Spain

We evaluate a rule-based (Lee et al., 2013) and neural (Lee et al., 2018) coreference system on Dutch datasets of two domains: literary novels and news/Wikipedia text. The results provide insight into the relative strengths of data-driven and knowledge-driven systems, as well as the influence of domain, document length, and annotation schemes. The neural system performs best on news/Wikipedia text, while the rule-based system performs best on literature. The neural system shows weaknesses with limited training data and long documents, while the rule-based system is affected by annotation differences. The code and models used in this paper are available at https://github.com/andreasvc/crac2020

COLING 2020

A Benchmark of Rule-Based and Neural Coreference Resolution in Dutch Novels and News

dutch

coreference

literature

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

technical paper

The AMR (Abstract Meaning Representation) formalism for representing
meaning of natural language sentences puts emphasis on predicate-argument structure and was not designed to deal with scope and quantifiers. By extending AMR with indices for contexts and formulating constraints on these contexts, a formalism is derived that makes correct predictions for inferences involving negation and bound variables. The attractive core predicate-argument structure of AMR is preserved. The resulting framework is similar to the meaning representations of Discourse Representation Theory employed in the Parallel Meaning Bank.

Separating Argument Structure from Logical Structure in AMR

Ethics in the Vision and Language of Artificial Intelligence

This is an introductory tutorial to UCCA (Universal Conceptual Cognitive Annotation), a cross-linguistically applicable framework for semantic representation, with corpora annotated in English, German and French, and ongoing annotation in Russian and Hebrew. UCCA builds on extensive typological work and supports rapid annotation. The tutorial will provide a detailed introduction to the UCCA annotation guidelines, design philosophy and the available resources; and a comparison to other meaning representations. It will also survey the existing parsing work, including the findings of three recent shared tasks, in SemEval and CoNLL, that addressed UCCA parsing. Finally, the tutorial will present recent applications and extensions to the scheme, demonstrating its value for natural language processing in a range of languages and domains.

Parsing, Evaluation and Applications

While UCCA structures and categories are intentionally coarse, the scheme has a multi-layered architecture, which allows for refinement using additional layers, which serve as "modules" of semantic distinctions. We will give an overview of the recently proposed extensions (to support semantic roles, coreference, and implicit argument disambiguation). We will also situate UCCA in the meaning representation research landscape, comparing its design with widely-used formalisms such as AMR and UD.

Extension Layers and Comparison to Other Formalisms

Armenian is a language with significant variation and unevenly distributed NLP resources for different varieties. An attempt is made to process an RNN model for morphological annotation on the basis of different Armenian data (provided or not with morphologically annotated corpora), and to compare the annotation results of RNN and rule-based models. Different tests were carried out to evaluate the reuse of an unspecialized model of lemmatization and POS-tagging for under-resourced language varieties. The research focused on three dialects and further extended to Western Armenian with a mean accuracy of 94,00 % in lemmatization and 97,02% in POS-tagging, as well as a possible reusability of models to cover different other Armenian varieties. Interestingly, the comparison of an RNN model trained on Eastern Armenian with the Eastern Armenian National Corpus rule-based model applied to Western Armenian showed an enhancement of 19% in parsing. This model covers 88,79% of a short heterogeneous dataset in Western Armenian, and could be a baseline for a massive corpus annotation in that standard. It is argued that an RNN-based model can be a valid alternative to a rule-based one giving consideration to such factors as time-consumption, reusability for different varieties of a target language and significant qualitative results in morphological annotation.

Recycling and Comparing Morphological Annotation Models for Armenian Diachronic-Variational Corpus Processing

In this talk, I describe recent efforts to bring language-guided navigation agents from the Vision-and-Language Navigation task to robotic platforms.

Exploring the Sim-2-Real Gap in Vision-and-Language Navigation

"Language reflects demographics, as people of different demographic groups systematically use language differently. That holds also for gender. Gender-speficic language affects NLP tools, usually because it is not sufficiently modeled. Instead, models assume all language is the same. If they are ignored, these linguistic differences lead to uneven performance and even discrimination. If we instead start paying attention to WHO is talking, and not just WHAT is said, they give us the opportunity to model language in all its diversity, open new applications, and improve both performance and fairness.
In this talk, I will first show how gender representation is reflected in syntax, and then how this affects various NLP tasks. Lack of awareness of gendered differences mean that NLP models perform differently for different genders in part of speech tagging and parsing, and also affects the style of machine translations and sentence completions in BERT and GPT2."

Sampling, Syntax, and Sentence Completions.The (Overlooked?) Impact of Gender on NLP Tools

Large Scale Author Obfuscation Using Siamese Variational Auto-Encoder: The SiamAO System

This paper describes the SemEval-2020 shared task "Assessing Humor in Edited News Headlines." The task's dataset contains news headlines in which short edits were applied to make them funny, and the funniness of these edited headlines was rated using crowdsourcing. This task includes two subtasks, the first of which is to estimate the funniness of headlines on a humor scale in the interval 0-3. The second subtask is to predict, for a pair of edited versions of the same original headline, which is the funnier version. To date, this task is the most popular shared computational humor task, attracting 48 teams for the first subtask and 31 teams for the second.

Assessing Humor in Edited News Headlines

Humans learn to understand speech from weak and noisy supervision: they manage to extract structure and meaning from speech by simply being exposed to utterances situated and grounded in their daily sensory experience. Emulating this remarkable skill has been the goal of numerous studies; however researchers have often used severely simplified settings where either the language input or the extralinguistic sensory input, or both, are small-scale and symbolically represented. I present a series of studies on modelling visually grounded language understanding. Using variations of recurrent neural networks to model the temporal nature of spoken language, we examine how form and meaning-based linguistic knowledge emerges from the input signal.

A Benchmark of Rule-Based and Neural Coreference Resolution in Dutch Novels and News

Downloads

Next from COLING 2020

Separating Argument Structure from Logical Structure in AMR

Similar lecture

Extension Layers and Comparison to Other Formalisms

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

A Benchmark of Rule-Based and Neural Coreference Resolution in Dutch Novels and News

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from COLING 2020

Separating Argument Structure from Logical Structure in AMR

Similar lecture

Extension Layers and Comparison to Other Formalisms

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads