Search Results for author:
Found 326 papers, 173 papers with code
IMPLI: Investigating NLI Models’ Performance on Figurative Language
Natural language inference (NLI) has been widely used as a task to train and evaluate models for language understanding.
Human-In-The-LoopEntity Linking for Low Resource Domains
Entity linking (EL) is concerned with disambiguating entity mentions in a text against knowledge bases (KB).
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning
Learning sentence embeddings often requires a large amount of labeled data.
A Neural Graph-based Local Coherence Model
Entity grids and entity graphs are two frameworks for modeling local coherence.
Evaluating Coreference Resolvers on Community-based Question Answering: From Rule-based to State of the Art
The results of our extrinsic evaluation show that while there is a significant difference between the performance of the rule-based system vs. state-of-the-art neural model on coreference resolution datasets, we do not observe a considerable difference on their impact on downstream models.
Event Coreference Data (Almost) for Free: Mining Hyperlinks from Online News
Cross-document event coreference resolution (CDCR) is the task of identifying which event mentions refer to the same events throughout a collection of documents.
Composing Structure-Aware Batches for Pairwise Sentence Classification
Identifying the relation between two sentences requires datasets with pairwise annotations.
Exploring Metaphoric Paraphrase Generation
Metaphor generation is a difficult task, and has seen tremendous improvement with the advent of deep pretrained models.
Constrained C-Test Generation via Mixed-Integer Programming
This work proposes a novel method to generate C-Tests; a deviated form of cloze tests (a gap filling exercise) where only the last part of a word is turned into a gap.
Early Period of Training Impacts Out-of-Distribution Generalization
Prior research has found that differences in the early period of neural network training significantly impact the performance of in-distribution (ID) tasks.
Multimodal Large Language Models to Support Real-World Fact-Checking
To the best of our knowledge, we are the first to evaluate MLLMs for real-world fact-checking.
IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators
In particular, most mainstream Code-LMs have been pre-trained on source code files alone.
Socratic Reasoning Improves Positive Text Rewriting
In this work, we address this gap by augmenting open-source datasets for positive text rewriting with synthetically-generated Socratic rationales using a novel framework called \textsc{SocraticReframe}.
Variational Learning is Effective for Large Deep Networks
We give extensive empirical evidence against the common belief that variational learning is ineffective for large neural networks.
Triple-Encoders: Representations That Fire Together, Wire Together
Search-based dialog models typically re-encode the dialog history at every turn, incurring high cost.
M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection
The advent of Large Language Models (LLMs) has brought an unprecedented surge in machine-generated text (MGT) across diverse channels.
Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon
Improving multilingual language models capabilities in low-resource languages is generally difficult due to the scarcity of large-scale data in those languages.
Dive into the Chasm: Probing the Gap between In- and Cross-Topic Generalization
Pre-trained language models (LMs) perform well in In-Topic setups, where training and testing data come from the same topics.
Document Structure in Long Document Transformers
Long documents often exhibit structure with hierarchically organized elements of different functions, such as section headers and paragraphs.
Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs
Reasoning is a fundamental component of language understanding.
Learning from Emotions, Demographic Information and Implicit User Feedback in Task-Oriented Document-Grounded Dialogues
The success of task-oriented and document-grounded dialogue systems depends on users accepting and enjoying using them.
Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning
We introduce Adapters, an open-source library that unifies parameter-efficient and modular transfer learning in large language models.
Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers
The increased use of large language models (LLMs) across a variety of real-world applications calls for mechanisms to verify the factual accuracy of their outputs.
A Survey of Confidence Estimation and Calibration in Large Language Models
Assessing their confidence and calibrating them across different tasks can help mitigate risks and enable LLMs to produce better generations.
How are Prompts Different in Terms of Sensitivity?
In-context learning (ICL) has become one of the most popular learning paradigms.
A Template Is All You Meme
Here, to aid understanding of memes, we release a knowledge base of memes and information found on www. knowyourmeme. com, which we call the Know Your Meme Knowledge Base (KYMKB), composed of more than 54, 000 images.
Exploring Jiu-Jitsu Argumentation for Writing Peer Review Rebuttals
In this work, we are the first to explore Jiu-Jitsu argumentation for peer review by proposing the novel task of attitude and theme-guided rebuttal generation.
AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification
As a solution, we propose AdaSent, which decouples SEPT from DAPT by training a SEPT adapter on the base PLM.
Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones?
Learning from free-text human feedback is essential for dialog systems, but annotated data is scarce and usually covers only a small fraction of error types known in conversational AI.
Model Merging by Uncertainty-Based Gradient Matching
Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail?
Measuring Pointwise $\mathcal{V}$-Usable Information In-Context-ly
In-context learning (ICL) is a new learning paradigm that has gained popularity along with the development of large language models.
How to Handle Different Types of Out-of-Distribution Scenarios in Computational Argumentation? A Comprehensive and Fine-Grained Field Study
Our findings challenge the previously asserted general superiority of in-context learning (ICL) for OOD.
Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings
Large language models (LLMs) are highly adept at question answering and reasoning tasks, but when reasoning in a situational context, human expectations vary depending on the relevant cultural common ground.
CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration
In recent years, large language models (LLMs) have shown remarkable capabilities at scale, particularly at generating text conditioned on a prompt.
Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting
However, the available NLP literature disagrees on the efficacy of this technique - it remains unclear for which tasks and scenarios it can help, and the role of the individual factors in sociodemographic prompting is still unexplored.
Are Emergent Abilities in Large Language Models just In-Context Learning?
Large language models have exhibited emergent abilities, demonstrating exceptional performance across diverse tasks for which they were not explicitly trained, including those that require complex reasoning abilities.
SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval
In this work, we provide SPRINT, a unified Python toolkit based on Pyserini and Lucene, supporting a common interface for evaluating neural sparse retrieval.
Analyzing Dataset Annotation Quality Management in the Wild
A majority of the annotated publications apply good or excellent quality management.
Surveying (Dis)Parities and Concerns of Compute Hungry NLP Research
Many recent improvements in NLP stem from the development and use of large pre-trained language models (PLMs) with billions of parameters.
UKP-SQuARE: An Interactive Tool for Teaching Question Answering
To evaluate the effectiveness of UKP-SQuARE in teaching scenarios, we adopted it in a postgraduate NLP course and surveyed the students after the course.
Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generation
These models also suffer from posterior collapse, i. e., the decoder tends to ignore latent variables and directly access information captured in the encoder through the cross-attention mechanism.
M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection
These results show that the problem is far from solved and that there is a lot of room for improvement.
MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems
While automatic dialogue tutors hold great potential in making education personalized and more accessible, research on such systems has been hampered by a lack of sufficiently large and high-quality datasets.
DAPR: A Benchmark on Document-Aware Passage Retrieval
This drives us to build a benchmark for this task including multiple datasets from heterogeneous domains.
A Diachronic Analysis of Paradigm Shifts in NLP Research: When, How, and Why?
In this study, we propose a systematic framework for analyzing the evolution of research topics in a scientific field using causal discovery and inference techniques.
Learning to Reason over Scene Graphs: A Case Study of Finetuning GPT-2 into a Robot Language Model for Grounded Task Planning
Long-horizon task planning is essential for the development of intelligent assistive and service robots.
Lessons Learned from a Citizen Science Project for Natural Language Processing
Citizen Science is an alternative to crowdsourcing that is relatively unexplored in the context of NLP.
Romanization-based Large-scale Adaptation of Multilingual Language Models
In order to boost the capacity of mPLMs to deal with low-resource and unseen languages, we explore the potential of leveraging transliteration on a massive scale.
UKP-SQuARE v3: A Platform for Multi-Agent QA Research
To ease research in multi-agent models, we extend UKP-SQuARE, an online platform for QA research, to support three families of multi-agent systems: i) agent selection, ii) early-fusion of agents, and iii) late-fusion of agents.
Elastic Weight Removal for Faithful and Abstractive Dialogue Generation
We evaluate our method -- using different variants of Flan-T5 as a backbone language model -- on multiple datasets for information-seeking dialogue generation and compare our method with state-of-the-art techniques for faithfulness, such as CTRL, Quark, DExperts, and Noisy Channel reranking.
Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence Embeddings
Training and inference on edge devices often requires an efficient setup due to computational limitations.
CARE: Collaborative AI-Assisted Reading Environment
Recent years have seen impressive progress in AI-assisted writing, yet the developments in AI-assisted reading are lacking.
Like a Good Nearest Neighbor: Practical Content Moderation and Text Classification
Few-shot text classification systems have impressive capabilities but are infeasible to deploy and use reliably due to their dependence on prompting and billion-parameter language models.
