To address the challenging low-resource non-topical text classification problems in domain specific settings we introduce ContextGen – a novel approach that uses targeted text generation with no fine tuning to augment the available small annotated dataset. It first adapts the powerful GPT-2 text generation model to generate samples relevant for the domain by using properly designed context text as input for generation. Then it assigns class labels to the newly generated samples after which they are added to the initial training set. We demonstrate the superior performance of a state-of-the-art text classifier trained with the augmented labelled dataset for four different non-topical tasks in the low resource setting, three of which are from specialized domains.

Speech synthesis for poetry is challenging due to specific intonation patterns inherent to poetic speech.In this work, we propose an approach to synthesise poems with almost human like naturalness in order to enable literary scholars to systematically examine hypotheses on the interplay between text, spoken realisation, and the listener's perception of poems.To meet these special requirements for literary studies, we resynthesise poems by cloning prosodic values from a human reference recitation, and afterwards make use of fine-grained prosody control to manipulate the synthetic speech in a human-in-the-loop setting to alter the recitation w.r.t.specific phenomena.We find that finetuning our TTS model on poetry captures poetic intonation patterns to a large extent which is beneficial for prosody cloning and manipulation and verify the success of our approach both in an objective evaluation as well as in human studies.

We present the steps taken towards an exploration platform for a multi-modal corpus of German lyric poetry from the Romantic era developed in the project »textklang«. This interdisciplinary project develops a mixed-methods approach for the systematic investigation of the relationship between written text (here lyric poetry) and its potential and actual sonic realisation (in recitations, musical performances etc.). The multi-modal »textklang« platform will be designed to technically and analytically combine three modalities: the poetic text, the audio signal of a recorded recitation and, at a later stage, music scores of a musical setting of a poem. The methodological workflow will enable scholars to develop hypotheses about the relationship between textual form and sonic/prosodic realisation based on theoretical considerations, text interpretation and evidence from recorded recitations. The full workflow will support hypothesis testing either through systematic corpus analysis alone or with addtional contrastive perception experiments. For the experimental track, researchers will be enabled to manipulate prosodic parameters in (re-)synthesised variants of the original recordings. The focus of this paper is on the design of the base corpus and on tools for systematic exploration – placing special emphasis on our response to challenges stemming from multi-modality and the methodologically diverse interdisciplinary setup.

Large scale, multi-label text datasets with high numbers of different classes are expensive to annotate, even more so if they deal with domain specific language. In this work, we aim to build classifiers on these datasets using Active Learning in order to reduce the labeling effort. We outline the challenges when dealing with extreme multi-label settings and show the limitations of existing Active Learning strategies by focusing on their effectiveness as well as efficiency in terms of computational cost. In addition, we present five multi-label datasets which were compiled from hierarchical classification tasks to serve as benchmarks in the context of extreme multi-label classification for future experiments. Finally, we provide insight into multi-class, multi-label evaluation and present an improved classifier architecture on top of pre-trained transformer language models.

Sinan Kurtyigit, Maike Park, Dominik Schlechtweg, Jonas Kuhn, Sabine Schulte im Walde. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

In this paper, we revisit the task of negation resolution, which includes the subtasks of cue detection (e.g."not", "never") and scope resolution.In the context of previous shared tasks, a variety of evaluation metrics have been proposed.Subsequent works usually use different subsets of these, including variations and custom implementations, rendering meaningful comparisons between systems difficult.Examining the problem both from a linguistic perspective and from a downstream viewpoint, we here argue for a negation-instance based approach to evaluating negation resolution.Our proposed metrics correspond to expectations over per-instance scores and hence are intuitively interpretable.To render research comparable and to foster future work, we provide results for a set of current state-of-the-art systems for negation resolution on three English corpora, and make our implementation of the evaluation scripts publicly available.

