Classification is a core NLP task architecture with many potential applications. While large language models (LLMs) have brought substantial advancements in text generation, their potential for enhancing classification tasks remains underexplored. To address this gap, we propose a framework for thoroughly investigating fine-tuning LLMs for classification, including both generation- and encoding-based approaches. We instantiate this framework in edit intent classification (EIC), a challenging and underexplored classification task. Our extensive experiments and systematic comparisons with various training approaches and a representative selection of LLMs yield new insights into their application for EIC. We investigate the generalizability of these findings on five further classification tasks. To demonstrate the proposed methods and address the data shortage for empirical edit analysis, we use our best-performing EIC model to create Re3-Sci2.0, a new large-scale dataset of 1,780 scientific document revisions with over 94k labeled edits. The quality of the dataset is assessed through human evaluation. The new dataset enables an in-depth empirical study of human editing behavior in academic writing. We make our experimental framework, models and data publicly available.

Generalization and robustness to input variation are core desiderata of machine learning research. Language varies along several axes, most importantly, language instance (e.g. French) and domain (e.g. news). While adapting NLP models to new languages within a single domain, or to new domains within a single language, is widely studied, research in joint adaptation is hampered by the lack of evaluation datasets. This prevents the transfer of NLP systems from well-resourced languages and domains to non-dominant language-domain combinations. To address this gap, we introduce M2QA, a multi-domain multilingual question answering benchmark.M2QA includes 13,500 SQuAD 2.0-style question-answer instances in German, Turkish, and Chinese for the domains of product reviews, news, and creative writing. We use M2QA to explore cross-lingual cross-domain performance of fine-tuned models and state-of-the-art LLMs and investigate modular approaches to domain and language adaptation.We witness **1)** considerable performance _variations_ across domain-language combinations within model classes and **2)** considerable performance _drops_ between source and target language-domain combinations across all model sizes. We demonstrate that M2QA is far from solved, and new methods to effectively transfer both linguistic and domain-specific information are necessary.

Long documents often exhibit structure with hierarchically organized elements of different functions, such as section headers and paragraphs. Despite the omnipresence of document structure, its role in natural language processing (NLP) remains opaque. Do long-document Transformer models acquire an internal representation of document structure during pre-training? How can structural information be communicated to a model after pre-training, and how does it influence downstream performance? To answer these questions, we develop a novel suite of probing tasks to assess structure-awareness of long-document Transformers, propose general-purpose structure infusion methods, and evaluate the effects of structure infusion on QASPER and Evidence Inference, two challenging long-document NLP tasks. Results on LED and LongT5 suggest that they acquire implicit understanding of document structure during pre-training, which can be further enhanced by structure infusion, leading to improved end-task performance. To foster research on the role of document structure in NLP modeling, we make our data and code publicly available.

Collaborative review and revision of textual documents is the core of knowledge work and a promising target for empirical analysis and NLP assistance. Yet, a holistic framework that would allow modeling complex relationships between document revisions, reviews and author responses is lacking. To address this gap, we introduce Re3, a framework for joint analysis of collaborative document revision. We instantiate this framework in the scholarly domain, and present Re3-Sci, a large corpus of aligned scientific paper revisions manually labeled according to their action and intent, and supplemented with the respective peer reviews and human-written edit summaries. We use the new data to provide first empirical insights into collaborative document revision in the academic domain, and to assess the capabilities of state-of-the-art LLMs at automating edit analysis and facilitating text-based collaboration. We make our annotation environment and protocols, the resulting data and experimental code publicly available.

Large language models (LLMs) bring unprecedented flexibility in defining and executing complex, creative natural language generation (NLG) tasks. Yet, this flexibility brings new challenges, as it introduces new degrees of freedom in formulating the task inputs and instructions and in evaluating model performance. To facilitate the exploration of creative NLG tasks, we propose a three-component research framework that consists of systematic input manipulation, reference data, and output measurement. We use this framework to explore citation text generation – a popular scholarly NLP task that lacks consensus on the task definition and evaluation metric and has not yet been tackled within the LLM paradigm. Our results highlight the importance of systematically investigating both task instruction and input configuration when prompting LLMs, and reveal non-trivial relationships between different evaluation metrics used for citation text generation. Additional human generation and human evaluation experiments provide new qualitative insights into the task to guide future research in citation text generation. We make our code and data publicly available.

