Search Results for author:
Found 29 papers, 10 papers with code
GFST: Gender-Filtered Self-Training for More Accurate Gender in Translation
Targeted evaluations have found that machine translation systems often output incorrect gender in translations, even when the gender is clear from context.
Predicting Sentence Deletions for Text Simplification Using a Functional Discourse Structure
Document-level text simplification often deletes some sentences besides performing lexical, grammatical or structural simplification to reduce text complexity.
Profiling News Discourse Structure Using Explicit Subtopic Structures Guided Critics
We present an actor-critic framework to induce subtopical structures in a news article for news discourse profiling.
Ranked #4 on
Text Classification
on NewsDiscourse
Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents
Automated service agents require well-structured workflows to provide consistent and accurate responses to customer queries.
Unanswerability Evaluation for Retreival Augmented Generation
Existing evaluation frameworks for retrieval-augmented generation (RAG) systems focus on answerable queries, but they overlook the importance of appropriately rejecting unanswerable requests.
Distill-SynthKG: Distilling Knowledge Graph Synthesis Workflow for Improved Coverage and Efficiency
Additionally, there is a gap in evaluation datasets and methodologies for ontology-free KG construction.
Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage
Using this categorization, we introduce a fine-grained evaluation protocol that provides insights into the retrieval and generation characteristics of RAG systems, including three commercial generative answer engines: You. com, Perplexity AI, and Bing Chat.
Lexical Repetitions Lead to Rote Learning: Unveiling the Impact of Lexical Overlap in Train and Test Reference Summaries
Ideal summarization models should generalize to novel summary-worthy content without remembering reference training summaries by rote.
Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles
In this paper, we propose a new task of summarizing diverse information encountered in multiple news articles encompassing the same event.
XGen-7B Technical Report
Most open-source LLMs, on the other hand, are limited in their ability to support longer sequence lengths, which is a key requirement for many tasks that require inference over an input context.
Improving Factual Consistency in Summarization with Compression-Based Post-Editing
We propose to use sentence-compression data to train the post-editing model to take a summary with extrinsic entity errors marked with special tokens and output a compressed, well-formed summary with those errors removed.
Conformal Predictor for Improving Zero-shot Text Classification Efficiency
Pre-trained language models (PLMs) have been shown effective for zero-shot (0shot) text classification.
Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning
Through this way, SESoM inherits the superior generalization of model ensemble approaches and simultaneously captures the sample-specific competence of each source prompt.
Modeling Document-level Temporal Structures for Building Temporal Dependency Graphs
We propose to leverage news discourse profiling to model document-level temporal structures for building temporal dependency graphs.
CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization
Then, we fine-tune a base summarization model, which is trained on all training samples, on the clean (noisy) subset to obtain an \textit{expert} (\textit{anti-expert}) model.
P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts
They take LLM embeddings as input and output continuous prompts that are used to query the LLM.
Improving Gender Translation Accuracy with Filtered Self-Training
Targeted evaluations have found that machine translation systems often output incorrect gender, even when the gender is clear from context.
Automatic Data Acquisition for Event Coreference Resolution
We propose to leverage lexical paraphrases and high precision rules informed by news discourse structure to automatically collect coreferential and non-coreferential event pairs from unlabeled English news articles.
Discourse as a Function of Event: Profiling Discourse Structure in News Articles around the Main Event
Understanding discourse structures of news articles is vital to effectively contextualize the occurrence of a news event.
Ranked #5 on
Text Classification
on NewsDiscourse
One Classifier for All Ambiguous Words: Overcoming Data Sparsity by Utilizing Sense Correlations Across Words
Most supervised word sense disambiguation (WSD) systems build word-specific classifiers by leveraging labeled data.
In Plain Sight: Media Bias Through the Lens of Factual Reporting
The increasing prevalence of political bias in news media calls for greater public awareness of it, as well as robust methods for its detection.
Modeling Document-level Causal Structures for Event Causal Relation Identification
We aim to comprehensively identify all the event causal relations in a document, both within a sentence and across sentences, which is important for reconstructing pivotal event structures.
Improving Dialogue State Tracking by Discerning the Relevant Context
Specifically, we use the current user utterance and the most recent system utterance to determine the relevance of a system utterance.
Improving Event Coreference Resolution by Modeling Correlations between Event Coreference Chains and Document Topic Structures
This paper proposes a novel approach for event coreference resolution that models correlations between event coreference chains and document topical structures through an Integer Linear Programming formulation.
Identifying the Most Dominant Event in a News Article by Mining Event Coreference Relations
Identifying the most dominant and central event of a document, which governs and connects other foreground and background events in the document, is useful for many applications, such as text summarization, storyline generation and text segmentation.
TAMU at KBP 2017: Event Nugget Detection and Coreference Resolution
Our simple system designed using minimal features achieved the micro-average F1 scores of 57. 72, 44. 27 and 42. 47 for event span detection, type identification and realis status classification tasks respectively.
A Sequential Model for Classifying Temporal Relations between Intra-Sentence Events
We present a sequential model for temporal relation classification between intra-sentence events.
Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events
We introduce a novel iterative approach for event coreference resolution that gradually builds event clusters by exploiting inter-dependencies among event mentions within the same chain as well as across event chains.
