Search Results for author:
Found 72 papers, 14 papers with code
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.
Less Text, More Visuals: Evaluating the Onboarding Phase in a GWAP for NLP
Games-with-a-purpose find attracting players a challenge.
We Need to Consider Disagreement in Evaluation
Instead, we suggest that we need to better capture the sources of disagreement to improve today’s evaluation practice.
Patterns of Polysemy and Homonymy in Contextualised Language Models
One of the central aspects of contextualised language models is that they should be able to distinguish the meaning of lexically ambiguous words by their contexts.
Anaphoric Zero Pronoun Identification: A Multilingual Approach
We propose a BERT-based multilingual model for AZP identification from predicted zero pronoun positions, and evaluate it on the Arabic and Chinese portions of OntoNotes 5. 0.
Word Sense Distance in Human Similarity Judgements and Contextualised Word Embeddings
Homonymy is often used to showcase one of the advantages of context-sensitive word embedding techniques such as ELMo and BERT.
The Universal Anaphora Scorer
It also supports the evaluation of split antecedent anaphora and discourse deixis, for which no tools existed.
ArMIS - The Arabic Misogyny and Sexism Corpus with Annotator Subjective Disagreements
The use of misogynistic and sexist language has increased in recent years in social media, and is increasing in the Arabic world in reaction to reforms attempting to remove restrictions on women lives.
Hard and Soft Evaluation of NLP models with BOOtSTrap SAmpling - BooStSa
Natural Language Processing (NLP) ‘s applied nature makes it necessary to select the most effective and robust models.
The QMUL/HRBDT contribution to the NADI Arabic Dialect Identification Shared Task
We present the Arabic dialect identification system that we used for the country-level subtask of the NADI challenge.
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.
Understanding The Effect Of Temperature On Alignment With Human Opinions
With the increasing capabilities of LLMs, recent studies focus on understanding whose opinions are represented by them and how to effectively extract aligned opinion distributions.
ClarQ-LLM: A Benchmark for Models Clarifying and Requesting Information in Task-Oriented Dialog
The benchmark includes 31 different task types, each with 10 unique dialogue scenarios between information seeker and provider agents.
The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representation
Large Language Models (LLMs) have emerged as powerful support tools across various natural language tasks and a range of application domains.
Integrating knowledge bases to improve coreference and bridging resolution for the chemical domain
Resolving coreference and bridging relations in chemical patents is important for better understanding the precise chemical process, where chemical domain knowledge is very critical.
Extending Activation Steering to Broad Skills and Multiple Behaviours
In this paper, we investigate the efficacy of activation steering for broad skills and multiple behaviours.
Large Language Models as Minecraft Agents
In this work we examine the use of Large Language Models (LLMs) in the challenging setting of acting as a Minecraft agent.
SemEval-2023 Task 11: Learning With Disagreements (LeWiDi)
We report on the second LeWiDi shared task, which differs from the first edition in three crucial respects: (i) it focuses entirely on NLP, instead of both NLP and computer vision tasks in its first edition; (ii) it focuses on subjective tasks, instead of covering different types of disagreements-as training with aggregated labels for subjective NLP tasks is a particularly obvious misrepresentation of the data; and (iii) for the evaluation, we concentrate on soft approaches to evaluation.
Joint Coreference Resolution for Zeros and non-Zeros in Arabic
Most existing proposals about anaphoric zero pronoun (AZP) resolution regard full mention coreference and AZP resolution as two independent tasks, even though the two tasks are clearly related.
Aggregating Crowdsourced and Automatic Judgments to Scale Up a Corpus of Anaphoric Reference for Fiction and Wikipedia Texts
Although several datasets annotated for anaphoric reference/coreference exist, even the largest such datasets have limitations in terms of size, range of domains, coverage of anaphoric phenomena, and size of documents included.
Scoring Coreference Chains with Split-Antecedent Anaphors
Anaphoric reference is an aspect of language interpretation covering a variety of types of interpretation beyond the simple case of identity reference to entities introduced via nominal expressions covered by the traditional coreference task in its most recent incarnation in ONTONOTES and similar datasets.
Patterns of Lexical Ambiguity in Contextualised Language Models
One of the central aspects of contextualised language models is that they should be able to distinguish the meaning of lexically ambiguous words by their contexts.
Coreference Resolution for the Biomedical Domain: A Survey
Issues with coreference resolution are one of the most frequently mentioned challenges for information extraction from the biomedical literature.
Data Augmentation Methods for Anaphoric Zero Pronouns
In pro-drop language like Arabic, Chinese, Italian, Japanese, Spanish, and many others, unrealized (null) arguments in certain syntactic positions can refer to a previously introduced entity, and are thus called anaphoric zero pronouns.
SemEval-2021 Task 12: Learning with Disagreements
Disagreement between coders is ubiquitous in virtually all datasets annotated with human judgements in both natural language processing and computer vision.
Beyond Black \& White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning
Supervised learning assumes that a ground truth label exists.
Stay Together: A System for Single and Split-antecedent Anaphora Resolution
Split-antecedent anaphora is rarer and more complex to resolve than single-antecedent anaphora; as a result, it is not annotated in many datasets designed to test coreference, and previous work on resolving this type of anaphora was carried out in unrealistic conditions that assume gold mentions and/or gold split-antecedent anaphors are available.
BERTective: Language Models and Contextual Information for Deception Detection
In most cases, however, the target texts{'} preceding context is not considered.
Assessing Polyseme Sense Similarity through Co-predication Acceptability and Contextualised Embedding Distance
Co-predication is one of the most frequently used linguistic tests to tell apart shifts in polysemic sense from changes in homonymic meaning.
