Paper Group NANR 167
To What Extent is Immediate Constituency Analysis Dependency-Based? A Survey of Foundational Texts. A Dependency Treebank for Kurmanji Kurdish. Fully Delexicalized Contexts for Syntax-Based Word Embeddings. A Monotonicity Calculus and Its Completeness. The Language of Place: Semantic Value from Geospatial Context. A Rule-based Semantic Annotator: A …
To What Extent is Immediate Constituency Analysis Dependency-Based? A Survey of Foundational Texts
| Title | To What Extent is Immediate Constituency Analysis Dependency-Based? A Survey of Foundational Texts |
| Authors | Nicolas Mazziotta, Sylvain Kahane |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6515/ |
| https://www.aclweb.org/anthology/W17-6515 | |
| PWC | https://paperswithcode.com/paper/to-what-extent-is-immediate-constituency |
| Repo | |
| Framework | |
A Dependency Treebank for Kurmanji Kurdish
| Title | A Dependency Treebank for Kurmanji Kurdish |
| Authors | Memduh G{"o}k{\i}rmak, Francis M. Tyers |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6509/ |
| https://www.aclweb.org/anthology/W17-6509 | |
| PWC | https://paperswithcode.com/paper/a-dependency-treebank-for-kurmanji-kurdish |
| Repo | |
| Framework | |
Fully Delexicalized Contexts for Syntax-Based Word Embeddings
| Title | Fully Delexicalized Contexts for Syntax-Based Word Embeddings |
| Authors | Jenna Kanerva, Sampo Pyysalo, Filip Ginter |
| Abstract | |
| Tasks | Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6511/ |
| https://www.aclweb.org/anthology/W17-6511 | |
| PWC | https://paperswithcode.com/paper/fully-delexicalized-contexts-for-syntax-based |
| Repo | |
| Framework | |
A Monotonicity Calculus and Its Completeness
| Title | A Monotonicity Calculus and Its Completeness |
| Authors | Thomas Icard, Lawrence Moss, William Tune |
| Abstract | |
| Tasks | Natural Language Inference |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/W17-3408/ |
| https://www.aclweb.org/anthology/W17-3408 | |
| PWC | https://paperswithcode.com/paper/a-monotonicity-calculus-and-its-completeness |
| Repo | |
| Framework | |
The Language of Place: Semantic Value from Geospatial Context
| Title | The Language of Place: Semantic Value from Geospatial Context |
| Authors | Anne Cocos, Chris Callison-Burch |
| Abstract | There is a relationship between what we say and where we say it. Word embeddings are usually trained assuming that semantically-similar words occur within the same textual contexts. We investigate the extent to which semantically-similar words occur within the same geospatial contexts. We enrich a corpus of geolocated Twitter posts with physical data derived from Google Places and OpenStreetMap, and train word embeddings using the resulting geospatial contexts. Intrinsic evaluation of the resulting vectors shows that geographic context alone does provide useful information about semantic relatedness. |
| Tasks | Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2016/ |
| https://www.aclweb.org/anthology/E17-2016 | |
| PWC | https://paperswithcode.com/paper/the-language-of-place-semantic-value-from |
| Repo | |
| Framework | |
A Rule-based Semantic Annotator: Adding top-level ontology Tags
| Title | A Rule-based Semantic Annotator: Adding top-level ontology Tags |
| Authors | Guidson Coelho Andrade, Alcione Oliveira, Alex Moreira, ra |
| Abstract | |
| Tasks | |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6608/ |
| https://www.aclweb.org/anthology/W17-6608 | |
| PWC | https://paperswithcode.com/paper/a-rule-based-semantic-annotator-adding-top |
| Repo | |
| Framework | |
Evaluating Word Embeddings for Sentence Boundary Detection in Speech Transcripts
| Title | Evaluating Word Embeddings for Sentence Boundary Detection in Speech Transcripts |
| Authors | Marcos Treviso, Christopher Shulby, S Alu{'\i}sio, ra |
| Abstract | |
| Tasks | Boundary Detection, Sentiment Analysis, Speech Recognition, Word Embeddings |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6618/ |
| https://www.aclweb.org/anthology/W17-6618 | |
| PWC | https://paperswithcode.com/paper/evaluating-word-embeddings-for-sentence |
| Repo | |
| Framework | |
Universal Dependencies and Morphology for Hungarian - and on the Price of Universality
| Title | Universal Dependencies and Morphology for Hungarian - and on the Price of Universality |
| Authors | Veronika Vincze, Katalin Simk{'o}, Zsolt Sz{'a}nt{'o}, Rich{'a}rd Farkas |
| Abstract | In this paper, we present how the principles of universal dependencies and morphology have been adapted to Hungarian. We report the most challenging grammatical phenomena and our solutions to those. On the basis of the adapted guidelines, we have converted and manually corrected 1,800 sentences from the Szeged Treebank to universal dependency format. We also introduce experiments on this manually annotated corpus for evaluating automatic conversion and the added value of language-specific, i.e. non-universal, annotations. Our results reveal that converting to universal dependencies is not necessarily trivial, moreover, using language-specific morphological features may have an impact on overall performance. |
| Tasks | Morphological Tagging |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1034/ |
| https://www.aclweb.org/anthology/E17-1034 | |
| PWC | https://paperswithcode.com/paper/universal-dependencies-and-morphology-for |
| Repo | |
| Framework | |
A Rich Morphological Tagger for English: Exploring the Cross-Linguistic Tradeoff Between Morphology and Syntax
| Title | A Rich Morphological Tagger for English: Exploring the Cross-Linguistic Tradeoff Between Morphology and Syntax |
| Authors | Christo Kirov, John Sylak-Glassman, Rebecca Knowles, Ryan Cotterell, Matt Post |
