CCG Parsers 2017


Notes:

  • Data-driven parsing
  • Generative CCG parsing
  • Treebanking
  • Unsupervised tagging

Resources:

  • ccgbank .. translation of the penn treebank into a corpus of ccg derivations
  • software .. incomplete list of links to ccg software

Wikipedia:

References:

See also:

CCG Parsers 2014 | Combinatory Categorial Grammar & Natural Language GenerationOpenCCG (OpenNLP CCG Library)


The parallel meaning bank: Towards a multilingual corpus of translations annotated with compositional meaning representations
L Abzianidze, J Bjerva, K Evang, H Haagsma… – arXiv preprint arXiv …, 2017 – arxiv.org
… from source to target sentence more convenient (see Section 4). The version of CCG that we employ differs from standard CCG: in order to facilitate the cross- lingual projection process and retain composition- ality, type-changing rules of a CCG parser are explicated by …

Learning to Parse Natural Language to Grounded Reward Functions with Weak Supervision
EC Williams, M Rhee, N Gopalan, S Tellex – AAAI Fall Symposium on …, 2017 – ttic.edu
… our semantic representation. Related Work Zettlemoyer and Collins (2005) presented a supervised method to learn CCG parsers given natural language an- notated with lambda-calculus logical forms. Krishnamurthy and Mitchell …

Neural amr: Sequence-to-sequence models for parsing and generation
I Konstas, S Iyer, M Yatskar, Y Choi… – arXiv preprint arXiv …, 2017 – arxiv.org
… All other models that we compare against use se- mantic resources, such as WordNet, dependency parsers or CCG parsers (models marked with * were trained with less data, but only evaluate on newswire text; the rest evaluate on the full test set, containing text from blogs) …

Semantic parsing of pre-university math problems
T Matsuzaki, T Ito, H Iwane, H Anai… – Proceedings of the 55th …, 2017 – aclweb.org
… The semantic representa- tion of each sentence is determined by a semantic parser based on Combinatory Categorial Grammar (CCG) (Steedman, 2001, 2012). The output from the CCG parser is a ranked list of sentence-level logical forms for each sentence …

Learning structured natural language representations for semantic parsing
J Cheng, S Reddy, V Saraswat, M Lapata – arXiv preprint arXiv …, 2017 – arxiv.org
Page 1. arXiv:1704.08387v1 [cs.CL] 27 Apr 2017 Learning Structured Natural Language Representations for Semantic Parsing Jianpeng Cheng† Siva Reddy† Vijay Saraswat‡ and Mirella Lapata† †School of Informatics, University …

On-demand injection of lexical knowledge for recognising textual entailment
P Martínez-Gómez, K Mineshima, Y Miyao… – Proceedings of the 15th …, 2017 – aclweb.org
… These semantic inter- pretations were composed using Boxer (Bos et al., 2004) from derivations of a Combinatory Catego- rial Grammar (CCG) (Steedman, 2000) automat- ically obtained by C&C, a wide-coverage CCG parser (Clark and Curran, 2007) …

Universal semantic parsing
S Reddy, O Täckström, S Petrov, M Steedman… – arXiv preprint arXiv …, 2017 – arxiv.org
Page 1. Universal Semantic Parsing Siva Reddy† Oscar Täckström‡ Slav Petrov‡ Mark Steedman† Mirella Lapata† †ILCC, School of Informatics, University of Edinburgh ‡ Google, Inc. siva.reddy@ed.ac.uk, 1oscart, slavl@google.com, 1steedman, mlapl@inf.ed.ac.uk Abstract …

Joint learning of ontology and semantic parser from text
J Starc, D Mladeni? – Intelligent Data Analysis, 2017 – content.iospress.com
… To overcome this limitation [18] developed a open vocabulary semantic parser. Their approach uses a CCG parser on questions to from lambda statements, which besides Freebase vocabulary contain underspecified predicates …

