Search Results for author:
Found 73 papers, 25 papers with code
Evaluation of Coreference Resolution Systems Under Adversarial Attacks
A substantial overlap of coreferent mentions in the CoNLL dataset magnifies the recent progress on coreference resolution.
The CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue
The CODI-CRAC 2022 Shared Task on Anaphora Resolution in Dialogues is the second edition of an initiative focused on detecting different types of anaphoric relations in conversations of different kinds.
Incorporating Centering Theory into Neural Coreference Resolution
In recent years, transformer-based coreference resolution systems have achieved remarkable improvements on the CoNLL dataset.
Entity-based Neural Local Coherence Modeling
We evaluate our model on three downstream tasks showing that it is not only linguistically more sound than previous models but also that it outperforms them in end applications.
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.
A Novel Wikipedia based Dataset for Monolingual and Cross-Lingual Summarization
We collect high-quality, real-world cross-lingual data from Spektrum der Wissenschaft, which publishes human-written German scientific summaries of English science articles on various subjects.
Centering-based Neural Coherence Modeling with Hierarchical Discourse Segments
We approximate a linguistic theory of coherence, Centering theory, which we use to track the changes of focus between discourse segments.
Reconstructing Manual Information Extraction with DB-to-Document Backprojection: Experiments in the Life Science Domain
We introduce a novel scientific document processing task for making previously inaccessible information in printed paper documents available to automatic processing.
Countering the Influence of Essay Length in Neural Essay Scoring
In this work, we first show that state-of-the-art systems, recent neural essay scoring systems, might be also influenced by the correlation between essay length and scores in a standard dataset.
Ranked #3 on
Automated Essay Scoring
on ASAP-AES
Fine-tuning BERT Models for Summarizing German Radiology Findings
Writing the conclusion section of radiology reports is essential for communicating the radiology findings and its assessment to physician in a condensed form.
The CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue
In this paper, we provide an overview of the CODI-CRAC 2021 Shared-Task: Anaphora Resolution in Dialogue.
What Causes the Failure of Explicit to Implicit Discourse Relation Recognition?
We consider an unanswered question in the discourse processing community: why do relation classifiers trained on explicit examples (with connectives removed) perform poorly in real implicit scenarios?
Graph-based Clustering for Detecting Semantic Change Across Time and Languages
To address this issue, we propose a graph-based clustering approach to capture nuanced changes in both high- and low-frequency word senses across time and languages, including the acquisition and loss of these senses over time.
Normed Spaces for Graph Embedding
Theoretical results from discrete geometry suggest that normed spaces can abstractly embed finite metric spaces with surprisingly low theoretical bounds on distortion in low dimensions.
Investigating Multilingual Coreference Resolution by Universal Annotations
Multilingual coreference resolution (MCR) has been a long-standing and challenging task.
Modeling Graphs Beyond Hyperbolic: Graph Neural Networks in Symmetric Positive Definite Matrices
The uniform geometry of Euclidean and hyperbolic spaces allows for representing graphs with uniform geometric and topological features, such as grids and hierarchies, with minimal distortion.
Modeling Structural Similarities between Documents for Coherence Assessment with Graph Convolutional Networks
Coherence is an important aspect of text quality, and various approaches have been applied to coherence modeling.
Annotation-Inspired Implicit Discourse Relation Classification with Auxiliary Discourse Connective Generation
Implicit discourse relation classification is a challenging task due to the absence of discourse connectives.
SimCSum: Joint Learning of Simplification and Cross-lingual Summarization for Cross-lingual Science Journalism
Cross-lingual science journalism generates popular science stories of scientific articles different from the source language for a non-expert audience.
Abstractive Text Summarization
Cross-Lingual Abstractive Summarization
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence
Still, recent BERT-based evaluation metrics are weak in recognizing coherence, and thus are not reliable in a way to spot the discourse-level improvements of those text generation systems.
