Papers by Bonnie Webber
Culture Matters in Toxic Language Detection in Persian (2025.acl-long)
Copied to clipboard
| Challenge: | Toxic language detection is crucial for creating safer online environments and limiting the spread of harmful content. |
| Approach: | They compare different methods for toxic language detection in Persian to fine-tune, enrich data, and cross-lingual transfer learning. |
| Outcome: | The language of a country with cultural similarities to Persian yields better results in transfer learning. |
Evaluating Machine Translation Performance on Chinese Idioms with a Blacklist Method (L18-1)
Copied to clipboard
| Challenge: | idiom translation is a challenging problem in machine translation because meaning is non-compositional and literal translations are likely to be wrong. |
| Approach: | They propose a method to evaluate the quality of idiom translation of MT systems by a blacklist of literal translations. |
| Outcome: | The proposed method detects that a sizable number of idioms are mistranslated (46.1%) and that literal translation error is a common error type. |
A Joint Matrix Factorization Analysis of Multilingual Representations (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have demonstrated that pre-trained models acquire and incorporate linguistic knowledge in their multilingual representations. |
| Approach: | They propose a tool for comparing latent representations of multilingual and monolingual models . they use joint matrix factorization to analyze multiple sets of representations in a joint manner . |
| Outcome: | The proposed tool analyzes latent representations of multilingual and monolingual models . it shows that language properties influence the factorization outputs . |
Shallow Discourse Annotation for Chinese TED Talks (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods to annotate text with discourse properties are limited to newspaper articles and are not available in Chinese. |
| Approach: | They propose to annotate TED talks with Chinese-related properties using the Penn Discourse TreeBank annotation style . they propose to use planned monologues instead of written text to annnotate Chinese-specific properties. |
| Outcome: | The proposed method is able to achieve reliable results in Chinese spoken monologues, and is based on the Penn Discourse TreeBank annotation style. |
GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue (D19-1)
Copied to clipboard
| Challenge: | Ellipsis and co-reference are common and ubiquitous especially in multi-turn dialogues. |
| Approach: | They propose a unified end-to-end Generative Ellipsis and CO-reference Resolution model . the model can generate a new pragmatically complete user utterance by alternating the generation and copy mode for each user . |
| Outcome: | The proposed model can generate a new pragmatically complete user utterance by alternating the generation and copy mode for each user . intrinsic evaluations on the resolution of ellipsis and co-reference show that the model outperforms the baseline model in terms of EM, BLEU and F1 . |
Superlatives in Context: Modeling the Implicit Semantics of Superlatives (2025.naacl-long)
Copied to clipboard
| Challenge: | a study of superlatives shows that the semantics of superlations in context can be challenging for contemporary models. |
| Approach: | They propose a unified account of superlative semantics which allows for a broad-coverage annotation schema. |
| Outcome: | The proposed schema allows for interpreting superlative expressions and their semantic interpretations. |
Multi-token Mask-filling and Implicit Discourse Relations (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing mask-filling methods were ambiguous and ambiguic . a new study extends existing mask-filled methods to a discourse-level task . |
| Approach: | They propose a multi-token mask-filling approach that supports the prediction of multi-tongue connectives in masked positions. |
| Outcome: | The proposed multi-token mask-filling outperforms the single-token approach in recognizing implicit discourse relations. |
Syntactic Preposing and Discourse Relations (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing work on discourse has ignored non-canonical syntax . a mask-filling task shows that preposing can affect discourse-relational senses . |
| Approach: | They propose to use preposing to mark information status and structure discourse flow . they use a mask-filling task to predict when a constituent appears in canonical position . |
| Outcome: | The results show that the top-ranked mask-fillers agree more often with "gold" annotations in the Penn Discourse TreeBank than in the latter case. |
Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing training data is limited for languages other than English, so is the performance of the developed parsers. |