Initial explorations of CCG supertagging for Universal Dependency parsing
BK Akku?, H Azizoglu, R Cakici – … of the CoNLL 2017 Shared Task …, 2017 – aclweb.org
… Several fast and highly ac- curate CCG parsers have been introduced in the literature. These parsers make use of the CCG- Bank (Hockenmaier and Steedman, 2002) that is created by inducing a CCG Grammar from the Penn Treebank (Marcus et al., 1993) …

Open-Vocabulary Semantic Parsing with both Distributional Statistics and Formal Knowledge.
M Gardner, J Krishnamurthy – AAAI, 2017 – aaai.org
… ? + ?T ?) Figure 1: Overview of the components of our model. Given an input text, we use a CCG parser and an entity linker to produce a logical form with predicates derived from the text (shown in italics). For each predicate …

Prominent feature extraction for evidence gathering in question answering
LK Sharma, N Mittal – Journal of Intelligent & Fuzzy Systems, 2017 – content.iospress.com
… Open domain QA systems use wide-ranging coverage of parsers. The quickness and correctness of CCG parser suggested by [12] are used to parse answer candidates. We are mixing the parser into a QA system for evidence gathering, scoring and learning …

Tag parsing with neural networks and vector representations of supertags
J Kasai, B Frank, T McCoy, O Rambow… – Proceedings of the 2017 …, 2017 – aclweb.org
Page 1. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1712–1722 Copenhagen, Denmark, September 7–11, 2017. cO2017 Association for Computational Linguistics TAG …

Grounding proposition stores for question answering over linked data
B Cabaleiro, A Peñas, S Manandhar – Knowledge-Based Systems, 2017 – Elsevier
… GraphParser tackles this task by pairing reified logic forms derived from a Combinatory Categorial Grammar (CCG) parser [19] with Freebase properties. Each logic form corresponds in turn to a predicate-argument relation … GraphParser uses in this step a CCG parser …

Neural semantic parsing by character-based translation: Experiments with abstract meaning representations
R van Noord, J Bos – arXiv preprint arXiv:1705.09980, 2017 – arxiv.org
… Bos, Johan, Stephen Clark, Mark Steedman, James R. Curran, and Julia Hockenmaier (2004), Wide-coverage semantic representations from a ccg parser, Proceedings of the 20th International Conference on Computational Linguistics (COLING ’04), Geneva, Switzerland, pp …

LANGPRO: Natural Language Theorem Prover
L Abzianidze – arXiv preprint arXiv:1708.09417, 2017 – arxiv.org
… LangPro CCG parser LLFgen & Aligner NLog Prover p1 … pn h ? ? # trees LLFs In Out Figure 1: LangPro checks whether a set of premises p1,…,pn entails (?), contradicts (?) or is neutral (#) to a hypothesis h. of the system description …

The Impact of Word Segmentation on CCG-based Arabic-English SMT
HA Rajeh, Z LI, AG Mohammed – DEStech Transactions on …, 2017 – dpi-proceedings.com
… Despite on CCG supertags are powerfully parsable; our experiments focus on translation from Arabic into English language direction that is due to CCG parser is unavailable for Arabic as a target language despite tries by researchers, such as [10] and [11] …

A* CCG Parsing with a Supertag and Dependency Factored Model
M Yoshikawa, H Noji, Y Matsumoto – arXiv preprint arXiv:1704.06936, 2017 – arxiv.org
… One issue when applying this method for ob- taining the training data is that due to the mis- match between the rule set of our CCG parser, for which we follow Lewis and Steedman (2014), and the grammar in English CCGbank (Hockenmaier and Steedman, 2007) we cannot …

Deletion-based sentence compression using Bi-enc-dec LSTM
DV Lai, NT Son, N Le Minh – researchgate.net
… Though multi- target learning is helpful to learn higher abstract level, the additional features demand gaze data and CCG parser, hence breaks the root idea of utilizing cheap available features. 3 Models In this paper, we model the task as a sequence tagging …

