Related papers: Narrative Incoherence Detection
In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach…
The effectiveness of a language model is influenced by its token representations, which must encode contextual information and handle the same word form having a plurality of meanings (polysemy). Currently, none of the common language…
Automated discourse analysis tools based on Natural Language Processing (NLP) aiming at the diagnosis of language-impairing dementias generally extract several textual metrics of narrative transcripts. However, the absence of sentence…
Fraud detection is a difficult problem that can benefit from predictive modeling. However, the verification of a prediction is challenging; for a single insurance policy, the model only provides a prediction score. We present a case study…
Recent work has explored the syntactic abilities of RNNs using the subject-verb agreement task, which diagnoses sensitivity to sentence structure. RNNs performed this task well in common cases, but faltered in complex sentences (Linzen et…
Many applications of large language models (LLMs) require long-context understanding, but models continue to struggle with such tasks. We hypothesize that conventional next-token prediction training could contribute to this, because each…
Semantic consistency recognition aims to detect and judge whether the semantics of two text sentences are consistent with each other. However, the existing methods usually encounter the challenges of synonyms, polysemy and difficulty to…
Argument Unit Recognition and Classification aims at identifying argument units from text and classifying them as pro or against. One of the design choices that need to be made when developing systems for this task is what the unit of…
In hierarchical text classification, we perform a sequence of inference steps to predict the category of a document from top to bottom of a given class taxonomy. Most of the studies have focused on developing novels neural network…
Accuracy is one of the basic principles of journalism. However, it is increasingly hard to manage due to the diversity of news media. Some editors of online news tend to use catchy headlines which trick readers into clicking. These…
Finding attackable sentences in an argument is the first step toward successful refutation in argumentation. We present a first large-scale analysis of sentence attackability in online arguments. We analyze driving reasons for attacks in…
The CLEF 2019 ProtestNews Lab tasks participants to identify text relating to political protests within larger corpora of news data. Three tasks include article classification, sentence detection, and event extraction. I apply multitask…
As large-scale, pre-trained language models achieve human-level and superhuman accuracy on existing language understanding tasks, statistical bias in benchmark data and probing studies have recently called into question their true…
As the body of research on machine narrative comprehension grows, there is a critical need for consideration of performance assessment strategies as well as the depth and scope of different benchmark tasks. Based on narrative theories,…
Text detection, the key technology for understanding scene text, has become an attractive research topic. For detecting various scene texts, researchers propose plenty of detectors with different advantages: detection-based models enjoy…
Despite their growing capabilities, language models still frequently reproduce content from their training data, generate repetitive text, and favor common grammatical patterns and vocabulary. A possible cause is the decoding strategy: the…
Extracting and identifying latent topics in large text corpora has gained increasing importance in Natural Language Processing (NLP). Most models, whether probabilistic models similar to Latent Dirichlet Allocation (LDA) or neural topic…
In lexical semantics, full-sentence segmentation and segment labeling of various phenomena are generally treated separately, despite their interdependence. We hypothesize that a unified lexical semantic recognition task is an effective way…
We identify agreement and disagreement between utterances that express stances towards a topic of discussion. Existing methods focus mainly on conversational settings, where dialogic features are used for (dis)agreement inference. We extend…
While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often results in a degradation of their original performance. Some…