Large Language Models have found application in various mundane and repetitive tasks including Human Resource (HR) support. We worked with the domain experts of a large multinational company to develop an HR support chatbot as an efficient and effective tool for addressing employee inquiries. We inserted a human-in-the-loop in various parts of the development cycles such as dataset collection, prompt optimization, and evaluation of generated output. By enhancing the LLM-driven chatbot’s response quality and exploring alternative retrieval methods, we have created an efficient, scalable, and flexible tool for HR professionals to address employee inquiries effectively. Our experiments and evaluation conclude that GPT-4 outperforms other models and can overcome inconsistencies in data through internal reasoning capabilities. Additionally, through expert analysis, we infer that reference-free evaluation metrics such as G-Eval and Prometheus demonstrate reliability closely aligned with that of human evaluation.

In today’s digital world, seeking answers to health questions on the Internet is a common practice. However, existing question answering (QA) systems often rely on using pre-selected and annotated evidence documents, thus making them inadequate for addressing novel questions. Our study focuses on the open-domain QA setting, where the key challenge is to first uncover relevant evidence in large knowledge bases. By utilizing the common retrieve-then-read QA pipeline and PubMed as a trustworthy collection of medical research documents, we answer health questions from three diverse datasets. We modify different retrieval settings to observe their influence on the QA pipeline’s performance, including the number of retrieved documents, sentence selection process, the publication year of articles, and their number of citations. Our results reveal that cutting down on the amount of retrieved documents and favoring more recent and highly cited documents can improve the final macro F1 score up to 10%. We discuss the results, highlight interesting examples, and outline challenges for future research, like managing evidence disagreement and crafting user-friendly explanations.

The task of text privatization using Differential Privacy has recently taken the form of text rewriting, in which an input text is obfuscated via the use of generative (large) language models. While these methods have shown promising results in the ability to preserve privacy, these methods rely on autoregressive models which lack a mechanism to contextualize the private rewriting process. In response to this, we propose DP-MLM, a new method for differentially private text rewriting based on leveraging masked language models (MLMs) to rewrite text in a semantically similar and obfuscated manner. We accomplish this with a simple contextualization technique, whereby we rewrite a text one token at a time. We find that utilizing encoder-only MLMs provides better utility preservation at lower 𝜀 levels, as compared to previous methods relying on larger models with a decoder. In addition, MLMs allow for greater customization of the rewriting mechanism, as opposed to generative approaches. We make the code for DP-MLM public and reusable, found at https://github.com/sjmeis/DPMLM.

In recent years, Large Language Models (LLMs) have demonstrated an impressive ability to encode knowledge during pre-training on large text corpora. They can leverage this knowledge for downstream tasks like question answering (QA), even in complex areas involving health topics. Considering their high potential for facilitating clinical work in the future, understanding the quality of encoded medical knowledge and its recall in LLMs is an important step forward. In this study, we examine the capability of LLMs to exhibit medical knowledge recall by constructing a novel dataset derived from systematic reviews – studies synthesizing evidence-based answers for specific medical questions. Through experiments on the new MedREQAL dataset, comprising question-answer pairs extracted from rigorous systematic reviews, we assess six LLMs, such as GPT and Mixtral, analyzing their classification and generation performance. Our experimental insights into LLM performance on the novel biomedical QA dataset reveal the still challenging nature of this task.

The application of Differential Privacy to Natural Language Processing techniques has emerged in relevance in recent years, with an increasing number of studies published in established NLP outlets. In particular, the adaptation of Differential Privacy for use in NLP tasks has first focused on the *word-level*, where calibrated noise is added to word embedding vectors to achieve “noisy” representations. To this end, several implementations have appeared in the literature, each presenting an alternative method of achieving word-level Differential Privacy. Although each of these includes its own evaluation, no comparative analysis has been performed to investigate the performance of such methods relative to each other. In this work, we conduct such an analysis, comparing seven different algorithms on two NLP tasks with varying hyperparameters, including the *epsilon* parameter, or privacy budget. In addition, we provide an in-depth analysis of the results with a focus on the privacy-utility trade-off, as well as open-source our implementation code for further reproduction. As a result of our analysis, we give insight into the benefits and challenges of word-level Differential Privacy, and accordingly, we suggest concrete steps forward for the research field.