TAG Parser Evaluation using Textual Entailments
P Xu, R Frank, J Kasai, O Rambow – Proceedings of the 13th …, 2017 – aclweb.org
… set. The CCG parser makes use of a number of heuristics for entailment comparison, however. Adding such heuristics to our best TAG parser yields state-of-the-art results on the test set when using accuracy as a metric. This …

Robotic simulation using natural language commands
D Thenmozhi, R Seshathiri, K Revanth… – … and Signal Processing …, 2017 – ieeexplore.ieee.org
… Evang et al. [5] used CCG parser (Combinatory Categorical Grammar) with structured perceptron for supervised semantic parsing to convert from NL commands to RCL … This approach uses only CCG parser to convert from NL to RCL …

Peking at EPE 2017: A Comparison of Tree Approximation, Transition-based and Maximum Subgraph Models for Semantic Dependency Analysis
Y Chen, J Cao, W Sun, X Wan – EPE 2017, 2017 – svn.nlpl.eu
… Stephen Clark, Julia Hockenmaier, and Mark Steed- man. 2002. Building deep dependency struc- tures using a wide-coverage CCG parser. In Pro- ceedings of the 40th Annual Meeting of the As- sociation for Computational Linguistics, July 6- 12, 2002, Philadelphia, PA, USA …

STRUCTURED LEARNING WITH INEXACT SEARCH: ADVANCES IN SHIFT-REDUCE CCG PARSING
W Xu – 2017 – repository.cam.ac.uk
… 13 Page 32. (not safe) (Hockenmaier and Bisk, 2010). Nevertheless, CCG parsers often imple- ment it, because efficiency improvement is usually considerable even when spurious ambiguity is partially alleviated. This is the choice in the first wide-coverage CCG …

Towards Formalizing Statute Law as Default Logic through Automatic Semantic Parsing
M Pertierra, S Lawsky, E Hemberg, UM O’Reilly – 2017 – groups.csail.mit.edu
… [6] Johan Bos, Stephen Clark, Mark Steedman, James R Curran, and Julia Hock- enmaier. 2004. Wide-coverage semantic representations from a CCG parser. In Proceedings of the 20th international conference on Computational Linguistics …

The 2017 Shared Task on Extrinsic Parser Evaluation Towards a Reusable Community Infrastructure
S Oepen, L Øvrelid, J Björne, R Johansson, E Lapponi… – EPE 2017, 2017 – svn.nlpl.eu
… passive sentences). The participants were then required to create their own entailment recog- nition system, a step which the parser developers solved with varying degrees of success, where the two top-performing systems for this task both em- ployed a CCG parser …

Using gaze to predict text readability
AV Gonzalez-Garduño, A Søgaard – … of the 12th Workshop on Innovative …, 2017 – aclweb.org
… Baselines Ambati et al. (2016) obtained 78.87 percent accuracy on the Wikipedia dataset. They use features extracted from a Combinatory Cate- gorical Grammar (CCG) parser … 2016. Assessing relative sentence complexity using an incremental ccg parser …

CCG Supertagging via Bidirectional LSTM-CRF Neural Architecture
R Kadari, Y Zhang, W Zhang, T Liu – Neurocomputing, 2017 – Elsevier
Sequence labeling is the widely used method for CCG supertagging task where a supertag (lexical category) is assigned to each word in an input sentence. In CCG.

The Challenge of Composition in Distributional and Formal Semantics
R Tian, K Mineshima, P Martínez-Gómez – Proceedings of the IJCNLP …, 2017 – aclweb.org
… In EMNLP. K. Mineshima, R. Tanaka, P. Mart?nez-Gómez, Y. Miyao, and D. Bekki. 2016. Building compo- sitional semantics and higher-order inference sys- tem for a wide-coverage Japanese CCG parser. In EMNLP. J. Mitchell and M. Lapata. 2010 …

Parsing natural language conversations using contextual cues
S Srivastava, A Azaria, T Mitchell – Proceedings of the 26th …, 2017 – azariaa.com
… Our baselines include the following semantic parsing models: • Unstructured CCG: CCG parser from [Azaria et al., 2016], which uses the same lexicon and text-based features from Section 4, but does not incorporate structural features • Seq2Seq: Deep neural network based on …