Peer review constitutes a core component of scholarly publishing; yet it demands substantial expertise and training, and is susceptible to errors and biases. Various applications of NLP for peer reviewing assistance aim to support reviewers in this complex process, but the lack of clearly licensed datasets and multi-domain corpora prevent the systematic study of NLP for peer review. To remedy this, we introduce NLPeer– the first ethically sourced multidomain corpus of more than 5k papers and 11k review reports from five different venues. In addition to the new datasets of paper drafts, camera-ready versions and peer reviews from the NLP community, we establish a unified data representation and augment previous peer review datasets to include parsed and structured paper representations, rich metadata and versioning information. We complement our resource with implementations and analysis of three reviewing assistance tasks, including a novel guided skimming task. Our work paves the path towards systematic, multi-faceted, evidence-based study of peer review in NLP and beyond. The data and code are publicly available.

Natural language processing (NLP) researchers develop models of grammar, meaning and communication based on written text. Due to task and data differences, what is considered text can vary substantially across studies. A conceptual framework for systematically capturing these differences is lacking. We argue that clarity on the notion of text is crucial for reproducible and generalizable NLP. Towards that goal, we propose common terminology to discuss the production and transformation of textual data, and introduce a two-tier taxonomy of linguistic and non-linguistic elements that are available in textual sources and can be used in NLP modeling. We apply this taxonomy to survey existing work that extends the notion of text beyond the conservative language-centered view. We outline key desiderata and challenges of the emerging inclusive approach to text in NLP, and suggest community-level reporting as a crucial next step to consolidate the discussion.

Recent years have seen impressive progress in AI-assisted writing, yet the developments in AI-assisted reading are lacking. We propose inline commentary as a natural vehicle for AI-based reading assistance, and present CARE: the first open integrated platform for the study of inline commentary and reading. CARE facilitates data collection for inline commentaries in a commonplace collaborative reading environment, and provides a framework for enhancing reading with NLP-based assistance, such as text classification, generation or question answering. The extensible behavioral logging allows unique insights into the reading and commenting behavior, and flexible configuration makes the platform easy to deploy in new scenarios. To evaluate CARE in action, we apply the platform in a user study dedicated to scholarly peer review. CARE facilitates the data collection and study of inline commentary in NLP, extrinsic evaluation of NLP assistance, and application prototyping. We invite the community to explore and build upon the open source implementation of CARE.Github Repository: https://github.com/UKPLab/CAREPublic Live Demo: https://care.ukp.informatik.tu-darmstadt.de

Science progresses by building upon the prior body of knowledge documented in scientific publications. The acceleration of research makes it hard to stay up-to-date with the recent developments and to summarize the ever-growing body of prior work. To address this, the task of citation text generation aims to produce accurate textual summaries given a set of papers-to-cite and the citing paper context. Due to otherwise rare explicit anchoring of cited documents in the citing paper, citation text generation provides an excellent opportunity to study how humans aggregate and synthesize textual knowledge from sources. Yet, existing studies are based upon widely diverging task definitions, which makes it hard to study this task systematically. To address this challenge, we propose CiteBench: a benchmark for citation text generation that unifies multiple diverse datasets and enables standardized evaluation of citation text generation models across task designs and domains. Using the new benchmark, we investigate the performance of multiple strong baselines, test their transferability between the datasets, and deliver new insights into the task definition and evaluation to guide future research in citation text generation. We make the code for CiteBench publicly available at https://github.com/UKPLab/citebench.

Peer review is the key quality control mechanism in science. The core component of peer review are the review reports – argumentative texts where the reviewers evaluate the work and make suggestions to the authors. Reviewing is a demanding expert task prone to bias. An active line of research in NLP aims to support peer review via automatic analysis of review reports. This research meets two key challenges. First, NLP to date has focused on peer reviews from machine learning conferences. Yet, NLP models are prone to domain shift and might underperform when applied to reviews from a new research community. Second, while some venues make their reviewing processes public, peer reviewing data is generally hard to obtain and expensive to label. Approaches to low-data NLP processing for peer review remain under-investigated. Enabled by the recent release of open multi-domain corpora of peer reviews, the PragTag-2023 Shared Task explored the ways to increase domain robustness and address data scarcity in pragmatic tagging – a sentence tagging task where review statements are classified by their argumentative function. This paper describes the shared task, outlines the participating systems, and summarizes the results.