Multitask Learning-Based Neural Bridging Reference Resolution
can be achieved on full bridging resolution with this architecture.
Neural Coreference Resolution for Arabic
No neural coreference resolver for Arabic exists, in fact we are not aware of any learning-based coreference resolver for Arabic since (Bjorkelund and Kuhn, 2014).
Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution
One limitation of virtually all coreference resolution models is the focus on single-antecedent anaphors.
Named Entity Recognition as Dependency Parsing
Named Entity Recognition (NER) is a fundamental task in Natural Language Processing, concerned with identifying spans of text expressing references to entities.
Ranked #2 on
Named Entity Recognition (NER)
on GENIA
Speaking Outside the Box: Exploring the Benefits of Unconstrained Input in Crowdsourcing and Citizen Science Platforms
Crowdsourcing approaches provide a difficult design challenge for developers.
Aggregation Driven Progression System for GWAPs
As the uses of Games-With-A-Purpose (GWAPs) broadens, the systems that incorporate its usages have expanded in complexity.
Cross-lingual Zero Pronoun Resolution
In languages like Arabic, Chinese, Italian, Japanese, Korean, Portuguese, Spanish, and many others, predicate arguments in certain syntactic positions are not realized instead of being realized as overt pronouns, and are thus called zero- or null-pronouns.
Multi-task Learning Based Neural Bridging Reference Resolution
can be achieved on full bridging resolution with this architecture.
A Cluster Ranking Model for Full Anaphora Resolution
In this paper, we introduce an architecture to simultaneously identify non-referring expressions (including expletives, predicative s, and other types) and build coreference chains, including singletons.
Ranked #1 on
Coreference Resolution
on The ARRAU Corpus
Measuring Conversational Fluidity in Automated Dialogue Agents
We present an automated evaluation method to measure fluidity in conversational dialogue systems.
A Mention-Pair Model of Annotation with Nonparametric User Communities
The model is also flexible enough to be used in standard annotation tasks for classification where it registers on par performance with the state of the art.
Neural Mention Detection
We then evaluate our models for coreference resolution by using mentions predicted by our best model in start-of-the-art coreference systems.
Crowdsourcing and Aggregating Nested Markable Annotations
One of the key steps in language resource creation is the identification of the text segments to be annotated, or markables, which depending on the task may vary from nominal chunks for named entity resolution to (potentially nested) noun phrases in coreference resolution (or mentions) to larger text segments in text segmentation.
Using Automatically Extracted Minimum Spans to Disentangle Coreference Evaluation from Boundary Detection
To address this problem, minimum spans are manually annotated in smaller corpora.
A Crowdsourced Corpus of Multiple Judgments and Disagreement on Anaphoric Interpretation
The corpus, containing annotations for about 108, 000 markables, is one of the largest corpora for coreference for English, and one of the largest crowdsourced NLP corpora, but its main feature is the large number of judgments per markable: 20 on average, and over 2. 2M in total.
A Probabilistic Annotation Model for Crowdsourcing Coreference
The availability of large scale annotated corpora for coreference is essential to the development of the field.
Anaphora Resolution with the ARRAU Corpus
The most distinctive feature of the corpus is the annotation of a wide range of anaphoric relations, including bridging references and discourse deixis in addition to identity (coreference).
Comparing Bayesian Models of Annotation
We evaluate these models along four aspects: comparison to gold labels, predictive accuracy for new annotations, annotator characterization, and item difficulty, using four datasets with varying degrees of noise in the form of random (spammy) annotators.
Incongruent Headlines: Yet Another Way to Mislead Your Readers
This paper discusses the problem of incongruent headlines: those which do not accurately represent the information contained in the article with which they occur.
Visually Grounded and Textual Semantic Models Differentially Decode Brain Activity Associated with Concrete and Abstract Nouns
Dual coding theory considers concrete concepts to be encoded in the brain both linguistically and visually, and abstract concepts only linguistically.
Predicting Brexit: Classifying Agreement is Better than Sentiment and Pollsters
On June 23rd 2016, UK held the referendum which ratified the exit from the EU.
Phrase Detectives Corpus 1.0 Crowdsourced Anaphoric Coreference.
Corpora are typically annotated by several experts to create a gold standard; however, there are now compelling reasons to use a non-expert crowd to annotate text, driven by cost, speed and scalability.
ARRAU: Linguistically-Motivated Annotation of Anaphoric Descriptions
This paper presents a second release of the ARRAU dataset: a multi-domain corpus with thorough linguistically motivated annotation of anaphora and related phenomena.
The OnForumS corpus from the Shared Task on Online Forum Summarisation at MultiLing 2015
In this paper we present the OnForumS corpus developed for the shared task of the same name on Online Forum Summarisation (OnForumS at MultiLing{'}15).
Combining Minimally-supervised Methods for Arabic Named Entity Recognition
Supervised methods can achieve high performance on NLP tasks, such as Named Entity Recognition (NER), but new annotations are required for every new domain and/or genre change.
AraNLP: a Java-based Library for the Processing of Arabic Text.
We present a free, Java-based library named {``}AraNLP{''} that covers various Arabic text preprocessing tools.
PR2: A Language Independent Unsupervised Tool for Personality Recognition from Text
We present PR2, a personality recognition system available online, that performs instance-based classification of Big5 personality types from unstructured text, using language-independent features.
DeCour: a corpus of DEceptive statements in Italian COURts
In criminal proceedings, sometimes it is not easy to evaluate the sincerity of oral testimonies.
Domain-specific vs. Uniform Modeling for Coreference Resolution
Several corpora annotated for coreference have been made available in the past decade.