In the digital age, seeking health advice on the Internet has become a common practice. At the same time, determining the trustworthiness of online medical content is increasingly challenging. Fact-checking has emerged as an approach to assess the veracity of factual claims using evidence from credible knowledge sources. To help advance automated Natural Language Processing (NLP) solutions for this task, in this paper we introduce a novel dataset HealthFC. It consists of 750 health-related claims in German and English, labeled for veracity by medical experts and backed with evidence from systematic reviews and clinical trials. We provide an analysis of the dataset, highlighting its characteristics and challenges. The dataset can be used for NLP tasks related to automated fact-checking, such as evidence retrieval, claim verification, or explanation generation. For testing purposes, we provide baseline systems based on different approaches, examine their performance, and discuss the findings. We show that the dataset is a challenging test bed with a high potential for future use.

Legal tasks and datasets are often used as benchmarks for the capabilities of language models. However, openly available annotated datasets are rare. In this paper, we introduce AGB-DE, a corpus of 3,764 clauses from German consumer contracts that have been annotated and legally assessed by legal experts. Together with the data, we present a first baseline for the task of detecting potentially void clauses, comparing the performance of an SVM baseline with three fine-tuned open language models and the performance of GPT-3.5. Our results show the challenging nature of the task, with no approach exceeding an F1-score of 0.54. While the fine-tuned models often performed better with regard to precision, GPT-3.5 outperformed the other approaches with regard to recall. An analysis of the errors indicates that one of the main challenges could be the correct interpretation of complex clauses, rather than the decision boundaries of what is permissible and what is not.

Scientific literature searches are often exploratory, whereby users are not yet familiar with a particular field or concept but are interested in learning more about it. However, existing systems for scientific literature search are typically tailored to keyword-based lookup searches, limiting the possibilities for exploration. We propose NLP-KG, a feature-rich system designed to support the exploration of research literature in unfamiliar natural language processing (NLP) fields. In addition to a semantic search, NLP-KG allows users to easily find survey papers that provide a quick introduction to a field of interest. Further, a Fields of Study hierarchy graph enables users to familiarize themselves with a field and its related areas. Finally, a chat interface allows users to ask questions about unfamiliar concepts or specific articles in NLP and obtain answers grounded in knowledge retrieved from scientific publications. Our system provides users with comprehensive exploration possibilities, supporting them in investigating the relationships between different fields, understanding unfamiliar concepts in NLP, and finding relevant research literature. Demo, video, and code are available at: https://github.com/NLP-Knowledge-Graph/NLP-KG-WebApp.

Applications of Differential Privacy (DP) in NLP must distinguish between the syntactic level on which a proposed mechanism operates, often taking the form of *word-level* or *document-level* privatization. Recently, several word-level *Metric* Differential Privacy approaches have been proposed, which rely on this generalized DP notion for operating in word embedding spaces. These approaches, however, often fail to produce semantically coherent textual outputs, and their application at the sentence- or document-level is only possible by a basic composition of word perturbations. In this work, we strive to address these challenges by operating *between* the word and sentence levels, namely with *collocations*. By perturbing n-grams rather than single words, we devise a method where composed privatized outputs have higher semantic coherence and variable length. This is accomplished by constructing an embedding model based on frequently occurring word groups, in which unigram words co-exist with bi- and trigram collocations. We evaluate our method in utility and privacy tests, which make a clear case for tokenization strategies beyond the word level.

The increasing rate at which scientific knowledge is discovered and health claims shared online has highlighted the importance of developing efficient fact-checking systems for scientific claims. The usual setting for this task in the literature assumes that the documents containing the evidence for claims are already provided and annotated or contained in a limited corpus. This renders the systems unrealistic for real-world settings where knowledge sources with potentially millions of documents need to be queried to find relevant evidence. In this paper, we perform an array of experiments to test the performance of open-domain claim verification systems. We test the final verdict prediction of systems on four datasets of biomedical and health claims in different settings. While keeping the pipeline’s evidence selection and verdict prediction parts constant, document retrieval is performed over three common knowledge sources (PubMed, Wikipedia, Google) and using two different information retrieval techniques. We show that PubMed works better with specialized biomedical claims, while Wikipedia is more suited for everyday health concerns. Likewise, BM25 excels in retrieval precision, while semantic search in recall of relevant evidence. We discuss the results, outline frequent retrieval patterns and challenges, and provide promising future directions.

