Search Results for author:
Found 74 papers, 29 papers with code
Grounding Plural Phrases: Countering Evaluation Biases by Individuation
Phrase grounding (PG) is a multimodal task that grounds language in images.
Overview of the 2022 Validity and Novelty Prediction Shared Task
This paper provides an overview of the Argument Validity and Novelty Prediction Shared Task that was organized as part of the 9th Workshop on Argument Mining (ArgMining 2022).
Ranked #1 on
ValNov
on ValNov Subtask A
Data Augmentation for Improving the Prediction of Validity and Novelty of Argumentative Conclusions
Using only training data retrieved from related datasets by automatically labeling them for validity and novelty, combined with synthetic data, outperforms the baseline by 11. 5 points in F_1-score.
Reconstructing Implicit Knowledge with Language Models
In this work we propose an approach for generating statements that explicate implicit knowledge connecting sentences in text.
Explainable Unsupervised Argument Similarity Rating with Abstract Meaning Representation and Conclusion Generation
When assessing the similarity of arguments, researchers typically use approaches that do not provide interpretable evidence or justifications for their ratings.
A Dynamic, Interpreted CheckList for Meaning-oriented NLG Metric Evaluation – through the Lens of Semantic Similarity Rating
Evaluating the quality of generated text is difficult, since traditional NLG evaluation metrics, focusing more on surface form than meaning, often fail to assign appropriate scores. This is especially problematic for AMR-to-text evaluation, given the abstract nature of AMR. Our work aims to support the development and improvement of NLG evaluation metrics that focus on meaning by developing a dynamic CheckList for NLG metrics that is interpreted by being organized around meaning-relevant linguistic phenomena.
Modal Sense Classification At Large: Paraphrase-Driven Sense Projection, Semantically Enriched Classification Models and Cross-Genre Evaluations
Modal verbs have different interpretations depending on their context.
Clinical information extraction for Low-resource languages with Few-shot learning using Pre-trained language models and Prompting
Automatic extraction of medical information from clinical documents poses several challenges: high costs of required clinical expertise, limited interpretability of model predictions, restricted computational resources and privacy regulations.
Exploring Continual Learning of Compositional Generalization in NLI
In this paper, we introduce the Continual Compositional Generalization in Inference (C2Gen NLI) challenge, where a model continuously acquires knowledge of constituting primitive inference tasks as a basis for compositional inferences.
Graph Language Models
In our work we introduce a novel LM type, the Graph Language Model (GLM), that integrates the strengths of both approaches and mitigates their weaknesses.
On Measuring Faithfulness or Self-consistency of Natural Language Explanations
In this work we argue that these faithfulness tests do not measure faithfulness to the models' inner workings -- but rather their self-consistency at output level.
ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
With the ever-increasing popularity of pretrained Video-Language Models (VidLMs), there is a pressing need to develop robust evaluation methodologies that delve deeper into their visio-linguistic capabilities.
Dynamic MOdularized Reasoning for Compositional Structured Explanation Generation
Hence, we propose a dynamic modularized reasoning model, MORSE, to improve the compositional generalization of neural models.
Graecia capta ferum victorem cepit. Detecting Latin Allusions to Ancient Greek Literature
In this study, we introduce SPhilBERTa, a trilingual Sentence-RoBERTa model tailored for Classical Philology, which excels at cross-lingual semantic comprehension and identification of identical sentences across Ancient Greek, Latin, and English.
AMR4NLI: Interpretable and robust NLI measures from semantic graphs
The task of natural language inference (NLI) asks whether a given premise (expressed in NL) entails a given NL hypothesis.
With a Little Push, NLI Models can Robustly and Efficiently Predict Faithfulness
Conditional language models still generate unfaithful output that is not supported by their input.
SETI: Systematicity Evaluation of Textual Inference
We propose SETI (Systematicity Evaluation of Textual Inference), a novel and comprehensive benchmark designed for evaluating pre-trained language models (PLMs) for their systematicity capabilities in the domain of textual inference.
Exploring Large Language Models for Classical Philology
While prior work on Classical languages unanimously uses BERT, in this work we create four language models for Ancient Greek that vary along two dimensions to study their versatility for tasks of interest for Classical languages: we explore (i) encoder-only and encoder-decoder architectures using RoBERTa and T5 as strong model types, and create for each of them (ii) a monolingual Ancient Greek and a multilingual instance that includes Latin and English.
Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks
Arguments often do not make explicit how a conclusion follows from its premises.
MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks
We apply MM-SHAP in two ways: (1) to compare models for their average degree of multimodality, and (2) to measure for individual models the contribution of individual modalities for different tasks and datasets.
Better Smatch = Better Parser? AMR evaluation is not so simple anymore
Recently, astonishing advances have been observed in AMR parsing, as measured by the structural Smatch metric.
SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features
Models based on large-pretrained language models, such as S(entence)BERT, provide effective and efficient sentence embeddings that show high correlation to human similarity ratings, but lack interpretability.
A Dynamic, Interpreted CheckList for Meaning-oriented NLG Metric Evaluation -- through the Lens of Semantic Similarity Rating
Our work aims to support the development and improvement of NLG evaluation metrics that focus on meaning, by developing a dynamic CheckList for NLG metrics that is interpreted by being organized around meaning-relevant linguistic phenomena.
SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph Distance
The similarity of graph structures, such as Meaning Representations (MRs), is often assessed via structural matching algorithms, such as Smatch (Cai and Knight, 2013).
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
We propose VALSE (Vision And Language Structured Evaluation), a novel benchmark designed for testing general-purpose pretrained vision and language (V&L) models for their visio-linguistic grounding capabilities on specific linguistic phenomena.
MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning
Large-scale pretraining is fast becoming the norm in Vision-Language (VL) modeling.
Weisfeiler-Leman in the BAMBOO: Novel AMR Graph Metrics and a Benchmark for AMR Graph Similarity
In this work we propose new Weisfeiler-Leman AMR similarity metrics that unify the strengths of previous metrics, while mitigating their weaknesses.
Ranked #5 on
Graph Matching
on RARE
Translate, then Parse! A strong baseline for Cross-Lingual AMR Parsing
In cross-lingual Abstract Meaning Representation (AMR) parsing, researchers develop models that project sentences from various languages onto their AMRs to capture their essential semantic structures: given a sentence in any language, we aim to capture its core semantic content through concepts connected by manifold types of semantic relations.
Generating Hypothetical Events for Abductive Inference
This work offers the first study of how such knowledge impacts the Abductive NLI task -- which consists in choosing the more likely explanation for given observations.
COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion
Despite recent successes of large pre-trained language models in solving reasoning tasks, their inference capabilities remain opaque.
CO-NNECT: A Framework for Revealing Commonsense Knowledge Paths as Explicitations of Implicit Knowledge in Texts
We conduct evaluations on two argumentative datasets and show that a combination of the two model types generates meaningful, high-quality knowledge paths between sentences that reveal implicit knowledge conveyed in text.
COCO-EX: A Tool for Linking Concepts from Texts to ConceptNet
COCO-EX extracts meaningful concepts from natural language texts and maps them to conjunct concept nodes in ConceptNet, utilizing the maximum of relational information stored in the ConceptNet knowledge graph.
What is Multimodality?
The last years have shown rapid developments in the field of multimodal machine learning, combining e. g., vision, text or speech.
Seeing past words: Testing the cross-modal capabilities of pretrained V&L models on counting tasks
We investigate the reasoning ability of pretrained vision and language (V&L) models in two tasks that require multimodal integration: (1) discriminating a correct image-sentence pair from an incorrect one, and (2) counting entities in an image.
Social Commonsense Reasoning with Multi-Head Knowledge Attention
Notably we are, to the best of our knowledge, the first to demonstrate that a model that learns to perform counterfactual reasoning helps predicting the best explanation in an abductive reasoning task.
X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset
Even though SRL is researched for many languages, major improvements have mostly been obtained for English, for which more resources are available.
Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR
Systems that generate natural language text from abstract meaning representations such as AMR are typically evaluated using automatic surface matching metrics that compare the generated texts to reference texts from which the input meaning representations were constructed.
AMR Similarity Metrics from Principles
Different metrics have been proposed to compare Abstract Meaning Representation (AMR) graphs.
Ranked #4 on
Graph Matching
on RARE
Implicit Knowledge in Argumentative Texts: An Annotated Corpus
When speaking or writing, people omit information that seems clear and evident, such that only part of the message is expressed in words.