Impact of Target Word and Context on End-to-End Metonymy Detection
We show that the target word is less useful for detecting metonymy in our dataset.
Vector-valued Distance and Gyrocalculus on the Space of Symmetric Positive Definite Matrices
We propose the use of the vector-valued distance to compute distances and extract geometric information from the manifold of symmetric positive definite matrices (SPD), and develop gyrovector calculus, constructing analogs of vector space operations in this curved space.
Augmenting the User-Item Graph with Textual Similarity Models
This paper introduces a simple and effective form of data augmentation for recommender systems.
Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach
We propose the systematic use of symmetric spaces in representation learning, a class encompassing many of the previously used embedding targets.
Incremental Neural Lexical Coherence Modeling
We propose a coherence model which interprets sentences incrementally to capture lexical relations between them.
A Fully Hyperbolic Neural Model for Hierarchical Multi-Class Classification
Label inventories for fine-grained entity typing have grown in size and complexity.
A Large Harvested Corpus of Location Metonymy
We propose a new, labelled, high-quality corpus of location metonymy called WiMCor, which is large in size and has high coverage.
Adapting Deep Learning Methods for Mental Health Prediction on Social Media
Mental health poses a significant challenge for an individual's well-being.
On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages
Recent work has validated the importance of subword information for word representation learning.
Using Automatically Extracted Minimum Spans to Disentangle Coreference Evaluation from Boundary Detection
To address this problem, minimum spans are manually annotated in smaller corpora.
Fine-Grained Entity Typing in Hyperbolic Space
How can we represent hierarchical information present in large type inventories for entity typing?
Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation
Pretrained contextual and non-contextual subword embeddings have become available in over 250 languages, allowing massively multilingual NLP.
Ranked #3 on
Part-Of-Speech Tagging
on UD
A Neural Local Coherence Model for Text Quality Assessment
We propose a local coherence model that captures the flow of what semantically connects adjacent sentences in a text.
Transparent, Efficient, and Robust Word Embedding Access with WOMBAT
We present WOMBAT, a Python tool which supports NLP practitioners in accessing word embeddings from code.
Unrestricted Bridging Resolution
The second stage, bridging antecedent selection, finds the antecedents for all predicted bridging anaphors.
Event Argument Identification on Dependency Graphs with Bidirectional LSTMs
In this paper we investigate the performance of event argument identification.
BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages
We present BPEmb, a collection of pre-trained subword unit embeddings in 275 languages, based on Byte-Pair Encoding (BPE).
Using a Graph-based Coherence Model in Document-Level Machine Translation
Although coherence is an important aspect of any text generation system, it has received little attention in the context of machine translation (MT) so far.
Using Linguistic Features to Improve the Generalization Capability of Neural Coreference Resolvers
We show that generalization improves only slightly by merely using a set of additional linguistic features.
Revisiting Selectional Preferences for Coreference Resolution
Selectional preferences have long been claimed to be essential for coreference resolution.
Lexical Features in Coreference Resolution: To be Used With Caution
Lexical features are a major source of information in state-of-the-art coreference resolvers.
Trust, but Verify! Better Entity Linking through Automatic Verification
We introduce automatic verification as a post-processing step for entity linking (EL).
Use Generalized Representations, But Do Not Forget Surface Features
Only a year ago, all state-of-the-art coreference resolvers were using an extensive amount of surface features.
Microblog Emotion Classification by Computing Similarity in Text, Time, and Space
Most work in NLP analysing microblogs focuses on textual content thus neglecting temporal and spatial information.
Latent Structures for Coreference Resolution
Machine learning approaches to coreference resolution vary greatly in the modeling of the problem: while early approaches operated on the mention pair level, current research focuses on ranking architectures and antecedent trees.
Concept-based Selectional Preferences and Distributional Representations from Wikipedia Articles
This paper describes the derivation of distributional semantic representations for open class words relative to a concept inventory, and of concepts relative to open class words through grammatical relations extracted from Wikipedia articles.
