Spain

This paper describes a novel annotation scheme specifically designed for a customer-service context where written interactions take place between a given user and the chatbot of an Italian telecommunication company. More specifically, the scheme aims to detect and highlight two aspects: the presence of errors in the conversation on both sides (i.e. customer and chatbot) and the “emotional load” of the conversation. This can be inferred from the presence of emotions of some kind (especially negative ones) in the customer messages, and from the possible empathic
responses provided by the agent. The dataset annotated according to this scheme is currently used to develop the prototype of a rule-based Natural Language Generation system aimed at improving the chatbot responses and the customer experience overall.

COLING 2020

Annotating Errors and Emotions in Human-Chatbot Interactions in Italian

customer-service

errors

task-oriented dialogues

emotions

chatbot

**BRACIS** originated from the combination of the two most important scientific events in Brazil in Artificial Intelligence (AI) and Computational Intelligence (CI): the Brazilian Symposium on Artificial Intelligence – **SBIA** (22 editions), and the Brazilian Symposium on Neural Networks – **SBRN** (13 editions). **ENIAC** is a national forum for researchers, practitioners, educators and students to present and discuss innovations, trends, experiences, developments and work in progress in the fields of Artificial and Computational Intelligence. **STIL** is the bi-annual Language Technology event.
All events are supported by the Brazilian Computer Society – Special Interest Groups: **CE-IA**, **CE-IC** and **CE-PLN**.

To access the 10th Brazilian Conference on Intelligent Systems (**BRACIS**), you need to register for the conference.  Please visit the Conference official site to register

[Register now](http://c4ai.inova.usp.br/bracis2021/)

Register now

BRACIS 2021

BRACIS originated from the combination of the two most important scientific events in Brazil in Artificial Intelligence (AI) and Computational Intelligence (CI): the Brazilian Symposium on Artificial Intelligence – SBIA (22 editions), and the Brazilian Symposium on Neural Networks – SBRN (13 editions). 
ENIAC is a national forum for researchers, practitioners, educators and students to present and discuss innovations, trends, experiences, developments and work in progress in the fields of Artificial and Computational Intelligence. 
STIL is the bi-annual Language Technology event.
All events are supported by the Brazilian Computer Society – Special Interest Groups: CE-IA, CE-IC and CE-PLN

poster

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.

pyMMAX2 is an API for processing MMAX2 stand-off annotation data in Python. It provides a lightweight basis for the development of code which opens up the Java- and XML-based ecosystem of MMAX2 for more recent, Python-based NLP and data science methods. While pyMMAX2 is pure Python, and most functionality is implemented from scratch, the API re-uses the complex implementation of the essential business logic for MMAX2 annotation schemes by interfacing with the original MMAX2 Java libraries. pyMMAX2 is available for download at http://github.com/nlpAThits/pyMMAX2.

pyMMAX2: Deep Access to MMAX2 Projects from Python

This study develops the strand of research on topic transitions in social talk which aims to gain a better understanding of interlocutors' conversational goals. Luu and Malamud (2020) proposed that one way to identify such transitions is to annotate coherence relations, and then to identify utterances potentially expressing new topics as those that fail to participate in these relations. This work validates and refines their suggested annotation methodology, focusing on annotating most prominent coherence relations in face-to-face social dialogue. The result is a publicly accessible gold standard corpus with efficient and reliable annotation, whose broad coverage provides a foundation for future steps of identifying and classifying new topic utterances.