We propose a graph-based method to tackle the dependency tree linearization task. We formulate the task as a Traveling Salesman Problem (TSP), and use a biaffine attention model to calculate the edge costs. We facilitate the decoding by solving the TSP for each subtree and combining the solution into a projective tree. We then design a transition system as post-processing, inspired by non-projective transition-based parsing, to obtain non-projective sentences. Our proposed method outperforms the state-of-the-art linearizer while being 10 times faster in training and decoding.

This paper proposes a framework for the expression of typological statements which uses realvalued logics to capture the empirical truth value (truth degree) of a formula on a given data source, e.g. a collection of multilingual treebanks with comparable annotation.The formulae can be arbitrarily complex expressions of propositional logic.To illustrate the usefulness of such a framework, we present experiments on the Universal Dependencies treebanks for two use cases: (i) empirical (re-)evaluation of established formulae against the spectrum of available treebanks and (ii) evaluating new formulae (i.e.potential candidates for universals) generated by a search algorithm.

Modelling language change is an increasingly important area of interest within the fields of sociolinguistics and historical linguistics. In recent years, there has been a growing number of publications whose main concern is studying changes that have occurred within the past centuries. The Corpus of Historical American English (COHA) is one of the most commonly used large corpora in diachronic studies in English. This paper describes methods applied to the downloadable version of the COHA corpus in order to overcome its main limitations, such as inconsistent lemmas and malformed tokens, without compromising its qualitative and distributional properties. The resulting corpus CCOHA contains a larger number of cleaned word tokens which can offer better insights into language change and allow for a larger variety of tasks to be performed.

We present GRAIN-S, a set of manually created syntactic annotations for radio interviews in German. The dataset extends an existing corpus GRAIN and comes with constituency and dependency trees for six interviews. The rare combination of gold- and silver-standard annotation layers coming from GRAIN with high-quality syntax trees can serve as a useful resource for speech- and text-based research. Moreover, since interviews can be put between carefully prepared speech and spontaneous conversational speech, they cover phenomena not seen in traditional newspaper-based treebanks. Therefore, GRAIN-S can contribute to research into techniques for model adaptation and for building more corpus-independent tools. GRAIN-S follows TIGER, one of the established syntactic treebanks of German. We describe the annotation process and discuss decisions necessary to adapt the original TIGER guidelines to the interviews domain. Next, we give details on the conversion from TIGER-style trees to dependency trees. We provide data statistics and demonstrate differences between the new dataset and existing out-of-domain test sets annotated with TIGER syntactic structures. Finally, we provide baseline parsing results for further comparison.

DEbateNet-migr15 is a manually annotated dataset for German which covers the public debate on immigration in 2015. The building block of our annotation is the political science notion of a claim, i.e., a statement made by a political actor (a politician, a party, or a group of citizens) that a specific action should be taken (e.g., vacant flats should be assigned to refugees). We identify claims in newspaper articles, assign them to actors and fine-grained categories and annotate their polarity and date. The aim of this paper is two-fold: first, we release the full DEbateNet-mig15 corpus and document it by means of a quantitative and qualitative analysis; second, we demonstrate its application in a discourse network analysis framework, which enables us to capture the temporal dynamics of the political debate

Classical non-neural dependency parsers put considerable effort on the design of feature functions.Especially, they benefit from information coming from structural features, such as features drawn from neighboring tokens in the dependency tree.In contrast, their BiLSTM-based successors achieve state-ofthe-art performance without explicit information about the structural context.In this paper we aim to answer the question: How much structural context are the BiLSTM representations able to capture implicitly?We show that features drawn from partial subtrees become redundant when the BiLSTMs are used.We provide a deep insight into information flow in transition-and graph-based neural architectures to demonstrate where the implicit information comes from when the parsers make their decisions.Finally, with model ablations we demonstrate that the structural context is not only present in the models, but it significantly influences their performance.