Opportunities and Challenges in Neural Dialog Tutoring
Designing dialog tutors has been challenging as it involves modeling the diverse and complex pedagogical strategies employed by human tutors.
FUN with Fisher: Improving Generalization of Adapter-Based Cross-lingual Transfer with Scheduled Unfreezing
Our experiments reveal that scheduled unfreezing induces different learning dynamics compared to standard fine-tuning, and provide evidence that the dynamics of Fisher Information during training correlate with cross-lingual generalization performance.
Python Code Generation by Asking Clarification Questions
We hypothesize that the under-specification of a natural language description can be resolved by asking clarification questions.
CiteBench: A benchmark for Scientific Citation Text Generation
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.
GDPR Compliant Collection of Therapist-Patient-Dialogues
While these conversations are part of the daily routine of clinicians, gathering them is usually hindered by various ethical (purpose of data usage), legal (data privacy) and technical (data formatting) limitations.
NLP meets psychotherapy: Using predicted client emotions and self-reported client emotions to measure emotional coherence
No study has examined EC between the subjective experience of emotions and emotion expression in therapy or whether this coherence is associated with clients' well being.
Semantic Similarity Models for Depression Severity Estimation
Depressive disorders constitute a severe public health issue worldwide.
NLPeer: A Unified Resource for the Computational Study of Peer Review
Peer review constitutes a core component of scholarly publishing; yet it demands substantial expertise and training, and is susceptible to errors and biases.
An Inclusive Notion of Text
Natural language processing (NLP) researchers develop models of grammar, meaning and communication based on written text.
Contextual information integration for stance detection via cross-attention
Stance detection deals with identifying an author's stance towards a target.
Effective Cross-Task Transfer Learning for Explainable Natural Language Inference with T5
We compare sequential fine-tuning with a model for multi-task learning in the context where we are interested in boosting performance on two tasks, one of which depends on the other.
Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation
In our analysis, we show that, by design, existing NLP task definitions for fact-checking cannot refute misinformation as professional fact-checkers do for the majority of claims.
Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking
Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets.
The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification
First, the unexplored combination of the cross-encoder architecture (with parameterized similarity scoring function) and episodic meta-learning consistently yields the best FSIC performance.
One does not fit all! On the Complementarity of Vision Encoders for Vision and Language Tasks
While many VEs -- of different architectures, trained on different data and objectives -- are publicly available, they are not designed for the downstream V+L tasks.
Efficient Methods for Natural Language Processing: A Survey
Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance means that resource consumption also grows.
Transformers with Learnable Activation Functions
In contrast to conventional, predefined activation functions, RAFs can adaptively learn optimal activation functions during training according to input data.
UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA
In this paper, we introduce SQuARE v2, the new version of SQuARE, to provide an explainability infrastructure for comparing models based on methods such as saliency maps and graph-based explanations.
TexPrax: A Messaging Application for Ethical, Real-time Data Collection and Annotation
We evaluate TexPrax in a user-study with German factory employees who ask their colleagues for solutions on problems that arise during their daily work.
Mining Legal Arguments in Court Decisions
Identifying, classifying, and analyzing arguments in legal discourse has been a prominent area of research since the inception of the argument mining field.
Annotation Error Detection: Analyzing the Past and Present for a More Coherent Future
While researchers show that their approaches work well on their newly introduced datasets, they rarely compare their methods to previous work or on the same datasets.
Diversity Over Size: On the Effect of Sample and Topic Sizes for Argument Mining Datasets
The task of Argument Mining, that is extracting argumentative sentences for a specific topic from large document sources, is an inherently difficult task for machine learning models and humans alike, as large Argument Mining datasets are rare and recognition of argumentative sentences requires expert knowledge.
Arithmetic-Based Pretraining -- Improving Numeracy of Pretrained Language Models
In this paper, we propose a new extended pretraining approach called Arithmetic-Based Pretraining that jointly addresses both in one extended pretraining step without requiring architectural changes or pretraining from scratch.
Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization
In this work, we show that NLI models can be effective for this task when the training data is augmented with high-quality task-oriented examples.
Abstractive Text Summarization
Natural Language Inference
+1
Adaptable Adapters
The resulting adapters (a) contain about 50% of the learning parameters of the standard adapter and are therefore more efficient at training and inference, and require less storage space, and (b) achieve considerably higher performances in low-data settings.