Translate and Label! An Encoder-Decoder Approach for Cross-lingual Semantic Role Labeling
Finally, we measure the effectiveness of our method by using the generated data to augment the training basis for resource-poor languages and perform manual evaluation to show that it produces high-quality sentences and assigns accurate semantic role annotations.
Discourse-Aware Semantic Self-Attention for Narrative Reading Comprehension
In this work, we propose to use linguistic annotations as a basis for a \textit{Discourse-Aware Semantic Self-Attention} encoder that we employ for reading comprehension on long narrative texts.
Dissecting Content and Context in Argumentative Relation Analysis
When assessing relations between argumentative units (e. g., support or attack), computational systems often exploit disclosing indicators or markers that are not part of elementary argumentative units (EAUs) themselves, but are gained from their context (position in paragraph, preceding tokens, etc.).
Assessing the Difficulty of Classifying ConceptNet Relations in a Multi-Label Classification Setting
Commonsense knowledge relations are crucial for advanced NLU tasks.
Automatic Accuracy Prediction for AMR Parsing
Secondly, we perform parse selection based on predicted parse accuracies of candidate parses from alternative systems, with the aim of improving overall results.
Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs
To make machines better understand sentiments, research needs to move from polarity identification to understanding the reasons that underlie the expression of sentiment.
An Argument-Marker Model for Syntax-Agnostic Proto-Role Labeling
Semantic proto-role labeling (SPRL) is an alternative to semantic role labeling (SRL) that moves beyond a categorical definition of roles, following Dowty's feature-based view of proto-roles.
Addressing the Winograd Schema Challenge as a Sequence Ranking Task
The Winograd Schema Challenge targets pronominal anaphora resolution problems which require the application of cognitive inference in combination with world knowledge.
A Sequence-to-Sequence Model for Semantic Role Labeling
We explore a novel approach for Semantic Role Labeling (SRL) by casting it as a sequence-to-sequence process.
Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge
We introduce a neural reading comprehension model that integrates external commonsense knowledge, encoded as a key-value memory, in a cloze-style setting.
Neural Skill Transfer from Supervised Language Tasks to Reading Comprehension
Reading comprehension is a challenging task in natural language processing and requires a set of skills to be solved.
SRL4ORL: Improving Opinion Role Labeling using Multi-task Learning with Semantic Role Labeling
For over a decade, machine learning has been used to extract opinion-holder-target structures from text to answer the question "Who expressed what kind of sentiment towards what?".
Ranked #2 on
Fine-Grained Opinion Analysis
on MPQA
(using extra training data)
What do we need to know about an unknown word when parsing German
We propose a new type of subword embedding designed to provide more information about unknown compounds, a major source for OOV words in German.
Classifying Semantic Clause Types: Modeling Context and Genre Characteristics with Recurrent Neural Networks and Attention
Detecting aspectual properties of clauses in the form of situation entity types has been shown to depend on a combination of syntactic-semantic and contextual features.
A Mention-Ranking Model for Abstract Anaphora Resolution
We found model variants that outperform the baselines for nominal anaphors, without training on individual anaphor data, but still lag behind for pronominal anaphors.
Ranked #1 on
Abstract Anaphora Resolution
on The ARRAU Corpus
Assessing SRL Frameworks with Automatic Training Data Expansion
We present the first experiment-based study that explicitly contrasts the three major semantic role labeling frameworks.
Story Cloze Ending Selection Baselines and Data Examination
This paper describes two supervised baseline systems for the Story Cloze Test Shared Task (Mostafazadeh et al., 2016a).
A Web-based Tool for the Integrated Annotation of Semantic and Syntactic Structures
We introduce the third major release of WebAnno, a generic web-based annotation tool for distributed teams.
Multilingual Modal Sense Classification using a Convolutional Neural Network
Modal sense classification (MSC) is a special WSD task that depends on the meaning of the proposition in the modal's scope.
Combining Semantic Annotation of Word Sense \& Semantic Roles: A Novel Annotation Scheme for VerbNet Roles on German Language Data
We present a VerbNet-based annotation scheme for semantic roles that we explore in an annotation study on German language data that combines word sense and semantic role annotation.
