Refine
Year of publication
Document Type
- Conference Proceeding (326) (remove)
Keywords
- Korpus <Linguistik> (112)
- Deutsch (100)
- Annotation (33)
- Computerlinguistik (27)
- Computerunterstützte Lexikographie (26)
- Gesprochene Sprache (26)
- Englisch (22)
- Automatische Sprachanalyse (19)
- German (17)
- Französisch (12)
-
Conversion and annotation web services for spoken language data in CLARIN
(2017)
- We present an approach to making existing CLARIN web services usable for spoken language transcriptions. Our approach is based on a new TEI-based ISO standard for such transcriptions. We show how existing tool formats can be transformed to this standard, how an encoder/decoder pair for the TCF format enables users to feed this type of data through a WebLicht tool chain, and why and how web services operating directly on the standard format would be useful.
-
Annotation and classification of French feedback communicative functions
(2015)
- Feedback utterances are among the most frequent in dialogue. Feedback is also a crucial aspect of all linguistic theories that take social interaction involving language into account. However, determining communicative functions is a notoriously difficult task both for human interpreters and systems. It involves an interpretative process that integrates various sources of information. Existing work on communicative function classification comes from either dialogue act tagging where it is generally coarse grained concerning the feed- back phenomena or it is token-based and does not address the variety of forms that feed- back utterances can take. This paper introduces an annotation framework, the dataset and the related annotation campaign (involving 7 raters to annotate nearly 6000 utterances). We present its evaluation not merely in terms of inter-rater agreement but also in terms of usability of the resulting reference dataset both from a linguistic research perspective and from a more applicative viewpoint.
-
IUCL at SemEval-2016 Task 6: An Ensemble Model for Stance Detection in Twitter
(2016)
- We present the IUCL system, based on supervised learning, for the shared task on stance detection. Our official submission, the random forest model, reaches a score of 63.60, and is ranked 6th out of 19 teams. We also use gradient boosting decision trees and SVM and merge all classifiers into an ensemble method. Our analysis shows that random forest is good at retrieving minority classes and gradient boosting majority classes. The strengths of different classifiers wrt. precision and recall complement each other in the ensemble.
-
Do FreeWord Order Languages Need More Treebank Data? Investigating Dative Alternation in German, English, and Russian
(2015)
- We investigate whether non-configurational languages, which display more word order variation than configurational ones, require more training data for a phenomenon to be parsed successfully. We perform a tightly controlled study comparing the dative alternation for English (a configurational language), German, and Russian (both non-configurational). More specifically, we compare the performance of a dependency parser when only canonical word order is present with its performance on data sets when all word orders are present. Our results show that for all languages, canonical data not only is easier to parse, but there exists no direct correspondence between the size of training sets containing free(er) word order variation and performance.
-
“My Curiosity was Satisfied, but not in a Good Way”: Predicting User Ratings for Online Recipes
(2014)
- In this paper, we develop an approach to automatically predict user ratings for recipes at Epicurious.com, based on the recipes’ reviews. We investigate two distributional methods for feature selection, Information Gain and Bi-Normal Separation; we also compare distributionally selected features to linguistically motivated features and two types of frameworks: a one-layer system where we aggregate all reviews and predict the rating vs. a two-layer system where ratings of individual reviews are predicted and then aggregated. We obtain our best results by using the two-layer architecture, in combination with 5 000 features selected by Information Gain. This setup reaches an overall accuracy of 65.60%, given an upper bound of 82.57%.
-
Parsing German: How Much Morphology Do We Need?
(2014)
- We investigate how the granularity of POS tags influences POS tagging, and furthermore, how POS tagging performance relates to parsing results. For this, we use the standard “pipeline” approach, in which a parser builds its output on previously tagged input. The experiments are performed on two German treebanks, using three POS tagsets of different granularity, and six different POS taggers, together with the Berkeley parser. Our findings show that less granularity of the POS tagset leads to better tagging results. However, both too coarse-grained and too fine-grained distinctions on POS level decrease parsing performance.