The shift towards publicly available text sources has enabled language processing at unprecedented scale, yet leaves under-serviced the domains where public and openly licensed data is scarce. Proactively collecting text data for research is a viable strategy to address this scarcity, but lacks systematic methodology taking into account the many ethical, legal and confidentiality-related aspects of data collection. Our work presents a case study on proactive data collection in peer review – a challenging and under-resourced NLP domain. We outline ethical and legal desiderata for proactive data collection and introduce “Yes-Yes-Yes”, the first donation-based peer reviewing data collection workflow that meets these requirements. We report on the implementation of Yes-Yes-Yes at ACL Rolling Review and empirically study the implications of proactive data collection for the dataset size and the biases induced by the donation behavior on the peer reviewing platform.

Peer review is a key component of the publishing process in most fields of science. Increasing submission rates put a strain on reviewing quality and efficiency, motivating the development of applications to support the reviewing and editorial work. While existing NLP studies focus on the analysis of individual texts, editorial assistance often requires modeling interactions between pairs of texts—yet general frameworks and datasets to support this scenario are missing. Relationships between texts are the core object of the intertextuality theory—a family of approaches in literary studies not yet operationalized in NLP. Inspired by prior theoretical work, we propose the first intertextual model of text-based collaboration, which encompasses three major phenomena that make up a full iteration of the review–revise–and–resubmit cycle: pragmatic tagging, linking, and long-document version alignment. While peer review is used across the fields of science and publication formats, existing datasets solely focus on conference-style review in computer science. Addressing this, we instantiate our proposed model in the first annotated multidomain corpus in journal-style post-publication open peer review, and provide detailed insights into the practical aspects of intertextual annotation. Our resource is a major step toward multidomain, fine-grained applications of NLP in editorial support for peer review, and our intertextual framework paves the path for general-purpose modeling of text-based collaboration. We make our corpus, detailed annotation guidelines, and accompanying code publicly available.1

Despite an ever-growing number of word representation models introduced for a large number of languages, there is a lack of a standardized technique to provide insights into what is captured by these models. Such insights would help the community to get an estimate of the downstream task performance, as well as to design more informed neural architectures, while avoiding extensive experimentation that requires substantial computational resources not all researchers have access to. A recent development in NLP is to use simple classification tasks, also called probing tasks, that test for a single linguistic feature such as part-of-speech. Existing studies mostly focus on exploring the linguistic information encoded by the continuous representations of English text. However, from a typological perspective the morphologically poor English is rather an outlier: The information encoded by the word order and function words in English is often stored on a subword, morphological level in other languages. To address this, we introduce 15 type-level probing tasks such as case marking, possession, word length, morphological tag count, and pseudoword identification for 24 languages. We present a reusable methodology for creation and evaluation of such tests in a multilingual setting, which is challenging because of a lack of resources, lower quality of tools, and differences among languages. We then present experiments on several diverse multilingual word embedding models, in which we relate the probing task performance for a diverse set of languages to a range of five classic NLP tasks: POS-tagging, dependency parsing, semantic role labeling, named entity recognition, and natural language inference. We find that a number of probing tests have significantly high positive correlation to the downstream tasks, especially for morphologically rich languages. We show that our tests can be used to explore word embeddings or black-box neural models for linguistic cues in a multilingual setting. We release the probing data sets and the evaluation suite LINSPECTOR with https://github.com/UKPLab/linspector.

Deep pre-trained contextualized encoders like BERT demonstrate remarkable performance on a range of downstream tasks. A recent line of research in probing investigates the linguistic knowledge implicitly learned by these models during pre-training. While most work in probing operates on the task level, linguistic tasks are rarely uniform and can be represented in a variety of formalisms. Any linguistics-based probing study thereby inevitably commits to the formalism used to annotate the underlying data. Can the choice of formalism affect probing results? To investigate, we conduct an in-depth cross-formalism layer probing study in role semantics. We find linguistically meaningful differences in the encoding of semantic role- and proto-role information by BERT depending on the formalism and demonstrate that layer probing can detect subtle differences between the implementations of the same linguistic formalism. Our results suggest that linguistic formalism is an important dimension in probing studies, along with the commonly used cross-task and cross-lingual experimental settings.