| Abstract | A traditional claim in linguistics is that all human languages are equally expressive{—}able to convey the same wide range of meanings. Morphologically rich languages, such as Czech, rely on overt inflectional and derivational morphology to convey many semantic distinctions. Languages with comparatively limited morphology, such as English, should be able to accomplish the same using a combination of syntactic and contextual cues. We capitalize on this idea by training a tagger for English that uses syntactic features obtained by automatic parsing to recover complex morphological tags projected from Czech. The high accuracy of the resulting model provides quantitative confirmation of the underlying linguistic hypothesis of equal expressivity, and bodes well for future improvements in downstream HLT tasks including machine translation. |
| Tasks | Dependency Parsing, Machine Translation, Morphological Analysis, Morphological Tagging |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2018/ |
| https://www.aclweb.org/anthology/E17-2018 | |
| PWC | https://paperswithcode.com/paper/a-rich-morphological-tagger-for-english |
| Repo | |
| Framework | |
End-to-End Trainable Attentive Decoder for Hierarchical Entity Classification
| Title | End-to-End Trainable Attentive Decoder for Hierarchical Entity Classification |
| Authors | Sanjeev Karn, Ulli Waltinger, Hinrich Sch{"u}tze |
| Abstract | We address fine-grained entity classification and propose a novel attention-based recurrent neural network (RNN) encoder-decoder that generates paths in the type hierarchy and can be trained end-to-end. We show that our model performs better on fine-grained entity classification than prior work that relies on flat or local classifiers that do not directly model hierarchical structure. |
| Tasks | Morphological Tagging |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2119/ |
| https://www.aclweb.org/anthology/E17-2119 | |
| PWC | https://paperswithcode.com/paper/end-to-end-trainable-attentive-decoder-for |
| Repo | |
| Framework | |
Finding the ``right’’ answers for customers
| Title | Finding the ``right’’ answers for customers | |
| Authors | Frank Schilder |
| Abstract | This talk will present a few NLG systems developed within Thomson Reuters providing information to professionals such as lawyers, accountants or traders. Based on the experience developing these system, I will discuss the usefulness of automatic metrics, crowd-sourced evaluation, corpora studies and expert reviews. I will conclude with exploring the question of whether developers of NLG systems need to follow ethical guidelines and how those guidelines could be established. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3510/ |
| https://www.aclweb.org/anthology/W17-3510 | |
| PWC | https://paperswithcode.com/paper/finding-the-right-answers-for-customers |
| Repo | |
| Framework | |
Optimal encoding! - Information Theory constrains article omission in newspaper headlines
| Title | Optimal encoding! - Information Theory constrains article omission in newspaper headlines |
| Authors | Robin Lemke, Eva Horch, Ingo Reich |
| Abstract | In this paper we pursue the hypothesis that the distribution of article omission specifically is constrained by principles of Information Theory (Shannon 1948). In particular, Information Theory predicts a stronger preference for article omission before nouns which are relatively unpredictable in context of the preceding words. We investigated article omission in German newspaper headlines with a corpus and acceptability rating study. Both support our hypothesis: Articles are inserted more often before unpredictable nouns and subjects perceive article omission before predictable nouns as more well-formed than before unpredictable ones. This suggests that information theoretic principles constrain the distribution of article omission in headlines. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2021/ |
| https://www.aclweb.org/anthology/E17-2021 | |
| PWC | https://paperswithcode.com/paper/optimal-encoding-information-theory |
| Repo | |
| Framework | |
FrameFOR – Uma Base de Conhecimento de Frames Sem^anticos para Per'\icias de Inform'atica (FrameFOR - a Knowledge Base of Semantic Frames for Digital Forensics)[In Portuguese]
| Title | FrameFOR – Uma Base de Conhecimento de Frames Sem^anticos para Per'\icias de Inform'atica (FrameFOR - a Knowledge Base of Semantic Frames for Digital Forensics)[In Portuguese] |
| Authors | Ravi Barreira, Vl{'a}dia Pinheiro, Vasco Furtado |
| Abstract | |
| Tasks | Semantic Role Labeling |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6620/ |
| https://www.aclweb.org/anthology/W17-6620 | |
| PWC | https://paperswithcode.com/paper/framefor-a-uma-base-de-conhecimento-de-frames |
| Repo | |
| Framework | |
Proceedings of the CoNLL SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection
| Title | Proceedings of the CoNLL SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-2000/ |
| https://www.aclweb.org/anthology/K17-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-conll-sigmorphon-2017 |
| Repo | |
| Framework | |
On the Need of Cross Validation for Discourse Relation Classification
| Title | On the Need of Cross Validation for Discourse Relation Classification |
| Authors | Wei Shi, Vera Demberg |
| Abstract | The task of implicit discourse relation classification has received increased attention in recent years, including two CoNNL shared tasks on the topic. Existing machine learning models for the task train on sections 2-21 of the PDTB and test on section 23, which includes a total of 761 implicit discourse relations. In this paper, we{'}d like to make a methodological point, arguing that the standard test set is too small to draw conclusions about whether the inclusion of certain features constitute a genuine improvement, or whether one got lucky with some properties of the test set, and argue for the adoption of cross validation for the discourse relation classification task by the community. |
| Tasks | Implicit Discourse Relation Classification, Language Modelling, Machine Translation, Question Answering, Relation Classification |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2024/ |
| https://www.aclweb.org/anthology/E17-2024 | |
| PWC | https://paperswithcode.com/paper/do-we-need-cross-validation-for-discourse |
| Repo | |
| Framework | |