-
Prosodic Matching and Turn Competition in Multi-Party Conversations
(2015)
- Prosodic constructions used to compete for the speaking turn in conversation have been widely studied (French & Local (1983), Kurtić et al. (2013)). Usually, turn competition arises in overlapping talk between at least two speakers. Coordination between participants in their prosodic design of talk (Szczepek-Reed, 2006) and social action (Gorisch et al. 2012), as well as entrainment in more general terms (Levitan et al. 2011), is well established in the literature. Nevertheless, previous studies on turn competition and overlap do not investigate the prosodic design of turn competitive incomings in reference to the orientation of the speakers to each other. Rather, they assume that prosodic constructions are used for turn competition regardless of the co-participants’ design of the turn. In this paper, we ask whether the prosodic design of turn competitive talk is co-constructed between two participants talking in overlap. More specifically, we investigate whether the prosodic design of one participant’s in overlap talk is developed with respect to the interlocutor’s prosodic features during the same portion of overlapped talk, and whether this prosodic matching can discriminate between the overlaps that are competitive and those that are not. 183 Our analyses are based on two-speaker overlaps drawn from a corpus of multi-party face-to face conversation between four friends recorded in British English (Kurtic et al. 2012). 3407 instances of twospeaker overlaps have been extracted from 4 hours of talk. Two independent conversation analysts performed the interactional categorisation of overlaps into competitive and non-competitive for all these two-speaker overlap instances and achieved a good agreement of alpha=0.807 (Krippendorff 2004) as measured on a subset of 808 overlaps selected for our initial analysis. For the analysis of prosodic features we focus on F0 related features: mean, slope, span and contour, all of which have previously been shown to be used by each overlapping speaker separately for turn competition (Kurtic et al. 2009; Oertel et al. 2012). We investigate the similarity in F0 mean, slope and span by correlating these features across the two participants. For F0 contour, a similarity coefficient is computed using dynamic programming method described in Gorisch et al. (2012). We consider the difference in F0 contour similarity in competitive and non-competitive overlaps as an indication of intonational matching being a turn competitive resource. We conduct these analyses for overlaps that are clearly competitive or noncompetitive as indicated by inter-annotator agreement. In addition, we qualitatively explore those cases that annotators disagree on in order to investigate whether they reveal further important interactional or prosodic features of in-overlap talk. Our preliminary results suggest that conversational participants attend and adapt to the interlocutor during overlap depending on whether they return competition or not. We explain our findings in relation to previous work on turn competition in overlap, discuss the quantitative method employed and also address the possible consequences of our results for the study of prosodic realization of other social actions in conversation.
-
Integrating corpora of computer-mediated communication into the language resources landscape: Initiatives and best practices from French, German, Italian and Slovenian projects
(2016)
- The paper presents best practices and results from projects in four countries dedicated to the creation of corpora of computer-mediated communication and social media interactions (CMC). Even though there are still many open issues related to building and annotating corpora of that type, there already exists a range of accessible solutions which have been tested in projects and which may serve as a starting point for a more precise discussion of how future standards for CMC corpora may (and should) be shaped like.
-
The Collection of Distributionally Idiosyncratic Items: A Multilingual Resource for Linguistic Research
(2006)
- We present two collections of lexical items with idiosyncratic distribution. The collections document the behavior of German and English bound words (BW, such as English “headway”), i.e., words which can only occur in one expression (“make headway”). BWs are a problem for both general and idiomatic dictionaries since it is unclear whether they have an independent lexical status and to what extent the expressions in which they occur are typical idiomatic expressions. We propose a system which allows us to document the information about BWs from dictionaries and linguistic literature, together with corpus data and example queries for major text corpora. We present our data structure and point to other phraseologically oriented collections. We will also show differences between the German and the English collection.
-
Discussing best practices for the annotation of Twitter microtext
(2013)
- This paper contributes to the discussion on best practices for the syntactic analysis of non-canonical language, focusing on Twitter microtext. We present an annotation experiment where we test an existing POS tagset, the Stuttgart-Tübingen Tagset (STTS), with respect to its applicability for annotating new text from the social media, in particular from Twitter microblogs. We discuss different tagset extensions proposed in the literature and test our extended tagset on a set of 506 tweets (7.418 tokens) where we achieve an inter-annotator agreement for two human annotators in the range of 92.7 to 94.4 (k). Our error analysis shows that especially the annotation of Twitterspecific phenomena such as hashtags and at-mentions causes disagreements between the human annotators. Following up on this, we provide a discussion of the different uses of the @- and #-marker in Twitter and argue against analysing both on the POS level by means of an at-mention or hashtag label. Instead, we sketch a syntactic analysis which describes these phenomena by means of syntactic categories and grammatical functions.