Revise and Resubmit: An Intertextual Model of Text-based Collaboration in Peer Review
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.
FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations
Despite recent improvements in abstractive summarization, most current approaches generate summaries that are not factually consistent with the source document, severely restricting their trust and usage in real-world applications.
UKP-SQUARE: An Online Platform for Question Answering Research
Recent advances in NLP and information retrieval have given rise to a diverse set of question answering tasks that are of different formats (e. g., extractive, abstractive), require different model architectures (e. g., generative, discriminative), and setups (e. g., with or without retrieval).
Delving Deeper into Cross-lingual Visual Question Answering
2) We analyze cross-lingual VQA across different question types of varying complexity for different multilingual multimodal Transformers, and identify question types that are the most difficult to improve on.
ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers
The applications of conversational agents for scientific disciplines (as expert domains) are understudied due to the lack of dialogue data to train such agents.
Ranked #1 on
Fact Selection
on ArgSciChat
Yes-Yes-Yes: Proactive Data Collection for ACL Rolling Review and Beyond
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.
Addressing the Challenges of Cross-Lingual Hate Speech Detection
The goal of hate speech detection is to filter negative online content aiming at certain groups of people.
GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval
This limits the usage of dense retrieval approaches to only a few domains with large training datasets.
Ranked #9 on
Zero-shot Text Search
on BEIR
MetaQA: Combining Expert Agents for Multi-Skill Question Answering
The recent explosion of question answering (QA) datasets and models has increased the interest in the generalization of models across multiple domains and formats by either training on multiple datasets or by combining multiple models.
On the rate of convergence of a classifier based on a Transformer encoder
Pattern recognition based on a high-dimensional predictor is considered.
xGQA: Cross-Lingual Visual Question Answering
In this work, we address this gap and provide xGQA, a new multilingual evaluation benchmark for the visual question answering task.
TxT: Crossmodal End-to-End Learning with Transformers
Reasoning over multiple modalities, e. g. in Visual Question Answering (VQA), requires an alignment of semantic concepts across domains.
Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning
Recent prompt-based approaches allow pretrained language models to achieve strong performances on few-shot finetuning by reformulating downstream tasks as a language modeling problem.
Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation
Recent work on multilingual AMR-to-text generation has exclusively focused on data augmentation strategies that utilize silver AMR.
Assisting Decision Making in Scholarly Peer Review: A Preference Learning Perspective
Peer review is the primary means of quality control in academia; as an outcome of a peer review process, program and area chairs make acceptance decisions for each paper based on the review reports and scores they received.
AdapterHub Playground: Simple and Flexible Few-Shot Learning with Adapters
The open-access dissemination of pretrained language models through online repositories has led to a democratization of state-of-the-art natural language processing (NLP) research.
Scientia Potentia Est -- On the Role of Knowledge in Computational Argumentation
Despite extensive research efforts in recent years, computational argumentation (CA) remains one of the most challenging areas of natural language processing.
Annotation Curricula to Implicitly Train Non-Expert Annotators
Annotation studies often require annotators to familiarize themselves with the task, its annotation scheme, and the data domain.
Metaphor Generation with Conceptual Mappings
Guided by conceptual metaphor theory, we propose to control the generation process by encoding conceptual mappings between cognitive domains to generate meaningful metaphoric expressions.
Investigating label suggestions for opinion mining in German Covid-19 social media
This work investigates the use of interactively updated label suggestions to improve upon the efficiency of gathering annotations on the task of opinion mining in German Covid-19 social media data.
BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
To address this, and to facilitate researchers to broadly evaluate the effectiveness of their models, we introduce Benchmarking-IR (BEIR), a robust and heterogeneous evaluation benchmark for information retrieval.
Ranked #1 on
Argument Retrieval
on ArguAna (BEIR)
The challenges of temporal alignment on Twitter during crises
Language use changes over time, and this impacts the effectiveness of NLP systems.
Learning to Reason for Text Generation from Scientific Tables
In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions.
What to Pre-Train on? Efficient Intermediate Task Selection
Our best methods achieve an average Regret@3 of less than 1% across all target tasks, demonstrating that we are able to efficiently identify the best datasets for intermediate training.
TWEAC: Transformer with Extendable QA Agent Classifiers
We argue that there exist a wide range of specialized QA agents in literature.
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning
Learning sentence embeddings often requires a large amount of labeled data.