Generating natural language text from graph-structured data is essential for conversational information seeking. Semantic triples derived from knowledge graphs can serve as a valuable source for grounding responses from conversational agents by providing a factual basis for the information they communicate. This is especially relevant in the context of large language models, which offer great potential for conversational interaction but are prone to hallucinating, omitting, or producing conflicting information. In this study, we conduct an empirical analysis of conversational large language models in generating natural language text from semantic triples. We compare four large language models of varying sizes with different prompting techniques. Through a series of benchmark experiments on the WebNLG dataset, we analyze the models’ performance and identify the most common issues in the generated predictions. Our findings show that the capabilities of large language models in triple verbalization can be significantly improved through few-shot prompting, post-processing, and efficient fine-tuning techniques, particularly for smaller models that exhibit lower zero-shot performance.

Conversational search systems enable information retrieval via natural language interactions, with the goal of maximizing users’ information gain over multiple dialogue turns. The increasing prevalence of conversational interfaces adopting this search paradigm challenges traditional information retrieval approaches, stressing the importance of better understanding the engineering process of developing these systems. We undertook a systematic literature review to investigate the links between theoretical studies and technical implementations of conversational search systems. Our review identifies real-world application scenarios, system architectures, and functional components. We consolidate our results by presenting a layered architecture framework and explaining the core functions of conversational search systems. Furthermore, we reflect on our findings in light of the rapid progress in large language models, discussing their capabilities, limitations, and directions for future research.

The task of fact-checking deals with assessing the veracity of factual claims based on credible evidence and background knowledge. In particular, scientific fact-checking is the variation of the task concerned with verifying claims rooted in scientific knowledge. This task has received significant attention due to the growing importance of scientific and health discussions on online platforms. Automated scientific fact-checking methods based on NLP can help combat the spread of misinformation, assist researchers in knowledge discovery, and help individuals understand new scientific breakthroughs. In this paper, we present a comprehensive survey of existing research in this emerging field and its related tasks. We provide a task description, discuss the construction process of existing datasets, and analyze proposed models and approaches. Based on our findings, we identify intriguing challenges and outline potential future directions to advance the field.

With the increasing number of clinical trial reports generated every day, it is becoming hard to keep up with novel discoveries that inform evidence-based healthcare recommendations. To help automate this process and assist medical experts, NLP solutions are being developed. This motivated the SemEval-2023 Task 7, where the goal was to develop an NLP system for two tasks: evidence retrieval and natural language inference from clinical trial data. In this paper, we describe our two developed systems. The first one is a pipeline system that models the two tasks separately, while the second one is a joint system that learns the two tasks simultaneously with a shared representation and a multi-task learning approach. The final system combines their outputs in an ensemble system. We formalize the models, present their characteristics and challenges, and provide an analysis of achieved results. Our system ranked 3rd out of 40 participants with a final submission.

As an efficient approach to understand, generate, and process natural language texts, research in natural language processing (NLP) has exhibited a rapid spread and wide adoption in recent years. Given the increasing research work in this area, several NLP-related approaches have been surveyed in the research community. However, a comprehensive study that categorizes established topics, identifies trends, and outlines areas for future research remains absent. Contributing to closing this gap, we have systematically classified and analyzed research papers in the ACL Anthology. As a result, we present a structured overview of the research landscape, provide a taxonomy of fields of study in NLP, analyze recent developments in NLP, summarize our findings, and highlight directions for future work.