Peer review is a core element of the scientific process, particularly in conference-centered fields such as ML and NLP. However, only few studies have evaluated its properties empirically. Aiming to fill this gap, we present a corpus that contains over 4k reviews and 1.2k author responses from ACL-2018. We quantitatively and qualitatively assess the corpus. This includes a pilot study on paper weaknesses given by reviewers and on quality of author responses. We then focus on the role of the rebuttal phase, and propose a novel task to predict after-rebuttal (i.e., final) scores from initial reviews and author responses. Although author responses do have a marginal (and statistically significant) influence on the final scores, especially for borderline papers, our results suggest that a reviewer’s final score is largely determined by her initial score and the distance to the other reviewers’ initial scores. In this context, we discuss the conformity bias inherent to peer reviewing, a bias that has largely been overlooked in previous research. We hope our analyses will help better assess the usefulness of the rebuttal phase in NLP conferences.

Thematic role hierarchy is a widely used linguistic tool to describe interactions between semantic roles and their syntactic realizations. Despite decades of dedicated research and numerous thematic hierarchy suggestions in the literature, this concept has not been used in NLP so far due to incompatibility and limited scope of existing hierarchies. We introduce an empirical framework for thematic hierarchy induction and evaluate several role ranking strategies on English and German full-text corpus data. We hypothesize that global thematic hierarchy induction is feasible, that a hierarchy can be induced from just fractions of training data and that resulting hierarchies apply cross-lingually. We evaluate these assumptions empirically.

Distributional word representations (often referred to as word embeddings) are omnipresent in modern NLP. Early work has focused on building representations for word types, and recent studies show that lemmatization and part of speech (POS) disambiguation of targets in isolation improve the performance of word embeddings on a range of downstream tasks. However, the reasons behind these improvements, the qualitative effects of these operations and the combined performance of lemmatized and POS disambiguated targets are less studied. This work aims to close this gap and puts previous findings into a general perspective. We examine the effect of lemmatization and POS typing on word embedding performance in a novel resource-based evaluation scenario, as well as on standard similarity benchmarks. We show that these two operations have complimentary qualitative and vocabulary-level effects and are best used in combination. We find that the improvement is more pronounced for verbs and show how lemmatization and POS typing implicitly target some of the verb-specific issues. We claim that the observed improvement is a result of better conceptual alignment between word embeddings and lexical resources, stressing the need for conceptually plausible modeling of word embedding targets.

This paper describes our approach to the SemEval 2017 Task 10: Extracting Keyphrases and Relations from Scientific Publications, specifically to Subtask (B): Classification of identified keyphrases. We explored three different deep learning approaches: a character-level convolutional neural network (CNN), a stacked learner with an MLP meta-classifier, and an attention based Bi-LSTM. From these approaches, we created an ensemble of differently hyper-parameterized systems, achieving a micro-F₁-score of 0.63 on the test data. Our approach ranks 2nd (score of 1st placed system: 0.64) out of four according to this official score. However, we erroneously trained 2 out of 3 neural nets (the stacker and the CNN) on only roughly 15% of the full data, namely, the original development set. When trained on the full data (training+development), our ensemble has a micro-F₁-score of 0.69. Our code is available from https://github.com/UKPLab/semeval2017-scienceie.

Domain dependence of NLP systems is one of the major obstacles to their application in large-scale text analysis, also restricting the applicability of FrameNet semantic role labeling (SRL) systems. Yet, current FrameNet SRL systems are still only evaluated on a single in-domain test set. For the first time, we study the domain dependence of FrameNet SRL on a wide range of benchmark sets. We create a novel test set for FrameNet SRL based on user-generated web text and find that the major bottleneck for out-of-domain FrameNet SRL is the frame identification step. To address this problem, we develop a simple, yet efficient system based on distributed word representations. Our system closely approaches the state-of-the-art in-domain while outperforming the best available frame identification system out-of-domain. We publish our system and test data for research purposes.

We present the first experiment-based study that explicitly contrasts the three major semantic role labeling frameworks. As a prerequisite, we create a dataset labeled with parallel FrameNet-, PropBank-, and VerbNet-style labels for German. We train a state-of-the-art SRL tool for German for the different annotation styles and provide a comparative analysis across frameworks. We further explore the behavior of the frameworks with automatic training data generation. VerbNet provides larger semantic expressivity than PropBank, and we find that its generalization capacity approaches PropBank in SRL training, but it benefits less from training data expansion than the sparse-data affected FrameNet.