Ranked #1 on
Re-Ranking
on AskUbuntu
AmbiFC: Fact-Checking Ambiguous Claims with Evidence
Automated fact-checking systems verify claims against evidence to predict their veracity.
Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval
Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image.
Structural Adapters in Pretrained Language Models for AMR-to-text Generation
Pretrained language models (PLM) have recently advanced graph-to-text generation, where the input graph is linearized into a sequence and fed into the PLM to obtain its representation.
Ranked #1 on
Data-to-Text Generation
on AMR3.0
Focusing Knowledge-based Graph Argument Mining via Topic Modeling
We use a topic model to extract topic- and sentence-specific evidence from the structured knowledge base Wikidata, building a graph based on the cosine similarity between the entity word vectors of Wikidata and the vector of the given sentence.
Empirical Evaluation of Supervision Signals for Style Transfer Models
In this work we empirically compare the dominant optimization paradigms which provide supervision signals during training: backtranslation, adversarial training and reinforcement learning.
UNKs Everywhere: Adapting Multilingual Language Models to New Scripts
The ultimate challenge is dealing with under-resourced languages not covered at all by the models and written in scripts unseen during pretraining.
How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models
In this work, we provide a systematic and comprehensive empirical comparison of pretrained multilingual language models versus their monolingual counterparts with regard to their monolingual task performance.
Coreference Reasoning in Machine Reading Comprehension
We propose a methodology for creating MRC datasets that better reflect the challenges of coreference reasoning and use it to create a sample evaluation set.
The Curse of Dense Low-Dimensional Information Retrieval for Large Index Sizes
Information Retrieval using dense low-dimensional representations recently became popular and showed out-performance to traditional sparse-representations like BM25.
Generalizing Cross-Document Event Coreference Resolution Across Multiple Corpora
This raises strong concerns on their generalizability -- a must-have for downstream applications where the magnitude of domains or event mentions is likely to exceed those found in a curated corpus.
Ranking Creative Language Characteristics in Small Data Scenarios
We therefore adapt the DirectRanker to provide a new deep model for ranking creative language with small data.
Improving Robustness by Augmenting Training Sentences with Predicate-Argument Structures
Existing approaches to improve robustness against dataset biases mostly focus on changing the training objective so that models learn less from biased examples.
AdapterDrop: On the Efficiency of Adapters in Transformers
Massively pre-trained transformer models are computationally expensive to fine-tune, slow for inference, and have large storage requirements.
Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks
Bi-encoders, on the other hand, require substantial training data and fine-tuning over the target task to achieve competitive performance.
Why do you think that? Exploring Faithful Sentence-Level Rationales Without Supervision
We propose a differentiable training-framework to create models which output faithful rationales on a sentence level, by solely applying supervision on the target task.
Improving QA Generalization by Concurrent Modeling of Multiple Biases
Our framework weights each example based on the biases it contains and the strength of those biases in the training data.
MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale
We investigate the model performances on nine benchmarks of answer selection and question similarity tasks, and show that all 140 models transfer surprisingly well, where the large majority of models substantially outperforms common IR baselines.
Towards Debiasing NLU Models from Unknown Biases
Recently proposed debiasing methods are shown to be effective in mitigating this tendency.
Predicting the Humorousness of Tweets Using Gaussian Process Preference Learning
Most humour processing systems to date make at best discrete, coarse-grained distinctions between the comical and the conventional, yet such notions are better conceptualized as a broad spectrum.
Investigating Pretrained Language Models for Graph-to-Text Generation
We show that the PLMs BART and T5 achieve new state-of-the-art results and that task-adaptive pretraining strategies improve their performance even further.
Ranked #1 on
KG-to-Text Generation
on WebNLG (All)
AdapterHub: A Framework for Adapting Transformers
We propose AdapterHub, a framework that allows dynamic "stitching-in" of pre-trained adapters for different tasks and languages.
From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains
Entity linking (EL) is concerned with disambiguating entity mentions in a text against knowledge bases (KB).
How to Probe Sentence Embeddings in Low-Resource Languages: On Structural Design Choices for Probing Task Evaluation
We then probe embeddings in a multilingual setup with design choices that lie in a 'stable region', as we identify for English, and find that results on English do not transfer to other languages.
Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs
We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation.
Ranked #5 on
KG-to-Text Generation
on AGENDA
Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers
Following the major success of neural language models (LMs) such as BERT or GPT-2 on a variety of language understanding tasks, recent work focused on injecting (structured) knowledge from external resources into these models.