Learning an Executable Neural Semantic Parser
J Cheng, S Reddy, V Saraswat, M Lapata – arXiv preprint arXiv …, 2017 – arxiv.org
Page 1. arXiv:1711.05066v1 [cs.CL] 14 Nov 2017 Learning an Executable Neural Semantic Parser Jianpeng Cheng University of Edinburgh Siva Reddy Stanford University Vijay Saraswat IBM TJ Watson Research Mirella Lapata University of Edinburgh …

Psycholinguistic Models of Sentence Processing Improve Sentence Readability Ranking
DM Howcroft, V Demberg – Proceedings of the 15th Conference of the …, 2017 – aclweb.org
… informative than features extracted from a non- incremental parser. To this end, they used the incremental derivations from a combinatory cat- egorial grammar (CCG) parser. Ambati et al. ran several models on the English and Simple …

A Dynamic Window Neural Network for CCG Supertagging.
H Wu, J Zhang, C Zong – AAAI, 2017 – aaai.org
… arXiv preprint arXiv:1409.0473. Bos, J.; Clark, S.; Steedman, M.; Curran, JR; and Hock- enmaier, J. 2004. Wide-coverage semantic representations from a CCG parser. In Proceedings of the 20th international conference on Computational Linguistics, 1240 …

Determining Semantic Textual Similarity using Natural Deduction Proofs
H Yanaka, K Mineshima, P Martinez-Gomez… – arXiv preprint arXiv …, 2017 – arxiv.org
… trees. In ccg2lambda, two wide-coverage CCG parsers, C&C (Clark and Curran, 2007) and Easy- CCG (Lewis and Steedman, 2014), are used for converting tokenized sentences into CCG trees ro- bustly … Page 3. CCG parser Sentence …

A Type-Theoretical system for the FraCaS test suite: Grammatical Framework meets Coq
JP Bernardy, S Chatzikyriakidis – IWCS 2017-12th International …, 2017 – aclweb.org
… Common nouns We represent common nouns as customary in typed formal semantics, namely as pred- icates over an abstract object type: 1One could use other systems to perform parsing, eg a CCG parser would be also suitable …

AppTechMiner: Mining Applications and Techniques from Scientific Articles
S Agarwal, M Singh, S Dan, P Goyal… – arXiv preprint arXiv …, 2017 – arxiv.org
… Bleu Score, Perceptron Algorithm, Word Alignment, Stanford POS Tagger, Collins Parser, Natural Language Processing, Bleu Metric, Coreference Resolution, Moses Decoder, Giza++ Toolkit, Brill Tagger, TnT Tagger,Anaphora Resolution, MST Parser, CCG Parser, Malt Parser …

Spoken instruction-based one-shot object and action learning in a cognitive robotic architecture
M Scheutz, E Krause, B Oosterveld, T Frasca… – Proceedings of the 16th …, 2017 – dl.acm.org
… The particular parser employed in DIARC is an incremental and extended version of the Combinatory Categorial Grammar (CCG) parser from [6]. It contains a dictionary of pars- ing rules each composed of three parts: a lexical entry, a syntactic CCG definition of the semantic …

Concept Learning from Natural Language Interactions
S Srivastava – 2017 – cs.cmu.edu
… Our baselines include:(i)Unstructured CCG: Traditional CCG parser (following Zettlemoyer and Collins (2005)) which uses the same lexicon and text-based fea- tures, but does not incorporate structural features (ii) Seq2Seq: Neural network based on sequence-to-sequence …

Dual track multimodal automatic learning through human-robot interaction
S Jiang, W Min, X Li, H Wang, J Sun… – Proceedings of the 26th …, 2017 – vipl.ict.ac.cn
… max ?1,?2,…?n p(?|?) (2) After symbol grounding, we get the sentence S. We then extract the triple information from S using EasyCCG [Lewis and Steedman, 2014]. The CCG parser y of the sentence S is defined as a list of lexical categories c1,c2 …cnand a deriva- tion …

