One paper from DFKI-NLP authors has been accepted for publication as a Findings paper at EMNLP 2023, the 2023 Conference on Empirical Methods in Natural Language Processing. The conference is planned to be a hybrid meeting and will take place in Singapore, from Dec 6th to Dec 10th, 2023.

One paper from Cora4NLP researchers has been accepted for publication at KONVENS 2023, the 19th German Conference on Natural Language Processing. The conference will take place in Ingolstadt, Germany, from Sep 18th to Sep 22nd, 2023.

Two papers from Cora4NLP researchers have been accepted for publication at ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics. The conference is planned to be a hybrid meeting and will take place in Toronto, Canada, from Jul 9th through July 14th, 2023.

We are happy to announce that two papers from Cora4NLP members have been accepted for publication at the 17th Conference of the European Chapter of the Association for Computational Linguistics. The conference will take place from May2nd to May 6th, 2023.

One paper from Cora4NLP authors has been accepted for publication at CoNLL 2022, the SIGNLL Conference on Computational Natural Language Learning. The conference is co-located with EMNLP 2022 and planned to be a hybrid meeting.

While recently developed NLP explainability methods let us open the black box in various ways (Madsen et al., 2022), a missing ingredient in this endeavor is an interactive tool offering a conversational interface. Such a dialogue system can help users explore datasets and models with explanations in a contextualized manner, e.g. via clarification or follow-up questions, and through a natural language interface. We adapt the conversational explanation framework TalkToModel (Slack et al., 2022) to the NLP domain, add new NLP-specific operations such as free-text rationalization, and illustrate its generalizability on three NLP tasks (dialogue act classification, question answering, hate speech detection). To recognize user queries for explanations, we evaluate fine-tuned and few-shot prompting models and implement a novel Adapter-based approach. We then conduct two user studies on (1) the perceived correctness and helpfulness of the dialogues, and (2) the simulatability, i.e. how objectively helpful dialogical explanations are for humans in figuring out the model’s predicted label when it’s not shown. We found rationalization and feature attribution were helpful in explaining the model behavior. Moreover, users could more reliably predict the model outcome based on an explanation dialogue rather than one-off explanations.

The paper presents two multilingual coreference resolution systems submitted for the CRAC Shared Task 2023. The DFKI-Adapt system achieves 61.86 F1 score on the shared task test data, outperforming the official baseline by 4.9 F1 points. This system uses a combination of different features and training settings, including character embeddings, adapter modules, joint pre-training and loss-based re-training. We provide evaluation for each of the settings on 12 different datasets and compare the results. The other submission uses a novel approach that involves prompting for mention generation. Although the scores achieved by this model are lower compared to the baseline, the method shows a new way of approaching the coreference task and shows promising results with just five epochs of training.

Joint Entity and Relation Extraction (JERE) is an important research direction in Information Extraction (IE). Given the surprising performance with fine-tuning of pre-trained BERT in a wide range of NLP tasks, nowadays most studies for JERE are based on the BERT model. Rather than predicting a simple tag for each word, these approaches are usually forced to design complex tagging schemes, as they may have to extract entity-relation pairs which may overlap with others from the same sequence of word representations in a sentence. Recently, sequence-to-sequence (seq2seq) pre-trained BART models show better performance than BERT models in many NLP tasks. Importantly, a seq2seq BART model can simply generate sequences of (many) entity-relation triplets with its decoder, rather than just tag input words. In this paper, we present a new generative JERE framework based on pre-trained BART. Different from the basic seq2seq BART architecture: 1) our framework employs a constrained classifier which only predicts either a token of the input sentence or a relation in each decoding step, and 2) we reuse representations from the pre-trained BART encoder in the classifier instead of a newly trained weight matrix, as this better utilizes the knowledge of the pre-trained model and context-aware representations for classification, and empirically leads to better performance. In our experiments on the widely studied NYT and WebNLG datasets, we show that our approach outperforms previous studies and establishes a new state-of-the-art (92.91 and 91.37 F1 respectively in exact match evaluation).

Factuality can play an important role when automatically processing clinical text, as it makes a difference if particular symptoms are explicitly not present, possibly present, not mentioned, or affirmed. In most cases, a sufficient number of examples is necessary to handle such phenomena in a supervised machine learning setting. However, as clinical text might contain sensitive information, data cannot be easily shared. In the context of factuality detection, this work presents a simple solution using machine translation to translate English data to German to train a transformer-based factuality detection model.

In this paper we describe the task of adapting NLP models to dialogue processing in the emergency response domain. Our goal is to provide a recipe for building a system that performs dialogue act classification and domain-specific slot tagging while being efficient, flexible and robust. We show that adapter models (Pfeiffer et al., 2020) perform well in the emergency response domain and benefit from additional dialogue context and speaker information. Comparing adapters to standard fine-tuned Transformer models we show that they achieve competitive results and can easily accommodate new tasks without significant memory increase since the base model can be shared between the adapters specializing on different tasks. We also address the problem of scarce annotations in the emergency response domain and evaluate different data augmentation techniques in a low-resource setting.