Bonnie Webber
YOU?
Author Swipe
View article: Beyond semantics: the challenges of annotating pragmatic and discourse phenomena
Beyond semantics: the challenges of annotating pragmatic and discourse phenomena Open
The goal of this special issue is to show the challenges faced in reliably annotating abstractsemantic and pragmatic information at both the sentence and discourse levels, and how those chal-lenges are being met. Such information is freque…
View article: Culture Matters in Toxic Language Detection in Persian
Culture Matters in Toxic Language Detection in Persian Open
Toxic language detection is crucial for creating safer online environments and limiting the spread of harmful content. While toxic language detection has been under-explored in Persian, the current work compares different methods for this …
View article: Superlatives in Context: Modeling the Implicit Semantics of Superlatives
Superlatives in Context: Modeling the Implicit Semantics of Superlatives Open
View article: “Otherwise” in Context: Exploring Discourse Functions with Language Models
“Otherwise” in Context: Exploring Discourse Functions with Language Models Open
View article: Culture Matters in Toxic Language Detection in Persian
Culture Matters in Toxic Language Detection in Persian Open
View article: Multi-token Mask-filling and Implicit Discourse Relations
Multi-token Mask-filling and Implicit Discourse Relations Open
View article: Leveraging Hierarchical Prototypes as the Verbalizer for Implicit Discourse Relation Recognition
Leveraging Hierarchical Prototypes as the Verbalizer for Implicit Discourse Relation Recognition Open
Implicit discourse relation recognition involves determining relationships that hold between spans of text that are not linked by an explicit discourse connective. In recent years, the pre-train, prompt, and predict paradigm has emerged as…
View article: Multi-Label Classification for Implicit Discourse Relation Recognition
Multi-Label Classification for Implicit Discourse Relation Recognition Open
Discourse relations play a pivotal role in establishing coherence within textual content, uniting sentences and clauses into a cohesive narrative. The Penn Discourse Treebank (PDTB) stands as one of the most extensively utilized datasets i…
View article: Superlatives in Context: Modeling the Implicit Semantics of Superlatives
Superlatives in Context: Modeling the Implicit Semantics of Superlatives Open
Superlatives are used to single out elements with a maximal/minimal property. Semantically, superlatives perform a set comparison: something (or some things) has the min/max property out of a set. As such, superlatives provide an ideal phe…
View article: Syntactic Preposing and Discourse Relations
Syntactic Preposing and Discourse Relations Open
View article: Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs
Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs Open
Translating literary works has perennially stood as an elusive dream in machine translation (MT), a journey steeped in intricate challenges. To foster progress in this domain, we hold a new shared task at WMT 2023, the first edition of the…
View article: A Joint Matrix Factorization Analysis of Multilingual Representations
A Joint Matrix Factorization Analysis of Multilingual Representations Open
We present an analysis tool based on joint matrix factorization for comparing latent representations of multilingual and monolingual models. An alternative to probing, this tool allows us to analyze multiple sets of representations in a jo…
View article: Rant or rave: variation over time in the language of online reviews
Rant or rave: variation over time in the language of online reviews Open
We examine how the language of online reviews has changed over the past 20 years. The corpora we use for this analysis consist of online reviews, each of which is paired with a numerical rating. This allows us to control for the perceived …
View article: Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations
Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations Open
Implicit discourse relation recognition is a challenging task that involves identifying the sense or senses that hold between two adjacent spans of text, in the absence of an explicit connective between them. In both PDTB-2 and PDTB-3, dis…
View article: Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs
Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs Open
Longyue Wang, Zhaopeng Tu, Yan Gu, Siyou Liu, Dian Yu, Qingsong Ma, Chenyang Lyu, Liting Zhou, Chao-Hong Liu, Yufeng Ma, Weiyu Chen, Yvette Graham, Bonnie Webber, Philipp Koehn, Andy Way, Yulin Yuan, Shuming Shi. Proceedings of the Eighth …
View article: A Joint Matrix Factorization Analysis of Multilingual Representations
A Joint Matrix Factorization Analysis of Multilingual Representations Open
We present an analysis tool based on joint matrix factorization for comparing latent representations of multilingual and monolingual models. An alternative to probing, this tool allows us to analyze multiple sets of representations in a jo…
View article: Annotation Error Detection: Analyzing the Past and Present for a More Coherent Future
Annotation Error Detection: Analyzing the Past and Present for a More Coherent Future Open