Revision of TPS with Switch Cost in Relative Keys
SH Arn – 2017 – dspace.jaist.ac.jp
… TPS and contributing to that theory. The upcoming main section will give an overview on TPS and CCG parsers for music. Page 20. 15 2.3 Implication-Realization Model … This parser focused on CCG only and featured no TPS calculations. This parser performed better than …

World Interaction Networks: Grounding Natural Language to World Updates with Minimal Supervision
S Karamcheti, E Charniak, S Tellex – siddkaramcheti.com
… Artzi and Zettlemoyer (2013) learn a weakly- supervised CCG Parser for navigational instruction follow- ing … (2017) also learn a weakly-supervised CCG Parser for instruction grounding, but with a smarter validation function, eliminating the need for explicit plan- ning …

Multiword expression-aware A* TAG parsing revisited
J Waszczuk, A Savary… – … Workshop on Tree …, 2017 – hal.archives-ouvertes.fr
… of the supertagger. Lewis and Steedman (2014) showed that it is possible to obtain a highly accurate and fast CCG parser by (i) adopting a simple probabilis- tic model factored on lexical category assign- ments and (ii) using …

Towards Universal Semantic Tagging
L Abzianidze, J Bos – arXiv preprint arXiv:1709.10381, 2017 – arxiv.org
… 301–304. Bos, J., S. Clark, M. Steedman, JR Curran, and J. Hockenmaier (2004). Wide-coverage semantic repre- sentations from a CCG parser. In Proceedings of the 20th International Conference on Computational Linguistics (COLING 2004), Geneva, Switzerland, pp …

Exploring the Syntactic Abilities of RNNs with Multi-task Learning
E Enguehard, Y Goldberg, T Linzen – arXiv preprint arXiv:1706.03542, 2017 – arxiv.org
… For example, intransitive verbs (smile), transitive verbs (build) and raising verbs (seem) all have different tags: S\NP, (S\NP)/NP and (S\NP)/(S\NP), respectively. CCG parsers typically rely on a supertagging step where each word in a sentence is associated Page 3 …

Natural language understanding and communication for human-robot collaboration
MI Bloch – ipvs.informatik.uni-stuttgart.de
… [RLS14] introduces a data driven approach for a question answering system for querying Freebase in natural language. Their semantic parser maps the output of a CCG parser to a graph-based representation which is similar to Freebase …

Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks
R Das, M Zaheer, S Reddy, A McCallum – arXiv preprint arXiv:1704.08384, 2017 – arxiv.org
… In EMNLP. Yonatan Bisk, Siva Reddy, John Blitzer, Julia Hock- enmaier, and Mark Steedman. 2016. Evaluating In- duced CCG Parsers on Grounded Semantic Parsing. In EMNLP. Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008 …

Visual Denotations for Recognizing Textual Entailment
D Han, P Martínez-Gómez, K Mineshima – Proceedings of the 2017 …, 2017 – aclweb.org
… Johan Bos, Stephen Clark, Mark Steedman, James R Curran, and Julia Hockenmaier. 2004. Wide- coverage semantic representations from a CCG parser. In Proceedings of the 20th international con- ference on Computational Linguistics, pages 104– 111 …

Syntax-Mediated Semantic Parsing
S Reddy – sivareddy.in
Page 1. Syntax-Mediated Semantic Parsing Siva Reddy T H E U NIVER S I T Y O F E DI NBU R G H Doctor of Philosophy Institute for Language, Cognition and Computation School of Informatics University of Edinburgh 2017 Page 2. Page 3. Abstract …

TTPDrill: Automatic and Accurate Extraction of Threat Actions from Unstructured Text of CTI Sources
G Husari, E Al-Shaer, M Ahmed, B Chu… – Proceedings of the 33rd …, 2017 – dl.acm.org
Page 1. TTPDrill: Automatic and Accurate Extraction of Threat Actions from Unstructured Text of CTI Sources Ghaith Husari, Ehab Al-Shaer, Mohiuddin Ahmed, Bill Chu, and Xi Niu Department of So ware and Information Systems …