Understanding the structures of political debates (which actors make what claims) is essential for understanding democratic political decision-making.The vision of computational construction of such discourse networks from newspaper reports brings together political science and natural language processing.This paper presents three contributions towards this goal: (a) a requirements analysis, linking the task to knowledge base population; (b) a first release of an annotated corpus of claims on the topic of migration, based on German newspaper reports; (c) initial modeling results.

We present a dependency tree linearization model with two novel components: (1) a tree-structured encoder based on bidirectional Tree-LSTM that propagates information first bottom-up then top-down, which allows each token to access information from the entire tree; and (2) a linguistically motivated headfirst decoder that emphasizes the central role of the head and linearizes the subtree by incrementally attaching the dependents on both sides of the head.With the new encoder and decoder, we reach state-of-the-art performance on the Surface Realization Shared Task 2018 dataset, outperforming not only the shared tasks participants, but also previous state-ofthe-art systems (Bohnet et al., 2011;Puduppully et al., 2016).Furthermore, we analyze the power of the tree-structured encoder with a probing task and show that it is able to recognize the topological relation between any pair of tokens in a tree.

Recent work on bridging resolution has so far been based on the corpus ISNotes (Markert et al. 2012), as this was the only corpus available with unrestricted bridging annotation. Hou et al. 2014’s rule-based system currently achieves state-of-the-art performance on this corpus, as learning-based approaches suffer from the lack of available training data. Recently, a number of new corpora with bridging annotations have become available. To test the generalisability of the approach by Hou et al. 2014, we apply a slightly extended rule-based system to these corpora. Besides the expected out-of-domain effects, we also observe low performance on some of the in-domain corpora. Our analysis shows that this is the result of two very different phenomena being defined as bridging, namely referential and lexical bridging. We also report that filtering out gold or predicted coreferent anaphors before applying the bridging resolution system helps improve bridging resolution.

Kyle Richardson, Jonathan Berant, Jonas Kuhn. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

We consider the problem of translating high-level textual descriptions to formal representations in technical documentation as part of an effort to model the meaning of such documentation.We focus specifically on the problem of learning translational correspondences between text descriptions and grounded representations in the target documentation, such as formal representation of functions or code templates.Our approach exploits the parallel nature of such documentation, or the tight coupling between high-level text and the low-level representations we aim to learn.Data is collected by mining technical documents for such parallel text-representation pairs, which we use to train a simple semantic parsing model.We report new baseline results on sixteen novel datasets, including the standard library documentation for nine popular programming languages across seven natural languages, and a small collection of Unix utility manuals.1. Java Documentation * Returns the greater of two long values * * @param a an argument * @param b another argument * @return the larger of a and b * @see java.lang.Long#MAX VALUE * / public static long max(long a, long b) 2. Clojure Documentation (defn random-sample "Returns items from coll with random probability of prob (0.0 -1.0)" ([prob coll] ...)) 3. PHP documentation (French) Ajoute une valeur comme dernier élément * * @param value La valeur á ajouter * @see ArrayIterations::next() * / public void append(mixed $value)

One of the main obstacles for many Digital Humanities projects is the low data availability.Texts have to be digitized in an expensive and time consuming process whereas Optical Character Recognition (OCR) post-correction is one of the time-critical factors.At the example of OCR post-correction, we show the adaptation of a generic system to solve a specific problem with little data.The system accounts for a diversity of errors encountered in OCRed texts coming from different time periods in the domain of literature.We show that the combination of different approaches, such as e.g.Statistical Machine Translation and spell checking, with the help of a ranking mechanism tremendously improves over singlehanded approaches.Since we consider the accessibility of the resulting tool as a crucial part of Digital Humanities collaborations, we describe the workflow we suggest for efficient text recognition and subsequent automatic and manual postcorrection.