Annotated data is an essential ingredient in natural language processing for training and evaluating machine learning models. It is therefore very desirable for the annotations to be of high quality. Recent work, however, has shown that se…
View article: Annotation Error Detection: Analyzing the Past and Present for a More Coherent Future
Annotation Error Detection: Analyzing the Past and Present for a More Coherent Future Open
Annotated data is an essential ingredient in natural language processing for training and evaluating machine learning models. It is therefore very desirable for the annotations to be of high quality. Recent work, however, has shown that se…
View article: Revisiting Shallow Discourse Parsing in the PDTB-3: Handling Intra-sentential Implicits
Revisiting Shallow Discourse Parsing in the PDTB-3: Handling Intra-sentential Implicits Open
In the PDTB-3, several thousand implicit discourse relations were newly annotated \textit{within} individual sentences, adding to the over 15,000 implicit relations annotated \textit{across} adjacent sentences in the PDTB-2. Given that the…
View article: Automatically Discarding Straplines to Improve Data Quality for Abstractive News Summarization
Automatically Discarding Straplines to Improve Data Quality for Abstractive News Summarization Open
Recent improvements in automatic news summarization fundamentally rely on large corpora of news articles and their summaries. These corpora are often constructed by scraping news websites, which results in including not only summaries but …
View article: Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations
Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations Open
Implicit discourse relation recognition is a challenging task that involves identifying the sense or senses that hold between two adjacent spans of text, in the absense of an explicit connective between them. In both PDTB-2 (prasad et al.,…
View article: Have We Solved The Hard Problem? It’s Not Easy! Contextual Lexical Contrast as a Means to Probe Neural Coherence
Have We Solved The Hard Problem? It’s Not Easy! Contextual Lexical Contrast as a Means to Probe Neural Coherence Open
Lexical cohesion is a fundamental mechanism for text which requires a pair of words to be interpreted as a certain type of lexical relation (e.g., similarity) to understand a coherent context; we refer to such relations as the contextual l…
View article: Kathy McKeown Interviews Bonnie Webber
Kathy McKeown Interviews Bonnie Webber Open
Because the 2020 ACL Lifetime Achievement Award presentation could not be done in person, we replaced the usual LTA talk with an interview between Professor Kathy McKeown (Columbia University) and the recipient, Bonnie Webber. The followin…
View article: Refocusing on Relevance: Personalization in NLG
Refocusing on Relevance: Personalization in NLG Open
Many NLG tasks such as summarization, dialogue response, or open domain question answering focus primarily on a source text in order to generate a target response. This standard approach falls short, however, when a user's intent or contex…
View article: Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing
Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing Open
The availability of corpora has led to significant advances in training semantic parsers in English. Unfortunately, for languages other than English, annotated data is limited and so is the performance of the developed parsers. Recently, p…
View article: Revisiting Shallow Discourse Parsing in the PDTB-3: Handling Intra-sentential Implicits
Revisiting Shallow Discourse Parsing in the PDTB-3: Handling Intra-sentential Implicits Open
In the PDTB-3, several thousand implicit discourse relations were newly annotated within individual sentences, adding to the over 15,000 implicit relations annotated across adjacent sentences in the PDTB-2. Given that the position of the a…
View article: Querent Intent in Multi-Sentence Questions
Querent Intent in Multi-Sentence Questions Open
Multi-sentence questions (MSQs) are sequences of questions connected by relations which, unlike sequences of standalone questions, need to be answered as a unit. Following Rhetorical Structure Theory (RST), we recognise that different "que…
View article: Extending Implicit Discourse Relation Recognition to the PDTB-3
Extending Implicit Discourse Relation Recognition to the PDTB-3 Open
The PDTB-3 contains many more Implicit discourse relations than the previous PDTB-2. This is in part because implicit relations have now been annotated within sentences as well as between them. In addition, some now co-occur with explicit …
View article: Reducing Quantity Hallucinations in Abstractive Summarization
Reducing Quantity Hallucinations in Abstractive Summarization Open
It is well-known that abstractive summaries are subject to hallucination---including material that is not supported by the original text. While summaries can be made hallucination-free by limiting them to general phrases, such summaries wo…
View article: Shallow Discourse Annotation for Chinese TED Talks
Shallow Discourse Annotation for Chinese TED Talks Open
Text corpora annotated with language-related properties are an important resource for the development of Language Technology. The current work contributes a new resource for Chinese Language Technology and for Chinese-English translation, …