Automatic assessment of absolute sentence complexity
S Štajner, SP Ponzetto, H Stuckenschmidt – Proceedings of the 26th …, 2017 – ijcai.org
… In Proceedings of YIWCALA, pages 46–53, 2010. [Ambati et al., 2016] Bharat Ram Ambati, Siva Reddy, and Mark Steedman. Assessing Relative Sentence Complex- ity using an Incremental CCG Parser. In Proceedings of NAACL-HLT, pages 1051–1057, 2016 …

Improving Shift?Reduce Phrase?Structure Parsing with Constituent Boundary Information
W Chen, M Zhu, M Zhang, Y Zhang… – Computational …, 2017 – Wiley Online Library
By continuing to browse this site you agree to us using cookies as described in About Cookies. Remove maintenance message …

Logic-based Approach to Machine Comprehension of Text
P Chabierski, A Russo, M Law – 2017 – imperial.ac.uk
Page 1. Imperial College London Department of Computing MEng Individual Project Logic-based Approach to Machine Comprehension of Text Author: Piotr Chabierski Project Supervisors: Prof. Alessandra Russo Mark Law June 19, 2017 Page 2. Page 3. Abstract …

Neural-Symbolic Learning for Semantic Parsing
C Xiao – 2017 – tel.archives-ouvertes.fr
Page 1. HAL Id: tel-01699569 https://tel.archives-ouvertes.fr/tel-01699569 Submitted on 2 Feb 2018 HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not …

Text mining for improved exposure assessment
K Larsson, S Baker, I Silins, Y Guo, U Stenius… – PloS one, 2017 – journals.plos.org
Chemical exposure assessments are based on information collected via different methods, such as biomonitoring, personal monitoring, environmental monitoring and questionnaires. The vast amount of chemical-specific exposure information available from web-based databases …

The portability of three types of text mining techniques into the patent text genre
L Andersson, A Hanbury, A Rauber – Current Challenges in Patent …, 2017 – Springer
… CFG algorithms form the basis of all approaches to create a hierarchical phrase structure [17] (see Fig. 9.4). The subcategorisation group consists of parsers that are lexicon driven, such as the combinatory categorial grammar (CCG) parser …

SUGILITE: creating multimodal smartphone automation by demonstration
TJJ Li, A Azaria, BA Myers – Proceedings of the 2017 CHI Conference …, 2017 – dl.acm.org
… API. Then LIA uses a Combinatory Categorial Grammar (CCG) parser to parse the verbal command. Based on the parsing result, LIA can initiate a new recording or execute a SUGILITE script. Details on LIA can be found in [4] …

AppLP: A Dialogue on Applications of Logic Programming
DS Warren, YA Liu – arXiv preprint arXiv:1704.02375, 2017 – arxiv.org
Page 1. arXiv:1704.02375v1 [cs.PL] 7 Apr 2017 AppLP: A Dialogue on Applications of Logic Programming David S. Warren Yanhong A. Liu Stony Brook University This document describes the contributions of the 2016 Applications …

“Show me the cup”: Reference with Continuous Representations
G Boleda Torrent, M Baroni, S Padó – 2017 – repositori.upf.edu
… Models of Semantics. Journal of Artificial Intelligence Research 37 (2010) 141–188 5. Bos, J., Clark, S., Steedman, M., Curran, JR, Hockenmaier, J.: Wide-coverage semantic representations from a CCG parser. In: Proceedings of …

Information Extraction for the Seed Development Regulatory Networks of Arabidopsis Thaliana.
D Valsamou – 2017 – tel.archives-ouvertes.fr
Page 1. HAL Id: tel-01613508 https://tel.archives-ouvertes.fr/tel-01613508 Submitted on 9 Oct 2017 HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not …

(Visited 25 times, 1 visits today)