Sentence embeddings enable us to capture the semantic similarity of short texts. Most sentence embedding models are trained for general semantic textual similarity tasks. Therefore, to use sentence embeddings in a particular domain, the model must be adapted to it in order to achieve good results. Usually, this is done by fine-tuning the entire sentence embedding model for the domain of interest. While this approach yields state-of-the-art results, all of the model’s weights are updated during fine-tuning, making this method resource-intensive. Therefore, instead of fine-tuning entire sentence embedding models for each target domain individually, we propose to train lightweight adapters. These domain-specific adapters do not require fine-tuning all underlying sentence embedding model parameters. Instead, we only train a small number of additional parameters while keeping the weights of the underlying sentence embedding model fixed. Training domain-specific adapters allows always using the same base model and only exchanging the domain-specific adapters to adapt sentence embeddings to a specific domain. We show that using adapters for parameter-efficient domain adaptation of sentence embeddings yields competitive performance within 1% of a domain-adapted, entirely fine-tuned sentence embedding model while only training approximately 3.6% of the parameters.

Generic sentence embeddings provide coarse-grained approximation of semantic textual similarity, but ignore specific aspects that make texts similar. Conversely, aspect-based sentence embeddings provide similarities between texts based on certain predefined aspects. Thus, similarity predictions of texts are more targeted to specific requirements and more easily explainable. In this paper, we present AspectCSE, an approach for aspect-based contrastive learning of sentence embeddings. Results indicate that AspectCSE achieves an average improvement of 3.97% on information retrieval tasks across multiple aspects compared to the previous best results. We also propose the use of Wikidata knowledge graph properties to train models of multi-aspect sentence embeddings in which multiple specific aspects are simultaneously considered during similarity predictions. We demonstrate that multi-aspect embeddings outperform even single-aspect embeddings on aspect-specific information retrieval tasks. Finally, we examine the aspect-based sentence embedding space and demonstrate that embeddings of semantically similar aspect labels are often close, even without explicit similarity training between different aspect labels.

As the tide of Big Data continues to influence the landscape of Natural Language Processing (NLP), the utilization of modern NLP methods has grounded itself in this data, in order to tackle a variety of text-based tasks. These methods without a doubt can include private or otherwise personally identifiable information. As such, the question of privacy in NLP has gained fervor in recent years, coinciding with the development of new Privacy- Enhancing Technologies (PETs). Among these PETs, Differential Privacy boasts several desirable qualities in the conversation surrounding data privacy. Naturally, the question becomes whether Differential Privacy is applicable in the largely unstructured realm of NLP. This topic has sparked novel research, which is unified in one basic goal how can one adapt Differential Privacy to NLP methods? This paper aims to summarize the vulnerabilities addressed by Differential Privacy, the current thinking, and above all, the crucial next steps that must be considered.

The automated analysis of Terms and Conditions has gained attention in recent years, mainly due to its relevance to consumer protection. Well-structured data sets are the base for every analysis. While content extraction, in general, is a well-researched field and many open source libraries are available, our evaluation shows, that existing solutions cannot extract Terms and Conditions in sufficient quality, mainly because of their special structure. In this paper, we present an approach to extract the content and hierarchy of Terms and Conditions from German and English online shops. Our evaluation shows, that the approach outperforms the current state of the art. A python implementation of the approach is made available under an open license.

So-called standard form contracts, i.e. contracts that are drafted unilaterally by one party, like terms and conditions of online shops or terms of services of social networks, are cornerstones of our modern economy. Their processing is, therefore, of significant practical value. Often, the sheer size of these contracts allows the drafting party to hide unfavourable terms from the other party. In this paper, we compare different approaches for automatically classifying the topics of clauses in standard form contracts, based on a data-set of more than 6,000 clauses from more than 170 contracts, which we collected from German and English online shops and annotated based on a taxonomy of clause topics, that we developed together with legal experts. We will show that, in our comparison of seven approaches, from simple keyword matching to transformer language models, BERT performed best with an F1-score of up to 0.91, however much simpler and computationally cheaper models like logistic regression also achieved similarly good results of up to 0.87.

The task of quantifying the complexity of written language presents an interesting endeavor, particularly in the opportunity that it presents for aiding language learners. In this pursuit, the question of what exactly about natural language contributes to its complexity (or lack thereof) is an interesting point of investigation. We propose a hybrid approach, utilizing shallow models to capture linguistic features, while leveraging a fine-tuned embedding model to encode the semantics of input text. By harmonizing these two methods, we achieve competitive scores in the given metric, and we demonstrate improvements over either singular method. In addition, we uncover the effectiveness of Gaussian processes in the training of shallow models for text complexity analysis.

