ufal wiki courses:rg

courses:rg:2009-10-15-tabule

Anonymous (anonymous@undisclosed.example.com) — 2009-10-18T10:16:36+00:00

[Fotka tabule 1] [Fotka tabule 2]

courses:rg:2011-report-baby-steps

Anonymous (anonymous@undisclosed.example.com) — 2011-10-26T14:49:29+00:00

From Baby Steps to Leapfrog: How “Less is More” in Unsupervised Dependency Parsing Talk by Martin Majliš Report by Oldřich Krůza Introduction On Monday, October 24th 2011, we heard a talk about a paper by Valentin Spitkovsky, Hiyan Alshawi and Daniel Jurafsky on enhancing unsupervised language parsers. The paper itself focuses on improving the state of the art in unsupervised parsing, and reports a success in a rate of percents, which certainly makes it a paper worth notice.

courses:rg:2011-report-parser

Anonymous (anonymous@undisclosed.example.com) — 2012-09-27T11:22:41+00:00

A Fast, Accurate, Non-Projective, Semantically-Enriched Parser written by Stephen Tratz and Eduard Hovy (Information Sciences Institute, University of Southern Carolina) presented by Martin Popel reported by Michal Novák Introduction The paper describes a high-quality conversion of Penn Treebank to dependency trees. The authors introduce an improved labeled dependency scheme based on the Stanford's one. In addition, they extend the non-directional easy-first first algorithm of Goldberg and …

courses:rg:a-wordnet-based-system

Anonymous (anonymous@undisclosed.example.com) — 2010-11-02T16:00:47+00:00

A WordNet-based system for multi-way classification of semantic relations Matteo Negri and Milen Kouylekov A WordNet-based system for multi-way classification of semantic relations Comments * The paper briefly describes the task (SemEval-2010 Task #8). The task detail description itself which includes the annotation description, dataset configuration (training, development, test set), and evaluation methodology are described in different paper [1].

courses:rg:automatic-domain-adaptation-for-parsing

Anonymous (anonymous@undisclosed.example.com) — 2011-05-27T16:33:37+00:00

Automatic Domain Adaptation for Parsing David McClovsky, Eugene Charniak, Mark Johnson (ACL 2010) Presented by: Nathan Green Report by: Katerina Topilova Comments Summary: Idea – when parsing large data from diverse domains, it is useful for parsers to be able to generalize to a variety of domains. The result is a system that proposes linear combinations of parsing models trained on the source corpora.

courses:rg:automatic-domain-adaptation-for-parsing1

Anonymous (anonymous@undisclosed.example.com) — 2011-09-14T18:50:29+00:00

Automatic Domain Adaptation for Parsing Comments by : Loganathan Objective The objective of the paper is to make the statistical parsers adapting to new domains. Best parsing model for a particular testing data is identified by combining training data(source mixture) from different domains. This source mixture is learned from a regression model which will identify the appropriate parsing model.

courses:rg:bayes-with-tears

Anonymous (anonymous@undisclosed.example.com) — 2009-11-02T23:02:16+00:00

Poznámky k článku Kevin Knight: Bayesian Inference with Tears. September 2009. 1. část (26. října) Čtení Kevina Knighta nedopadlo podle mého nijak slavně, ale věřím, že repete příští týden to napraví a vše se v dobré obrátí. Co jsme se dozvěděli (prosím opravte mne, pokud něco píšu špatně):

courses:rg:beyond-nombank

Anonymous (anonymous@undisclosed.example.com) — 2010-10-14T19:49:31+00:00

Beyond NomBank: A Study of Implicit Arguments for Nominal Predicates Matthew Gerber and Joyce Y. Chai Comments * When reading the paper it is beneficial to have some basic knowledge about NomBank and PropBank (and don't be confused by other resources: VerbNet, FrameNet, WordNet,

courses:rg:coreference-resolution-haghihi-klein

Anonymous (anonymous@undisclosed.example.com) — 2011-01-09T22:32:11+00:00

Coreference Resolution in a Modular, Entity-Centered Model Aria Haghighi and Dan Klein HLT 2010, presented by Michal Novák Before reading * It is good to have an idea what is the philosophy of generative models (e.g. HMM tagging). In the end, we want to use the generative model to discover the hidden variables (POS tags or coreference in the case of this paper), but the didactical point of view is the opposite

courses:rg:cross-lingual-link-structure-of-wikipedia

Anonymous (anonymous@undisclosed.example.com) — 2011-07-06T10:46:53+00:00

Untangling the Cross-Lingual Link Structure of Wikipedia Gerard de Melo, Gerhard Weikum [ Untangling the Cross-Lingual Link Structure of Wikipedia ] in proceedings of ACL 2010 Report by Nathan Green and Lasha Abzianidze Introduction The paper has two main goals: * to find inaccurate connections in Wikipedia's cross-lingual link structure and use their algorithm that attempts to repair these connections;