Empowering Active Learning to Jointly Optimize System and User Demands
Existing approaches to active learning maximize the system performance by sampling unlabeled instances for annotation that yield the most efficient training.
AdapterFusion: Non-Destructive Task Composition for Transfer Learning
We show that by separating the two stages, i. e., knowledge extraction and knowledge composition, the classifier can effectively exploit the representations learned from multiple tasks in a non-destructive manner.
Low Resource Multi-Task Sequence Tagging -- Revisiting Dynamic Conditional Random Fields
We compare different models for low resource multi-task sequence tagging that leverage dependencies between label sequences for different tasks.
Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance
Models for natural language understanding (NLU) tasks often rely on the idiosyncratic biases of the dataset, which make them brittle against test cases outside the training distribution.
Improving Factual Consistency Between a Response and Persona Facts
Neural models for response generation produce responses that are semantically plausible but not necessarily factually consistent with facts describing the speaker's persona.
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer
The main goal behind state-of-the-art pre-trained multilingual models such as multilingual BERT and XLM-R is enabling and bootstrapping NLP applications in low-resource languages through zero-shot or few-shot cross-lingual transfer.
Ranked #5 on
Cross-Lingual Transfer
on XCOPA
(using extra training data)
A Matter of Framing: The Impact of Linguistic Formalism on Probing Results
Deep pre-trained contextualized encoders like BERT (Delvin et al., 2019) demonstrate remarkable performance on a range of downstream tasks.
Aspect-Controlled Neural Argument Generation
In this work, we train a language model for argument generation that can be controlled on a fine-grained level to generate sentence-level arguments for a given topic, stance, and aspect.
PuzzLing Machines: A Challenge on Learning From Small Data
To expose this problem in a new light, we introduce a challenge on learning from small data, PuzzLing Machines, which consists of Rosetta Stone puzzles from Linguistic Olympiads for high school students.
Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation
The training is based on the idea that a translated sentence should be mapped to the same location in the vector space as the original sentence.
Metaphoric Paraphrase Generation
This work describes the task of metaphoric paraphrase generation, in which we are given a literal sentence and are charged with generating a metaphoric paraphrase.
Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings
Therefore, we propose a novel semi-supervised framework, which models shared information between domains and domain-specific information separately.
Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs
Recent graph-to-text models generate text from graph-based data using either global or local aggregation to learn node representations.
Ranked #1 on
Graph-to-Sequence
on WebNLG
Stance Detection Benchmark: How Robust Is Your Stance Detection?
Stance Detection (StD) aims to detect an author's stance towards a certain topic or claim and has become a key component in applications like fake news detection, claim validation, and argument search.
Analyzing Structures in the Semantic Vector Space: A Framework for Decomposing Word Embeddings
Word embeddings are rich word representations, which in combination with deep neural networks, lead to large performance gains for many NLP tasks.
Two Birds with One Stone: Investigating Invertible Neural Networks for Inverse Problems in Morphology
We show that they are able to recover the morphological input parameters, i. e., predicting the lemma (e. g., cat) or the morphological tags (e. g., Plural) when run in the reverse direction, without any significant performance drop in the forward direction, i. e., predicting the surface form (e. g., cats).
Scalable Bayesian Preference Learning for Crowds
As previous solutions based on Gaussian processes do not scale to large numbers of users, items or pairwise labels, we propose a stochastic variational inference approach that limits computational and memory costs.
When is ACL's Deadline? A Scientific Conversational Agent
Our conversational agent UKP-ATHENA assists NLP researchers in finding and exploring scientific literature, identifying relevant authors, planning or post-processing conference visits, and preparing paper submissions using a unified interface based on natural language inputs and responses.
Interactive Text Ranking with Bayesian Optimisation: A Case Study on Community QA and Summarisation
For many NLP applications, such as question answering and summarisation, the goal is to select the best solution from a large space of candidates to meet a particular user's needs.
Neural Duplicate Question Detection without Labeled Training Data
We show that our proposed approaches are more effective in many cases because they can utilize larger amounts of unlabeled data from cQA forums.
A Richly Annotated Corpus for Different Tasks in Automated Fact-Checking
Automated fact-checking based on machine learning is a promising approach to identify false information distributed on the web.