In pace with developments in the research field of artificial intelligence, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry. As a representation of semantic relations between entities, KGs have proven to be particularly relevant for natural language processing (NLP), experiencing a rapid spread and wide adoption within recent years. Given the increasing amount of research work in this area, several KG-related approaches have been surveyed in the NLP research community. However, a comprehensive study that categorizes established topics and reviews the maturity of individual research streams remains absent to this day. Contributing to closing this gap, we systematically analyzed 507 papers from the literature on KGs in NLP. Our survey encompasses a multifaceted review of tasks, research types, and contributions. As a result, we present a structured overview of the research landscape, provide a taxonomy of tasks, summarize our findings, and highlight directions for future work.

Online shopping is an ever more important part of the global consumer economy, not just in times of a pandemic. When we place an order online as consumers, we regularly agree to the so-called “Terms and Conditions” (T&C), a contract unilaterally drafted by the seller. Often, consumers do not read these contracts and unwittingly agree to unfavourable and often void terms. Government and non-government organisations (NGOs) for consumer protection battle such terms on behalf of consumers, who often hesitate to take on legal actions themselves. However, the growing number of online shops and a lack of funding makes it increasingly difficult for such organisations to monitor the market effectively. This paper describes how Natural Language Processing (NLP) can be applied to support consumer advocates in their efforts to protect consumers. Together with two NGOs from Germany, we developed an NLP-based application that legally assesses clauses in T&C from German online shops under the European Union’s (EU) jurisdiction. We report that we could achieve an accuracy of 0.9 in the detection of void clauses by fine-tuning a pre-trained German BERT model. The approach is currently used by two NGOs and has already helped to challenge void clauses in T&C.

Historically speaking, the German legal language is widely neglected in NLP research, especially in summarization systems, as most of them are based on English newspaper articles. In this paper, we propose the task of automatic summarization of German court rulings. Due to their complexity and length, it is of critical importance that legal practitioners can quickly identify the content of a verdict and thus be able to decide on the relevance for a given legal case. To tackle this problem, we introduce a new dataset consisting of 100k German judgments with short summaries. Our dataset has the highest compression ratio among the most common summarization datasets. German court rulings contain much structural information, so we create a pre-processing pipeline tailored explicitly to the German legal domain. Additionally, we implement multiple extractive as well as abstractive summarization systems and build a wide variety of baseline models. Our best model achieves a ROUGE-1 score of 30.50. Therefore with this work, we are laying the crucial groundwork for further research on German summarization systems.

Language resources for languages other than English are often scarce. Rule-based surface realisers need elaborate lexica in order to be able to generate correct language, especially in languages like German, which include many irregular word forms. In this paper, we present MucLex, a German lexicon for the Natural Language Generation task of surface realisation, based on the crowd-sourced online lexicon Wiktionary. MucLex contains more than 100,000 lemmata and more than 670,000 different word forms in a well-structured XML file and is available under the Creative Commons BY-SA 3.0 license.

SimpleNLG is a popular open source surface realiser for the English language. For German, however, the availability of open source and non-domain specific realisers is sparse, partly due to the complexity of the German language. In this paper, we present SimpleNLG-DE, an adaption of SimpleNLG to German. We discuss which parts of the German language have been implemented and how we evaluated our implementation using the TIGER Corpus and newly created data-sets.

Every time we buy something online, we are confronted with Terms of Services. However, only a few people actually read these terms, before accepting them, often to their disadvantage. In this paper, we present the SaToS browser plugin which summarises and simplifies Terms of Services from German webshops.

Conversational interfaces recently gained a lot of attention. One of the reasons for the current hype is the fact that chatbots (one particularly popular form of conversational interfaces) nowadays can be created without any programming knowledge, thanks to different toolkits and so-called Natural Language Understanding (NLU) services. While these NLU services are already widely used in both, industry and science, so far, they have not been analysed systematically. In this paper, we present a method to evaluate the classification performance of NLU services. Moreover, we present two new corpora, one consisting of annotated questions and one consisting of annotated questions with the corresponding answers. Based on these corpora, we conduct an evaluation of some of the most popular NLU services. Thereby we want to enable both, researchers and companies to make more educated decisions about which service they should use.