courses:rg:cross-lingual_ontology_alignment

Anonymous (anonymous@undisclosed.example.com) — 2011-06-25T20:27:30+00:00

Cross-lingual Ontology Alignment using EuroWordNet and Wikipedia Gosse Bouma [ Cross-lingual Ontology Alignment using EuroWordNet and Wikipedia ] The International Conference on Language Resources and Evaluation (LREC) 2010 report by Lasha Abzianidze Introduction The paper is about cross-lingual ontology alignment - to map thesauri in different languages and to map resources that are large, rich in semantics but weak in formal structure. The author describes a system for linking the thesauru…

courses:rg:dependency_grammar_via_bitext_projection

Anonymous (anonymous@undisclosed.example.com) — 2010-11-01T13:55:25+00:00

Dependency Grammar Induction via Bitext Projection Constraints Kuzman Ganchev, Jeniffer Gillenwater, Ben Taskar [PDF] ACL 2009 Comments * Section 5, second paragraph: We don't know what are “conflicting edges” Does it mean non-projective edges? Or edges going from one node to more than parents?

courses:rg:extracting-parallel-sentences-from-comparable-corpora

Anonymous (anonymous@undisclosed.example.com) — 2011-05-22T19:23:39+00:00

Extracting Parallel Sentences from Comparable Corpora using Document Level Alignment Jason R. Smith Chris Quirk and Kristina Toutanova Introduction Article is about parallel sentence extraction from Wikipedia. This resource can be viewed as comparable corpus in which the document alignment is already provided by the interwiki links.

courses:rg:maxent-lm

Anonymous (anonymous@undisclosed.example.com) — 2013-04-27T22:52:28+00:00

Poznámky k článku o Maximum Entropy LM Ronald Rosenfeld: A Maximum Entropy Approach to Adaptive Statistical Language Modeling Definice entropie Před čtením článku je dobré si připomenout základy ze Statistických metod: * Mějme diskrétní prostor jevů X a dvě pravděpodobností rozdělení P, Q : X \rightarrow [0,1]. Pak

courses:rg:morphology-induction-with-spelling-rules

Anonymous (anonymous@undisclosed.example.com) — 2011-04-19T13:05:34+00:00

Improving morphology induction by learning spelling rules, ACL 2009 Jason Naradowsky and Sharon Goldwater Presented by: Loganathan Ramasamy Report by: Eduard Bejček Introduction * The paper describes morphology induction using Bayesian approach

courses:rg:multilingual-noise-robust-supervised-morphological-analysis-using-the-wordframe-model

Anonymous (anonymous@undisclosed.example.com) — 2011-01-09T17:53:54+00:00

Multilingual Noise-Robust Supervised Morphological Analysis using the WordFrame Model Richard Wicentowski (2004): [Multilingual Noise-Robust Supervised Morphological Analysis using the WordFrame Model] Comments Summary * In this paper the author presents a new supervized method for lemmatization, called WordFrame model. * This new method is compared to existing End-Of-String method and is proven better in most of the cases.

courses:rg:natural-logic-for-textual-inference

Anonymous (anonymous@undisclosed.example.com) — 2011-05-14T22:09:29+00:00

Natural Logic for Textual Inference Bill MacCartney, Christopher D. Manning (2007) Introduction This paper deals with “natural logic” which is a system of logical inference that operates over natural language. Usually the approaches for natural language inference are either robust but shallow or deep but brittle. The system proposed in this paper aims to be in the middle of the existent approaches and avoids, for instance, the error when translating a natural language to first-order logic.…

courses:rg:non-projective-dependency-parsing-using-spanning-tree-algorithms

Anonymous (anonymous@undisclosed.example.com) — 2011-04-19T12:09:33+00:00

Non-projective Dependency Parsing using Spanning Tree Algorithms Ryan McDonald, Fernando Pereira, Kiril Ribarov and Jan Hajič [ Non-projective Dependency Parsing using Spanning Tree Algorithms ] in proceedings of ACL 2005 report by Lasha Abzianidze Introduction In the paper, authors formalize weighted dependency parsing as searching for maximum spanning trees (

courses:rg:overcoming_vocabulary_sparsity_in_mt_using_lattices

Anonymous (anonymous@undisclosed.example.com) — 2011-01-09T19:43:15+00:00

Overcoming Vocabulary Sparsity in MT Using Lattices Steve DeNeefe and Ulf Hermjakob and Kevin Knight Overview of the article 1. Introduction 2. Related work 3-5. Three challenges and approaches to overcome them 6. Experiment 7. Conclusion Introduction

courses:rg:past

Anonymous (anonymous@undisclosed.example.com) — 2016-09-26T22:04:37+00:00

Past RG sessions (For the current semester see the main RG page) Spring&Summer 2016 date speaker paper Feb 22 Martin Popel W Ammar, G Mulcaire, M Ballesteros, C Dyer, NA Smith: One Parser, Many Languages 2016 Feb 29 cont. Mar 7 Jindřich Libovický