We propose a new shared task for tactical datato-text generation in the domain of source code libraries.Specifically, we focus on text generation of function descriptions from example software projects.Data is drawn from existing resources used for studying the related problem of semantic parser induction (Richardson and Kuhn, 2017b; Richardson and Kuhn, 2017a), and spans a wide variety of both natural languages and programming languages.In this paper, we describe these existing resources, which will serve as training and development data for the task, and discuss plans for building new independent test sets.1. Java Documentation * Returns the greater of two long values * / ... public static long max(long a, long b) 2. Python Documentation # from decimal.Context max(self, a, b): """Compares two values numerically and returns the maximum""" 3. aNALoGuE Challenge (Novikova and Rieser, 2016) MR input: name[Bibmbap House] food[French] priceRange[cheap], area[riverside] near[Clare Hall] NL output: Near Clare Hall, in the riverside area, Bibimbap serves French food in the price range cheap.

We cast sentence boundary detection and syntactic parsing as a joint problem, so an entire text document forms a training instance for transition-based dependency parsing. When trained with an early update or max-violation strategy for inexact search, we observe that only a tiny part of these very long training instances is ever exploited. We demonstrate this effect by extending the ArcStandard transition system with swap for the joint prediction task. When we use an alternative update strategy, our models are considerably better on both tasks and train in substantially less time compared to models trained with early update/max-violation. A comparison between a standard pipeline and our joint model furthermore empirically shows the usefulness of syntactic information on the task of sentence boundary detection.

We propose an approach to Named Entity Disambiguation that avoids a problem of standard work on the task (likewise affecting fully supervised, weakly supervised, or distantly supervised machine learning techniques): the treatment of name mentions referring to people with no (or very little) coverage in the textual training data is systematically incorrect. We propose to indirectly take into account the property information for the “non-prominent” name bearers, such as nationality and profession (e.g., for a Canadian law professor named Michael Jackson, with no Wikipedia article, it is very hard to obtain reliable textual training data). The target property information for the entities is directly available from name authority files, or inferrable, e.g., from listings of sportspeople etc. Our proposed approach employs topic modeling to exploit textual training data based on entities sharing the relevant properties. In experiments with a pilot implementation of the general approach, we show that the approach does indeed work well for name/referent pairs with limited textual coverage in the training data.

We introduce a new approach to training a semantic parser that uses textual entailment judgements as supervision. These judgements are based on high-level inferences about whether the meaning of one sentence follows from another. When applied to an existing semantic parsing task, they prove to be a useful tool for revealing semantic distinctions and background knowledge not captured in the target representations. This information is used to improve the quality of the semantic representations being learned and to acquire generic knowledge for reasoning. Experiments are done on the benchmark Sportscaster corpus (Chen and Mooney, 2008), and a novel RTE-inspired inference dataset is introduced. On this new dataset our method strongly outperforms several strong baselines. Separately, we obtain state-of-the-art results on the original Sportscaster semantic parsing task.

We present ICARUS for intonation – a graphical tool which allows to access automatically derived F0 features in an intu-itive and user-friendly way. It can be used for data exploration and search. Tonal features can be accessed together with infor-mation from other linguistic levels; this is exemplified in two search queries where we combine the search for a specific tonal contour with a) coreference annotations and b) automatically derived syntactic annotations. Thereby we demonstrate how ICARUS for intonation bridges the gap between manual/semi-automatic analysis of relatively small, manually annotated data sets and automatic analysis of larger corpora with automatically derived features.

We investigate different ways of learning structured perceptron models for coreference resolution when using non-local features and beam search. Our experimental results indicate that standard techniques such as early updates or Learning as Search Optimization (LaSO) perform worse than a greedy baseline that only uses local features. By modifying LaSO to delay updates until the end of each instance we obtain significant improvements over the baseline. Our model obtains the best results to date on recent shared task data for Arabic, Chinese, and English.

Gregor Thiele, Wolfgang Seeker, Markus Gärtner, Anders Björkelund, Jonas Kuhn. Proceedings of the Demonstrations at the 14th Conference of the European Chapter of the Association for Computational Linguistics. 2014.