Revisiting the Binary Linearization Technique for Surface Realization
End-to-end neural approaches have achieved state-of-the-art performance in many natural language processing (NLP) tasks.
Improving Generalization by Incorporating Coverage in Natural Language Inference
Finally, we show that using the coverage information is not only beneficial for improving the performance across different datasets of the same task.
Joint Wasserstein Autoencoders for Aligning Multimodal Embeddings
One of the key challenges in learning joint embeddings of multiple modalities, e. g. of images and text, is to ensure coherent cross-modal semantics that generalize across datasets.
What do Deep Networks Like to Read?
Recent research towards understanding neural networks probes models in a top-down manner, but is only able to identify model tendencies that are known a priori.
Better Rewards Yield Better Summaries: Learning to Summarise Without References
Human evaluation experiments show that, compared to the state-of-the-art supervised-learning systems and ROUGE-as-rewards RL summarisation systems, the RL systems using our learned rewards during training generate summarieswith higher human ratings.
Enhancing AMR-to-Text Generation with Dual Graph Representations
Generating text from graph-based data, such as Abstract Meaning Representation (AMR), is a challenging task due to the inherent difficulty in how to properly encode the structure of a graph with labeled edges.
Ranked #11 on
AMR-to-Text Generation
on LDC2017T10
FAMULUS: Interactive Annotation and Feedback Generation for Teaching Diagnostic Reasoning
Our proposed system FAMULUS helps students learn to diagnose based on automatic feedback in virtual patient simulations, and it supports instructors in labeling training data.
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
However, it requires that both sentences are fed into the network, which causes a massive computational overhead: Finding the most similar pair in a collection of 10, 000 sentences requires about 50 million inference computations (~65 hours) with BERT.
Ranked #5 on
Linear-Probe Classification
on SentEval
Dialogue Coherence Assessment Without Explicit Dialogue Act Labels
Recent dialogue coherence models use the coherence features designed for monologue texts, e. g. nominal entities, to represent utterances and then explicitly augment them with dialogue-relevant features, e. g., dialogue act labels.
Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation
The predominant RL paradigm for summarisation learns a cross-input policy, which requires considerable time, data and parameter tuning due to the huge search spaces and the delayed rewards.
LINSPECTOR WEB: A Multilingual Probing Suite for Word Representations
We present LINSPECTOR WEB, an open source multilingual inspector to analyze word representations.
Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference
While recent progress on abstractive summarization has led to remarkably fluent summaries, factual errors in generated summaries still severely limit their use in practice.
Predicting Humorousness and Metaphor Novelty with Gaussian Process Preference Learning
The inability to quantify key aspects of creative language is a frequent obstacle to natural language understanding.
Classification and Clustering of Arguments with Contextualized Word Embeddings
We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search.
Preference-based Interactive Multi-Document Summarisation
Interactive NLP is a promising paradigm to close the gap between automatic NLP systems and the human upper bound.
Analysis of Automatic Annotation Suggestions for Hard Discourse-Level Tasks in Expert Domains
Many complex discourse-level tasks can aid domain experts in their work but require costly expert annotations for data creation.
Pitfalls in the Evaluation of Sentence Embeddings
Our motivation is to challenge the current evaluation of sentence embeddings and to provide an easy-to-access reference for future research.
Fast Concept Mention Grouping for Concept Map-based Multi-Document Summarization
Concept map-based multi-document summarization has recently been proposed as a variant of the traditional summarization task with graph-structured summaries.
A Streamlined Method for Sourcing Discourse-level Argumentation Annotations from the Crowd
The study of argumentation and the development of argument mining tools depends on the availability of annotated data, which is challenging to obtain in sufficient quantity and quality.
Fine-Grained Argument Unit Recognition and Classification
In this work, we argue that the task should be performed on a more fine-grained level of sequence labeling.
Alternative Weighting Schemes for ELMo Embeddings
We evaluate different methods that combine the three vectors from the language model in order to achieve the best possible performance in downstream NLP tasks.
Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems
Visual modifications to text are often used to obfuscate offensive comments in social media (e. g., "! d10t") or as a writing style ("1337" in "leet speak"), among other scenarios.
Does My Rebuttal Matter? Insights from a Major NLP Conference
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.
LINSPECTOR: Multilingual Probing Tasks for Word Representations
We present a reusable methodology for creation and evaluation of such tests in a multilingual setting.
Predicting Research Trends From Arxiv
By extrapolation, we predict that these topics will remain lead problems/approaches in their fields in the short- and mid-term.