courses:rg:predicting_human_brain_activity_associated_with_the_meanings_of_nouns

Anonymous (anonymous@undisclosed.example.com) — 2011-09-11T12:52:30+00:00

Predicting Human Brain Activity Associated with the Meanings of Nouns Tom M. Mitchell, Svetlana V. Shinkareva, Andrew Carlson, Kai-Min Chang, Vicente L. Malave, Robert A. Mason, Marcel Adam Just Predicting Human Brain Activity Associated with the Meanings of Nouns Comments Summary * authors present a computational model, which predicts the functional magnetic resonance imaging (fMRI) of neural activation associated with words for which no fMRI data are available

courses:rg:reliability-measurment-without-limits

Anonymous (anonymous@undisclosed.example.com) — 2011-04-04T17:28:25+00:00

Comments -We discussed the history and why we are analyzing the agreement thresholds between .67 and .8 -Went through drawing the graphs relating to the relationship between the strength of relationships and the accuracy. For true annotation, the greater the relationship strength the greater the accuracy. -The paper indicates that when disagreement is caused by random noise it has little affect on the overall agreement. -We also went into alot of detail on different ways of computing annotator…

courses:rg:reranking-by-multitask-learning

Anonymous (anonymous@undisclosed.example.com) — 2011-09-20T11:32:30+00:00

N-best Reranking by Multitask Learning Kevin Duh, Katsuhito Sudoh, Hajime Tsukada, Hideki Isozaki, Masaaki Nagata Kevin's slides ACL 5th Workshop on Statistical Machine Translation (WMT) 2010 Suggestions for the presenter It would be great to have an illustrative but simple example of N-best list and also examples of features and examples of labels (to specify the terminology).

courses:rg:shooting_at_flies_in_the_dark

Anonymous (anonymous@undisclosed.example.com) — 2011-01-09T23:26:43+00:00

Linda Wiechetek, Francis M. Tyers, and Thomas Omma: Shooting at Flies in the Dark: Rule-Based Lexical Selection for a Minority Language Pair Topic Adding a lexical selection module to a ruled based MT system for translation from North Sami to Lule Sami.

courses:rg:towards-a-montagovian-account-of-dynamics

Anonymous (anonymous@undisclosed.example.com) — 2011-01-26T13:30:20+00:00

Philippe de Groote: Towards a Montagovian account of dynamics The paper deals with improving Montagovian account of semantics by introducing necessary machinery for dealing with both left and right context. Before (in Montagovian semantics) it was impossible for the left and right context to share information and variables. Authors look in particular at dealing with intersentential pronominal binding, including quantification scoping and donkey sentences.

courses:rg:transductive_learning_for_statistical_machine_translation

Anonymous (anonymous@undisclosed.example.com) — 2010-12-08T23:35:03+00:00

Transductive learning for statistical machine translation Nicola Ueffing and Gholamreza Haffari and Anoop Sarkar Introduction The paper is about the use of transductive semi-supervised methods for the effective use of monolingual data from the source language in order to improve translation quality. Transductive means that they repeatedly translate sentences from the development set or test set and use generated translation to improve the SMT system. Transductive learning is another mean to a…

courses:rg:unsupervised-methods-for-head-assignments

Anonymous (anonymous@undisclosed.example.com) — 2011-06-25T20:20:56+00:00

Unsupervised methods for head assignments, EACL 2009 Federico Sangati and Willem Zuidema Presented by: Zdeněk Žabokrtský Report by: Eduard Bejček and Lasha Abzianidze Introduction * The paper describes two methods (entropy minimization and

courses:rg:unsupervised_pof_tagging

Anonymous (anonymous@undisclosed.example.com) — 2011-11-03T16:16:11+00:00

Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections written by Dipanjan Das (Carnegie Mellon University) and Slav Petrov (Google Research) spoken by Michal Novák reported by Marie Konárová Introduction On Monday, October 31st 2011, Michal spoke about a paper which received the Best Paper award at the

courses:rg:unsupervised_pos_tagging

Anonymous (anonymous@undisclosed.example.com) — 2011-11-03T16:24:10+00:00

courses:rg:using-a-wikipedia-based-semantic-relatedness-measure-for-document-clustering

Anonymous (anonymous@undisclosed.example.com) — 2012-01-01T20:27:17+00:00

Using a Wikipedia-based Semantic Relatedness Measure for Document Clustering written by Majid Yazdani (Idiap Research Institute and EPFL) and Andrei Popescu-Belis (Idiap Research Institute) spoken by Marie Konárová reported by Martin Majlis Introduction

courses:rg:wishlist

Anonymous (anonymous@undisclosed.example.com) — 2014-10-13T20:20:58+00:00

Wishlist Parsing * Goldberg & Orwant: A Dataset of Syntactic-Ngrams over Time from a Very Large Corpus of English Books, 2013 * Yuan Zhang et al.: Steps to Excellence: Simple Inference with Refined Scoring of Dependency Trees, 2014 * Kong & Smith: An Empirical Comparison of Parsing Methods for Stanford Dependencies, 2014 * Ballesteros & Nivre: Malt Optimizer: Fast and effective parser optimization, 2014 * Keith Hall: k-best Spanning Tree Parsing ACL 2007 * Introduction to MALT Pars…