This short paper presents a pilot study investigating the training of a standard Semantic Role Labeling (SRL) system on product reviews for the new task of detecting comparisons.An (opinionated) comparison consists of a comparative "predicate" and up to three "arguments": the entity evaluated positively, the entity evaluated negatively, and the aspect under which the comparison is made.In user-generated product reviews, the "predicate" and "arguments" are expressed in highly heterogeneous ways; but since the elements are textually annotated in existing datasets, SRL is technically applicable.We address the interesting question how well training an outof-the-box SRL model works for English data.We observe that even without any feature engineering or other major adaptions to our task, the system outperforms a reasonable heuristic baseline in all steps (predicate identification, argument identification and argument classification) and in three different datasets.

Morphology and syntax interact considerably in many languages and language processing should pay attention to these interdependencies.We analyze the effect of syntactic features when used in automatic morphology prediction on four typologically different languages.We show that predicting morphology for languages with highly ambiguous word forms profits from taking the syntactic context of words into account and results in state-ofthe-art models.

Most morphologically rich languages with free word order use case systems to mark the grammatical function of nominal elements, especially for the core argument functions of a verb. The standard pipeline approach in syntactic dependency parsing assumes a complete disambiguation of morphological (case) information prior to automatic syntactic analysis. Parsing experiments on Czech, German, and Hungarian show that this approach is susceptible to propagating morphological annotation errors when parsing languages displaying syncretism in their morphological case paradigms. We develop a different architecture where we use case as a possibly underspecified filtering device restricting the options for syntactic analysis. Carefully designed morpho-syntactic constraints can delimit the search space of a statistical dependency parser and exclude solutions that would violate the restrictions overtly marked in the morphology of the words in a given sentence. The constrained system outperforms a state-of-the-art data-driven pipeline architecture, as we show experimentally, and, in addition, the parser output comes with guarantees about local and global morpho-syntactic wellformedness, which can be useful for downstream applications.

This paper discusses the use of statistical word alignment over multiple parallel texts for the identification of string spans that cannot be constituents in one of the languages. This information is exploited in monolingual PCFG grammar induction for that language, within an augmented version of the inside-outside algorithm. Besides the aligned corpus, no other resources are required. We discuss an implemented system and present experimental results with an evaluation against the Penn Tree-bank.

This paper proposes the application of finite-state approximation techniques on a unification-based grammar of word formation for a language like German. A refinement of an RTN-based approximation algorithm is proposed, which extends the state space of the automaton by selectively adding distinctions based on the parsing history at the point of entering a context-free rule. The selection of history items exploits the specific linguistic nature of word formation. As experiments show, this algorithm avoids an explosion of the size of the automaton in the approximation construction.

In Optimality-Theoretic Syntax, optimization with unrestricted expressive power on the side of the OT constraints is undecidable. This paper provides a proof for the decidability of optimization based on constraints expressed with reference to local subtrees (which is in the spirit of OT theory). The proof builds on Kaplan and Wedekind's (2000) construction showing that LFG generation produces context-free languages.

The Earley deduction algorithm is extended for the processing of OT syntax based on feature grammars. Due to faithfulness violations, infinitely many candidates must be compared. With the (reasonable) assumptions (i) that OT constraints are descriptions denoting bounded structures and (ii) that every rule recursion in the base grammar incurs some constraint violation, a chart algorithm can be devised. Interleaving parsing and generation permits the application of generation-based optimization even in the parsing task, i.e., for a string input.

We present a new approach to stochastic modeling of constraint-based grammars that is based on loglinear models and uses EM for estimation from unannotated data. The techniques are applied to an LFG grammar for German. Evaluation on an exact match task yields 86% precision for an ambiguity rate of 5.4, and 90% precision on a subcat frame match for an ambiguity rate of 25. Experimental comparison to training from a parsebank shows a 10% gain from EM training. Also, a new class-based grammar lexicalization is presented, showing a 10% gain over unlexicalized models.