP-1 that) (S (NP-SBJ *T*-1) NP-SBJ been VP (VP would Analysts (VP give expectingNP (NP the U.S. car maker) SBAR (NP (NP an eventual (ADJP 30 %) stake) NP S (PP-LOC in (NP the British company)))))))))))) a GM-Jaguar WHNP-1 VP pact that NP-SBJ VP *T*-1 would NP give Analysts have been expecting a GM-Jaguar NP PP-LOC pact that would give the U.S.
    [Show full text]
  • Semantic Role Labeling: an Introduction to the Special Issue
    Semantic Role Labeling: An Introduction to the Special Issue Llu´ıs Marquez` ∗ Universitat Politecnica` de Catalunya Xavier Carreras∗∗ Massachusetts Institute of Technology Kenneth C. Litkowski† CL Research Suzanne Stevenson‡ University of Toronto Semantic role labeling, the computational identification and labeling of arguments in text, has become a leading task in computational linguistics today. Although the issues for this task have been studied for decades, the availability of large resources and the development of statistical machine learning methods have heightened the amount of effort in this field. This special issue presents selected and representative work in the field. This overview describes linguistic background of the problem, the movement from linguistic theories to computational practice, the major resources that are being used, an overview of steps taken in computational systems, and a description of the key issues and results in semantic role labeling (as revealed in several international evaluations). We assess weaknesses in semantic role labeling and identify important challenges facing the field. Overall, the opportunities and the potential for useful further research in semantic role labeling are considerable. 1. Introduction The sentence-level semantic analysis of text is concerned with the characterization of events, such as determining “who” did “what” to “whom,” “where,” “when,” and “how.” The predicate of a clause (typically a verb) establishes “what” took place, and other sentence constituents express the participants in the event (such as “who” and “where”), as well as further event properties (such as “when” and “how”). The primary task of semantic role labeling (SRL) is to indicate exactly what semantic relations hold among a predicate and its associated participants and properties, with these relations Departament de Llenguatges i Sistemes Informatics,` Universitat Politecnica` de Catalunya, Jordi Girona ∗ Salgado 1–3, 08034 Barcelona, Spain.
    [Show full text]
  • Efficient Pairwise Document Similarity Computation in Big Datasets
    International Journal of Database Theory and Application Vol.8, No.4 (2015), pp.59-70 http://dx.doi.org/10.14257/ijdta.2015.8.4.07 Efficient Pairwise Document Similarity Computation in Big Datasets 1Papias Niyigena, 1Zhang Zuping*, 2Weiqi Li and 1Jun Long 1School of Information Science and Engineering, Central South University, Changsha, 410083, China 2School of Electronic and Information Engineering, Xi’an Jiaotong University Xian, 710049, China [email protected], * [email protected], [email protected], [email protected] Abstract Document similarity is a common task to a variety of problems such as clustering, unsupervised learning and text retrieval. It has been seen that document with the very similar content provides little or no new information to the user. This work tackles this problem focusing on detecting near duplicates documents in large corpora. In this paper, we are presenting a new method to compute pairwise document similarity in a corpus which will reduce the time execution and save space execution resources. Our method group shingles of all documents of a corpus in a relation, with an advantage of efficiently manage up to millions of records and ease counting and aggregating. Three algorithms are introduced to reduce the candidates shingles to be compared: one creates the relation of shingles to be considered, the second one creates the set of triples and the third one gives the similarity of documents by efficiently counting the shared shingles between documents. The experiment results show that our method reduces the number of candidates pairs to be compared from which reduce also the execution time and space compared with existing algorithms which consider the computation of all pairs candidates.
    [Show full text]