| Approach: | They propose to apply a pre-trained multilingual model to Italian, German and Dutch parsers where only a small number of manually annotated parses are available. |
| Outcome: | The proposed model improves on six parsers in English and Italian, German and Dutch, with the addition of universal dependency relations and universal POS tags as model-agnostic features. |
Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies on implicit discourse relation recognition have shown great success. |
| Approach: | They incorporate the sense hierarchy into the recognition process and use it to select negative examples. |
| Outcome: | The proposed approach achieves state-of-the-art performance on the task with no additional effort. |
Getting to “Hearer-old”: Charting Referring Expressions Across Time (D18-1)
Copied to clipboard
| Challenge: | a study of how expressions that refer to an entity develop over time is done . we track thousands of person and organization entities over 20 years of NYT . |
| Approach: | They track thousands of person and organization entities over 20 years of the NYT . they find that referring expressions evolve over time as entities move from hearer-new to hearer old . |
| Outcome: | The proposed model improves on a majority-class baseline by 10-30% . it shows that the expressions evolve as the entity becomes accepted into common knowledge . |
TED-CDB: A Large-Scale Chinese Discourse Relation Dataset on TED Talks (2020.emnlp-main)
Copied to clipboard
| Challenge: | TED-CDB dataset is a unique corpus of spoken discourse in Chinese . TED is based on the concept that discourse relations are grounded in an identifiable set of discourse connectives or Altlex expressions. |
| Approach: | They have created a dataset that annotates TED talks in Chinese . they propose to adapt the dataset to Chinese news text to improve its performance . |
| Outcome: | The TED-CDB dataset can improve the performance of systems for languages other than Chinese . it is adapted to features that are not present in English and can extract discourse semantic features . |
Refocusing on Relevance: Personalization in NLG (2021.emnlp-main)
Copied to clipboard
| Challenge: | a number of negative effects exist when NLG systems are not grounded to a specific input text. |
| Approach: | They argue that NLG systems should focus on making use of additional context . they argue that relevance should be thought of as a crucial tool for user-oriented text-generating tasks . |
| Outcome: | The proposed approach is more of the rule than the exception, the authors argue . they argue that value-sensitive design represents a crucial path forward . |
Discourse Coherence: Concurrent Explicit and Implicit Relations (P18-1)
Copied to clipboard
| Challenge: | Existing studies on discourse coherence show that multiple discourse relations can be operative between two segments for reasons not predicted by the literature. |
| Approach: | They show that people endorse seemingly divergent conjunctions to express the link they see between two segments in a crowdsourced conjunctioninsertion experiment. |
| Outcome: | The proposed results can inform future work on discourse coherence and lead to higher levels of performance in discourse parsing. |
Multi-Label Classification for Implicit Discourse Relation Recognition (2024.findings-acl)
Copied to clipboard
| Challenge: | Prior research in discourse relation recognition has treated these instances as separate examples during training, with a gold-standard prediction matching one of the labels considered correct at test time. |
| Approach: | They propose to use multiple labels to annotate an example when multiple relations are believed to hold simultaneously. |
| Outcome: | The proposed frameworks don't depress performance for single-label prediction. |
NegPar: A parallel corpus annotated for negation (L18-1)
Copied to clipboard
| Challenge: | NegPar is the first parallel corpus annotated for negation in the narrative domain. |
| Approach: | They present NegPar, a parallel corpus annotated for negation in the narrative domain . they follow the annotation guidelines in the CONANDOYLE-NEG corpus . |
| Outcome: | The proposed corpus is based on the CONANDOYLE-NEG corpus and is reannotated to ensure more consistent and interpretable representations. |
Reducing Quantity Hallucinations in Abstractive Summarization (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Abstractive summaries are subject to hallucination, but they are not very informative. |
| Approach: | They propose to use a beam-worth of abstractive summaries to up-rank summary that is not supported by the original text. |
| Outcome: | The proposed system up-ranks summaries whose quantity terms are supported by the original text without losing Recall, and shows higher Precision. |