Is it Time to Swish? Comparing Deep Learning Activation Functions Across NLP tasks
Activation functions play a crucial role in neural networks because they are the nonlinearities which have been attributed to the success story of deep learning.
Challenges in the Automatic Analysis of Students' Diagnostic Reasoning
We aim to enable the large-scale adoption of diagnostic reasoning analysis and feedback by automating the epistemic activity identification.
A Bayesian Approach for Sequence Tagging with Crowds
Current methods for sequence tagging, a core task in NLP, are data hungry, which motivates the use of crowdsourcing as a cheap way to obtain labelled data.
E2E NLG Challenge: Neural Models vs. Templates
E2E NLG Challenge is a shared task on generating restaurant descriptions from sets of key-value pairs.
Ranked #11 on
Data-to-Text Generation
on E2E NLG Challenge
Interactive Instance-based Evaluation of Knowledge Base Question Answering
Most approaches to Knowledge Base Question Answering are based on semantic parsing.
Integrating Knowledge-Supported Search into the INCEpTION Annotation Platform
Annotating entity mentions and linking them to a knowledge resource are essential tasks in many domains.
Cross-Lingual Argumentative Relation Identification: from English to Portuguese
Argument mining aims to detect and identify argument structures from textual resources.
Frame- and Entity-Based Knowledge for Common-Sense Argumentative Reasoning
Common-sense argumentative reasoning is a challenging task that requires holistic understanding of the argumentation where external knowledge about the world is hypothesized to play a key role.
PD3: Better Low-Resource Cross-Lingual Transfer By Combining Direct Transfer and Annotation Projection
We consider unsupervised cross-lingual transfer on two tasks, viz., sentence-level argumentation mining and standard POS tagging.
Corpus-Driven Thematic Hierarchy Induction
Thematic role hierarchy is a widely used linguistic tool to describe interactions between semantic roles and their syntactic realizations.
Cross-topic Argument Mining from Heterogeneous Sources
Argument mining is a core technology for automating argument search in large document collections.
UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification
The Fact Extraction and VERification (FEVER) shared task was launched to support the development of systems able to verify claims by extracting supporting or refuting facts from raw text.
APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning
The merit of preference-based interactive summarisation is that preferences are easier for users to provide than reference summaries.
Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering
The most approaches to Knowledge Base Question Answering are based on semantic parsing.
Ranked #1 on
Knowledge Base Question Answering
on WebQSP-WD
Killing Four Birds with Two Stones: Multi-Task Learning for Non-Literal Language Detection
In this paper we investigate multi-task learning for related non-literal language phenomena.
One Size Fits All? A simple LSTM for non-literal token and construction-level classification
In this paper, we tackle four different tasks of non-literal language classification: token and construction level metaphor detection, classification of idiomatic use of infinitive-verb compounds, and classification of non-literal particle verbs.
From Text to Lexicon: Bridging the Gap between Word Embeddings and Lexical Resources
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.
The INCEpTION Platform: Machine-Assisted and Knowledge-Oriented Interactive Annotation
We introduce INCEpTION, a new annotation platform for tasks including interactive and semantic annotation (e. g., concept linking, fact linking, knowledge base population, semantic frame annotation).
A Retrospective Analysis of the Fake News Challenge Stance-Detection Task
To date, there is no in-depth analysis paper to critically discuss FNC-1{'}s experimental setup, reproduce the results, and draw conclusions for next-generation stance classification methods.
Cross-lingual Argumentation Mining: Machine Translation (and a bit of Projection) is All You Need!
Argumentation mining (AM) requires the identification of complex discourse structures and has lately been applied with success monolingually.
BinLin: A Simple Method of Dependency Tree Linearization
Surface Realization Shared Task 2018 is a workshop on generating sentences from lemmatized sets of dependency triples.
Multimodal Grounding for Language Processing
This survey discusses how recent developments in multimodal processing facilitate conceptual grounding of language.
A Retrospective Analysis of the Fake News Challenge Stance Detection Task
To date, there is no in-depth analysis paper to critically discuss FNC-1's experimental setup, reproduce the results, and draw conclusions for next-generation stance classification methods.
Finding Convincing Arguments Using Scalable Bayesian Preference Learning
We introduce a scalable Bayesian preference learning method for identifying convincing arguments in the absence of gold-standard rat- ings or rankings.