Annotating Coherence Relations for Studying Topic Transitions in Social Talk

We propose a new method for annotating verbal fluency data, which allows the reliable detection of the age-related decline of lexical access capacity. The main innovation is that annotators should inferentially assess the intention of the speaker when producing a word form during a verbal fluency test. Our method correlates probable speaker inten-tions such as “intended as a valid answer” or “intended as a meta-comment” with linguistic features such as word intensity (e.g. reduced intensity suggests private speech) and syntactic integration. The annotation scheme can be implemented with high reliability, and minimal linguistic training. When fluency data are annotated using this scheme, a relation between fluency and age emerges; this is in contrast to a strict implementation of the traditional method of annotating verbal fluency data, which has no way of dealing with score-confounding phenomena because it force-groups all verbal fluency productions –regardless of speaker intention— into one of three categories (i.e. valid answers, perseverations, and intrusions). The traditional lack of fine-grained annotation units is especially problematic when analyzing the qualitatively distinct fluency data of older participants and may cause studies to miss the relation between lexical access capacity and age.

Towards an annotation scheme for the verbal fluency data of older participants

This poster summarizes the main features of the first UD Hittite treebank.

A Small Universal Dependencies Treebank for Hittite

We present the first Universal Dependencies (UD) treebank for Albanian consisting of 60 Wikipedia sentences, annotated with lemmas, POS-tags, morphological features and syntactic dependencies. We also discuss a selection of linguistic constructions whose analysis in UD is not self-evident.

Universal Dependencies for Albanian

Manx Gaelic is one of the three Q-Celtic languages, along with Irish and Scottish Gaelic. We present a new dependency treebank for Manx consisting of 291 sentences and about 6000 tokens, annotated according to the Universal Dependency (UD) guidelines. To the best of our knowledge, this is the first annotated corpus of any kind for Manx. Our annotations generally follow the conventions established by the existing UD treebanks for Irish and Scottish Gaelic, although we highlight some areas where the grammar of Manx diverges, requiring new analyses. We use 10-fold cross validation to evaluate the accuracy of dependency parsers trained on the corpus, and compare these results with delexicalized models transferred from Irish and Scottish Gaelic.

Universal Dependencies for Manx Gaelic

This paper reports on a systematic approach for deriving Universal Dependencies from LFG structures. The conversion starts with a step-wise transformation of the c-structure, combining part-of-speech (POS) information and the embedding path to determine the true head of dependency structures. The paper discusses several issues faced by existing algorithms when applied on Wolof and presents the strategies used to account for these issues. An experimental evaluation indicated that our approach was able to generate the correct output in more than 90% of the cases, leading to a substantial improvement in conversion accuracy compared to the previous models.

From LFG To UD: A Combined Approach

UDon2 is an open-source library for manipulating dependency trees represented in the CoNLL-U format. The library is compatible with the Universal Dependencies. UDon2 is aimed at developers of downstream Natural Language Processing applications that require manipulating dependency trees on the sentence level (to complement other available tools geared towards working with treebanks).

UDon2 - a package for manipulating UD trees

We present Palmyra 2.0, a graphical dependency-tree visualization and editing software. Palmyra 2.0 is designed to be highly configurable to any dependency parsing representation, and to enable the annotation of a multitude of linguistic features. It uses an intuitive interface that relies on drag-and-drop utilities as well as pop-up menus and keyboard shortcuts that can be easily specified.

Palmyra 2.0: A Configurable Multilingual Platform Independent Tool for Morphology and Syntax Annotation

HDT-UD, the largest German UD treebank, as well as the German-LIT treebank, currently do not analyze preposition-determiner contractions such as zum (= zu dem, “to the”) as multi-word tokens, which is inconsistent both with UD guidelines as well as other German UD corpora (GSD and PUD). In this paper, we show that harmonizing corpora with regard to this highly frequent phenomenon using a lookup-table leads to a considerable increase in automatic parsing performance.

Annotating Errors and Emotions in Human-Chatbot Interactions in Italian

Downloads

Next from COLING 2020

pyMMAX2: Deep Access to MMAX2 Projects from Python

Similar lecture

A Conversational Agent to Support Hospital Bed Allocation

Annotating Errors and Emotions in Human-Chatbot Interactions in Italian

.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

pyMMAX2: Deep Access to MMAX2 Projects from Python

Similar lecture

A Conversational Agent to Support Hospital Bed Allocation

Downloads